Not in the top 1,000 by GitHub stars
rohasnagpal/legal-ai-skills
Set Up an AI-Powered Full-Service Law Firm in 90 Seconds
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/adr-brief-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/adversarial-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/appeal-grounds-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitral-award-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitral-award-enforcement-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitration-clause-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitration-interim-relief-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitration-notice-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitration-pleading-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arbitrator-appointment-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/arrest-rights-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/ask-vclo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/assumption-flagger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/authority-validator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/avoidance-transaction-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/award-challenge-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/bail-advisor-and-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/board-resolution-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/breach-response-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/brief-to-counsel-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/builder-buyer-agreement-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cap-table-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/case-law-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/caucus-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cease-desist-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/chain-of-custody-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/chargesheet-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cheque-dishonour-complaint-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cheque-dishonour-notice-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/child-custody-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/chronology-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cirp-timeline-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/citation-integrity-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/claim-verification-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/clause-comparator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/client-intake/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/client-update-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/closing-checklist-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/closure-report-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/coc-decision-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/commercial-suit-filing-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/comparative-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/compensation-quantifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/compliance-obligations-mapper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/conciliation-proposal-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/conflict-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/consistency-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/constitutional-rights-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/construction-delay-defect-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/consumer-appeal-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/consumer-complaint-eligibility-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/consumer-pleading-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/contract-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/contract-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/contract-summariser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/costing-estimator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/court-order-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/covenant-monitor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/creditor-claim-preparer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/criminal-appeal-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/criminal-complaint-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/criminal-evidence-admissibility-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cross-border-transfer-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/cross-examination-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/damages-quantifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/data-processing-agreement-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/deal-structure-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/decree-execution-and-enforcement-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/defence-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/deficiency-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/demand-notice-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/development-agreement-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/digital-evidence-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/discharge-application-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/disciplinary-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/disclosure-request-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/divorce-grounds-assessor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/document-review-protocol-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/domestic-violence-remedies-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/dpdp-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/dpia-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/ecommerce-consumer-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/employment-contract-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/encumbrance-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/engagement-letter-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/england-wales-civil-claim-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/england-wales-pre-action-protocol-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/esop-scheme-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/evidence-organizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/examination-response-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/facility-agreement-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/family-court-procedure-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/fema-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/financial-services-licensing-assessor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/forum-jurisdiction-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/founders-agreement-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/fraud-pattern-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/government-contract-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/gst-compliance-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/guarantee-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/handbook-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/hello-rohas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/indemnity-liability-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/india-counsel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/india-legal-notice-response-strategist/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/infringement-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/input-tax-credit-dispute-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/insolvency-appeal-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/insolvency-options-assessor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/interim-application-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/investigation-report-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/investment-and-shareholder-agreement-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/ip-assignment-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/ip-portfolio-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/issue-spotter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/labour-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/land-use-zoning-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/learn-law-with-rohas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/lease-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-document-producer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-exam-prep-with-rohas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-hold-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-notice-analyser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-opinion-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-research-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legal-risk-assessor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/legislative-history-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/licence-application-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/limitation-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/liquidation-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/listing-obligations-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/litigation-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/litigation-viability-assessor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/loan-agreement-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/loan-default-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/m-and-a-diligence-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/maintenance-calculator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/matrimonial-petition-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/matrimonial-property-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/matter-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/mediation-opening-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/minutes-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/moratorium-impact-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/negotiation-position-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/notice-reply-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/obligations-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/offence-ingredients-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/operational-creditor-application-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/osint-collector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/party-interest-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/personal-guarantor-insolvency-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/pil-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/plaint-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/pleadings-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/policy-note-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/posh-compliance-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/pre-institution-mediation-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/precedent-mapper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/privacy-policy-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/privilege-log-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/procedural-order-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/product-liability-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/production-set-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/quashing-petition-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/recovery-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/redaction-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/redline-proposer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/regulatory-appeal-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/regulatory-applicability-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/regulatory-change-monitor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/regulatory-filing-preparer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/related-party-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/rera-complaint-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/rera-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/research-synthesiser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/resolution-plan-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/restructuring-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/rti-appeal-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/rti-application-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/sale-deed-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/sanctions-screening-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/sarfaesi-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/secretarial-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/secured-creditor-priority-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/securities-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/security-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/sentencing-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/separation-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/settlement-deed-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/settlement-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/settlement-evaluator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/settlement-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/should-i-sue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/stamp-duty-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/startup-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/statutory-interpreter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/succession-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tax-appeal-grounds-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tax-assessment-reply-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tax-litigation-strategy-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tax-notice-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tenancy-dispute-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/tender-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/termination-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/time-narrative-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/title-diligence-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/trademark-opposition-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/transaction-document-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/transaction-tracer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/transfer-pricing-documenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/treaty-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/trial-readiness-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/uk-companies-act-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/uk-counsel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/uk-data-protection-compliance-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/uk-employment-law-applicability-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/uk-insolvency-applicability-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-counsel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-employment-law-applicability-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-federal-civil-procedure-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-federal-state-issue-mapper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-privacy-law-applicability-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-sec-reporting-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/us-state-law-research-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/whistleblower-report-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/will-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/witness-statement-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/writ-petition-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/written-statement-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
plugins/legal-ai-skills/skills/written-submissions-drafter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
ad5df1934e98 → ad5df1934e98
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ad5df1934e98
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit ad5df1934e981f9aa1c2c163da02590d8ae0504c
git clone --filter=blob:none --no-checkout https://github.com/rohasnagpal/legal-ai-skills.git .hotskills/rohasnagpal-legal-ai-skills && git -C .hotskills/rohasnagpal-legal-ai-skills checkout --detach ad5df1934e981f9aa1c2c163da02590d8ae0504c
# Copy each selected skill directory from .hotskills/rohasnagpal-legal-ai-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/rohasnagpal/legal-ai-skills.git .hotskills/rohasnagpal-legal-ai-skills && git -C .hotskills/rohasnagpal-legal-ai-skills checkout --detach ad5df1934e981f9aa1c2c163da02590d8ae0504c
# Copy each selected skill directory from .hotskills/rohasnagpal-legal-ai-skills into .agents/skills/<skill-name>/201GitHub stars
4stars in 7 days
232skills in this repository
13commits in 30 days
Heat
4.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- administrative-action-challenge-analyst
plugins/legal-ai-skills/skills/administrative-action-challenge-analyst - adr-brief-drafter
plugins/legal-ai-skills/skills/adr-brief-drafter - adversarial-reviewer
plugins/legal-ai-skills/skills/adversarial-reviewer - appeal-grounds-drafter
plugins/legal-ai-skills/skills/appeal-grounds-drafter - arbitral-award-analyst
plugins/legal-ai-skills/skills/arbitral-award-analyst - arbitral-award-enforcement-advisor
plugins/legal-ai-skills/skills/arbitral-award-enforcement-advisor - arbitration-clause-reviewer
plugins/legal-ai-skills/skills/arbitration-clause-reviewer - arbitration-interim-relief-drafter
plugins/legal-ai-skills/skills/arbitration-interim-relief-drafter - arbitration-notice-drafter
plugins/legal-ai-skills/skills/arbitration-notice-drafter - arbitration-pleading-drafter
plugins/legal-ai-skills/skills/arbitration-pleading-drafter - arbitrator-appointment-advisor
plugins/legal-ai-skills/skills/arbitrator-appointment-advisor - arrest-rights-advisor
plugins/legal-ai-skills/skills/arrest-rights-advisor - ask-vclo
plugins/legal-ai-skills/skills/ask-vclo - assumption-flagger
plugins/legal-ai-skills/skills/assumption-flagger - authority-validator
plugins/legal-ai-skills/skills/authority-validator - avoidance-transaction-analyst
plugins/legal-ai-skills/skills/avoidance-transaction-analyst - award-challenge-analyst
plugins/legal-ai-skills/skills/award-challenge-analyst - bail-advisor-and-drafter
plugins/legal-ai-skills/skills/bail-advisor-and-drafter - board-resolution-drafter
plugins/legal-ai-skills/skills/board-resolution-drafter - breach-response-planner
plugins/legal-ai-skills/skills/breach-response-planner - brief-to-counsel-drafter
plugins/legal-ai-skills/skills/brief-to-counsel-drafter - builder-buyer-agreement-reviewer
plugins/legal-ai-skills/skills/builder-buyer-agreement-reviewer - cap-table-analyst
plugins/legal-ai-skills/skills/cap-table-analyst - case-law-analyst
plugins/legal-ai-skills/skills/case-law-analyst - caucus-strategy-planner
plugins/legal-ai-skills/skills/caucus-strategy-planner - cease-desist-drafter
plugins/legal-ai-skills/skills/cease-desist-drafter - chain-of-custody-documenter
plugins/legal-ai-skills/skills/chain-of-custody-documenter - chargesheet-analyst
plugins/legal-ai-skills/skills/chargesheet-analyst - cheque-dishonour-complaint-drafter
plugins/legal-ai-skills/skills/cheque-dishonour-complaint-drafter - cheque-dishonour-notice-drafter
plugins/legal-ai-skills/skills/cheque-dishonour-notice-drafter - child-custody-planner
plugins/legal-ai-skills/skills/child-custody-planner - chronology-builder
plugins/legal-ai-skills/skills/chronology-builder - cirp-timeline-checker
plugins/legal-ai-skills/skills/cirp-timeline-checker - citation-integrity-checker
plugins/legal-ai-skills/skills/citation-integrity-checker - claim-verification-analyst
plugins/legal-ai-skills/skills/claim-verification-analyst - clause-comparator
plugins/legal-ai-skills/skills/clause-comparator - client-intake
plugins/legal-ai-skills/skills/client-intake - client-update-drafter
plugins/legal-ai-skills/skills/client-update-drafter - closing-checklist-builder
plugins/legal-ai-skills/skills/closing-checklist-builder - closure-report-drafter
plugins/legal-ai-skills/skills/closure-report-drafter - coc-decision-analyst
plugins/legal-ai-skills/skills/coc-decision-analyst - commercial-suit-filing-checker
plugins/legal-ai-skills/skills/commercial-suit-filing-checker - comparative-analyst
plugins/legal-ai-skills/skills/comparative-analyst - compensation-quantifier
plugins/legal-ai-skills/skills/compensation-quantifier - compliance-obligations-mapper
plugins/legal-ai-skills/skills/compliance-obligations-mapper - conciliation-proposal-drafter
plugins/legal-ai-skills/skills/conciliation-proposal-drafter - conflict-checker
plugins/legal-ai-skills/skills/conflict-checker - consistency-checker
plugins/legal-ai-skills/skills/consistency-checker - constitutional-rights-analyst
plugins/legal-ai-skills/skills/constitutional-rights-analyst - construction-delay-defect-analyst
plugins/legal-ai-skills/skills/construction-delay-defect-analyst - consumer-appeal-drafter
plugins/legal-ai-skills/skills/consumer-appeal-drafter - consumer-complaint-eligibility-checker
plugins/legal-ai-skills/skills/consumer-complaint-eligibility-checker - consumer-pleading-drafter
plugins/legal-ai-skills/skills/consumer-pleading-drafter - contract-drafter
plugins/legal-ai-skills/skills/contract-drafter - contract-reviewer
plugins/legal-ai-skills/skills/contract-reviewer - contract-summariser
plugins/legal-ai-skills/skills/contract-summariser - costing-estimator
plugins/legal-ai-skills/skills/costing-estimator - court-order-compliance-checker
plugins/legal-ai-skills/skills/court-order-compliance-checker - covenant-monitor
plugins/legal-ai-skills/skills/covenant-monitor - creditor-claim-preparer
plugins/legal-ai-skills/skills/creditor-claim-preparer - criminal-appeal-planner
plugins/legal-ai-skills/skills/criminal-appeal-planner - criminal-complaint-analyst
plugins/legal-ai-skills/skills/criminal-complaint-analyst - criminal-evidence-admissibility-analyst
plugins/legal-ai-skills/skills/criminal-evidence-admissibility-analyst - cross-border-transfer-analyst
plugins/legal-ai-skills/skills/cross-border-transfer-analyst - cross-examination-planner
plugins/legal-ai-skills/skills/cross-examination-planner - damages-quantifier
plugins/legal-ai-skills/skills/damages-quantifier - data-processing-agreement-reviewer
plugins/legal-ai-skills/skills/data-processing-agreement-reviewer - deal-structure-analyst
plugins/legal-ai-skills/skills/deal-structure-analyst - decree-execution-and-enforcement-drafter
plugins/legal-ai-skills/skills/decree-execution-and-enforcement-drafter - defence-strategy-planner
plugins/legal-ai-skills/skills/defence-strategy-planner - deficiency-analyst
plugins/legal-ai-skills/skills/deficiency-analyst - demand-notice-drafter
plugins/legal-ai-skills/skills/demand-notice-drafter - development-agreement-reviewer
plugins/legal-ai-skills/skills/development-agreement-reviewer - digital-evidence-reviewer
plugins/legal-ai-skills/skills/digital-evidence-reviewer - discharge-application-drafter
plugins/legal-ai-skills/skills/discharge-application-drafter - disciplinary-documenter
plugins/legal-ai-skills/skills/disciplinary-documenter - disclosure-request-drafter
plugins/legal-ai-skills/skills/disclosure-request-drafter - divorce-grounds-assessor
plugins/legal-ai-skills/skills/divorce-grounds-assessor - document-review-protocol-builder
plugins/legal-ai-skills/skills/document-review-protocol-builder - domestic-violence-remedies-advisor
plugins/legal-ai-skills/skills/domestic-violence-remedies-advisor - dpdp-compliance-checker
plugins/legal-ai-skills/skills/dpdp-compliance-checker - dpia-documenter
plugins/legal-ai-skills/skills/dpia-documenter - ecommerce-consumer-compliance-checker
plugins/legal-ai-skills/skills/ecommerce-consumer-compliance-checker - employment-contract-drafter
plugins/legal-ai-skills/skills/employment-contract-drafter - encumbrance-analyst
plugins/legal-ai-skills/skills/encumbrance-analyst - engagement-letter-drafter
plugins/legal-ai-skills/skills/engagement-letter-drafter - england-wales-civil-claim-drafter
plugins/legal-ai-skills/skills/england-wales-civil-claim-drafter - england-wales-pre-action-protocol-checker
plugins/legal-ai-skills/skills/england-wales-pre-action-protocol-checker - esop-scheme-drafter
plugins/legal-ai-skills/skills/esop-scheme-drafter - evidence-organizer
plugins/legal-ai-skills/skills/evidence-organizer - examination-response-drafter
plugins/legal-ai-skills/skills/examination-response-drafter - facility-agreement-drafter
plugins/legal-ai-skills/skills/facility-agreement-drafter - family-court-procedure-checker
plugins/legal-ai-skills/skills/family-court-procedure-checker - fema-analyst
plugins/legal-ai-skills/skills/fema-analyst - financial-services-licensing-assessor
plugins/legal-ai-skills/skills/financial-services-licensing-assessor - forum-jurisdiction-analyst
plugins/legal-ai-skills/skills/forum-jurisdiction-analyst - founders-agreement-drafter
plugins/legal-ai-skills/skills/founders-agreement-drafter - fraud-pattern-analyst
plugins/legal-ai-skills/skills/fraud-pattern-analyst - government-contract-reviewer
plugins/legal-ai-skills/skills/government-contract-reviewer - gst-compliance-analyst
plugins/legal-ai-skills/skills/gst-compliance-analyst - guarantee-analyst
plugins/legal-ai-skills/skills/guarantee-analyst - handbook-drafter
plugins/legal-ai-skills/skills/handbook-drafter - hello-rohas
plugins/legal-ai-skills/skills/hello-rohas - indemnity-liability-analyst
plugins/legal-ai-skills/skills/indemnity-liability-analyst - india-counsel
plugins/legal-ai-skills/skills/india-counsel - india-legal-notice-response-strategist
plugins/legal-ai-skills/skills/india-legal-notice-response-strategist - infringement-analyst
plugins/legal-ai-skills/skills/infringement-analyst - input-tax-credit-dispute-analyst
plugins/legal-ai-skills/skills/input-tax-credit-dispute-analyst - insolvency-appeal-drafter
plugins/legal-ai-skills/skills/insolvency-appeal-drafter - insolvency-options-assessor
plugins/legal-ai-skills/skills/insolvency-options-assessor - interim-application-drafter
plugins/legal-ai-skills/skills/interim-application-drafter - investigation-report-drafter
plugins/legal-ai-skills/skills/investigation-report-drafter - investment-and-shareholder-agreement-reviewer
plugins/legal-ai-skills/skills/investment-and-shareholder-agreement-reviewer - ip-assignment-drafter
plugins/legal-ai-skills/skills/ip-assignment-drafter - ip-portfolio-analyst
plugins/legal-ai-skills/skills/ip-portfolio-analyst - issue-spotter
plugins/legal-ai-skills/skills/issue-spotter - labour-compliance-checker
plugins/legal-ai-skills/skills/labour-compliance-checker - land-use-zoning-advisor
plugins/legal-ai-skills/skills/land-use-zoning-advisor - learn-law-with-rohas
plugins/legal-ai-skills/skills/learn-law-with-rohas - lease-reviewer
plugins/legal-ai-skills/skills/lease-reviewer - legal-document-producer
plugins/legal-ai-skills/skills/legal-document-producer - legal-exam-prep-with-rohas
plugins/legal-ai-skills/skills/legal-exam-prep-with-rohas - legal-explainer
plugins/legal-ai-skills/skills/legal-explainer - legal-hold-planner
plugins/legal-ai-skills/skills/legal-hold-planner - legal-notice-analyser
plugins/legal-ai-skills/skills/legal-notice-analyser - legal-opinion-drafter
plugins/legal-ai-skills/skills/legal-opinion-drafter - legal-research-planner
plugins/legal-ai-skills/skills/legal-research-planner - legal-risk-assessor
plugins/legal-ai-skills/skills/legal-risk-assessor - legislative-history-analyst
plugins/legal-ai-skills/skills/legislative-history-analyst - licence-application-drafter
plugins/legal-ai-skills/skills/licence-application-drafter - limitation-checker
plugins/legal-ai-skills/skills/limitation-checker - liquidation-documenter
plugins/legal-ai-skills/skills/liquidation-documenter - listing-obligations-checker
plugins/legal-ai-skills/skills/listing-obligations-checker - litigation-strategy-planner
plugins/legal-ai-skills/skills/litigation-strategy-planner - litigation-viability-assessor
plugins/legal-ai-skills/skills/litigation-viability-assessor - loan-agreement-reviewer
plugins/legal-ai-skills/skills/loan-agreement-reviewer - loan-default-analyst
plugins/legal-ai-skills/skills/loan-default-analyst - m-and-a-diligence-checker
plugins/legal-ai-skills/skills/m-and-a-diligence-checker - maintenance-calculator
plugins/legal-ai-skills/skills/maintenance-calculator - matrimonial-petition-drafter
plugins/legal-ai-skills/skills/matrimonial-petition-drafter - matrimonial-property-analyst
plugins/legal-ai-skills/skills/matrimonial-property-analyst - matter-planner
plugins/legal-ai-skills/skills/matter-planner - mediation-opening-drafter
plugins/legal-ai-skills/skills/mediation-opening-drafter - minutes-drafter
plugins/legal-ai-skills/skills/minutes-drafter - moratorium-impact-analyst
plugins/legal-ai-skills/skills/moratorium-impact-analyst - negotiation-position-planner
plugins/legal-ai-skills/skills/negotiation-position-planner - notice-reply-drafter
plugins/legal-ai-skills/skills/notice-reply-drafter - obligations-extractor
plugins/legal-ai-skills/skills/obligations-extractor - offence-ingredients-analyst
plugins/legal-ai-skills/skills/offence-ingredients-analyst - operational-creditor-application-drafter
plugins/legal-ai-skills/skills/operational-creditor-application-drafter - osint-collector
plugins/legal-ai-skills/skills/osint-collector - party-interest-analyst
plugins/legal-ai-skills/skills/party-interest-analyst - personal-guarantor-insolvency-analyst
plugins/legal-ai-skills/skills/personal-guarantor-insolvency-analyst - pil-drafter
plugins/legal-ai-skills/skills/pil-drafter - plaint-drafter
plugins/legal-ai-skills/skills/plaint-drafter - pleadings-analyst
plugins/legal-ai-skills/skills/pleadings-analyst - policy-note-drafter
plugins/legal-ai-skills/skills/policy-note-drafter - posh-compliance-advisor
plugins/legal-ai-skills/skills/posh-compliance-advisor - pre-institution-mediation-advisor
plugins/legal-ai-skills/skills/pre-institution-mediation-advisor - precedent-mapper
plugins/legal-ai-skills/skills/precedent-mapper - privacy-policy-drafter
plugins/legal-ai-skills/skills/privacy-policy-drafter - privilege-log-builder
plugins/legal-ai-skills/skills/privilege-log-builder - procedural-order-drafter
plugins/legal-ai-skills/skills/procedural-order-drafter - product-liability-analyst
plugins/legal-ai-skills/skills/product-liability-analyst - production-set-checker
plugins/legal-ai-skills/skills/production-set-checker - quashing-petition-drafter
plugins/legal-ai-skills/skills/quashing-petition-drafter - recovery-strategy-planner
plugins/legal-ai-skills/skills/recovery-strategy-planner - redaction-reviewer
plugins/legal-ai-skills/skills/redaction-reviewer - redline-proposer
plugins/legal-ai-skills/skills/redline-proposer - regulatory-appeal-planner
plugins/legal-ai-skills/skills/regulatory-appeal-planner - regulatory-applicability-analyst
plugins/legal-ai-skills/skills/regulatory-applicability-analyst - regulatory-change-monitor
plugins/legal-ai-skills/skills/regulatory-change-monitor - regulatory-filing-preparer
plugins/legal-ai-skills/skills/regulatory-filing-preparer - related-party-analyst
plugins/legal-ai-skills/skills/related-party-analyst - rera-complaint-drafter
plugins/legal-ai-skills/skills/rera-complaint-drafter - rera-compliance-checker
plugins/legal-ai-skills/skills/rera-compliance-checker - research-synthesiser
plugins/legal-ai-skills/skills/research-synthesiser - resolution-plan-reviewer
plugins/legal-ai-skills/skills/resolution-plan-reviewer - restructuring-documenter
plugins/legal-ai-skills/skills/restructuring-documenter - rti-appeal-drafter
plugins/legal-ai-skills/skills/rti-appeal-drafter - rti-application-drafter
plugins/legal-ai-skills/skills/rti-application-drafter - sale-deed-drafter
plugins/legal-ai-skills/skills/sale-deed-drafter - sanctions-screening-documenter
plugins/legal-ai-skills/skills/sanctions-screening-documenter - sarfaesi-advisor
plugins/legal-ai-skills/skills/sarfaesi-advisor - secretarial-compliance-checker
plugins/legal-ai-skills/skills/secretarial-compliance-checker - secured-creditor-priority-analyst
plugins/legal-ai-skills/skills/secured-creditor-priority-analyst - securities-compliance-checker
plugins/legal-ai-skills/skills/securities-compliance-checker - security-documenter
plugins/legal-ai-skills/skills/security-documenter - sentencing-analyst
plugins/legal-ai-skills/skills/sentencing-analyst - separation-documenter
plugins/legal-ai-skills/skills/separation-documenter - settlement-deed-drafter
plugins/legal-ai-skills/skills/settlement-deed-drafter - settlement-documenter
plugins/legal-ai-skills/skills/settlement-documenter - settlement-evaluator
plugins/legal-ai-skills/skills/settlement-evaluator - settlement-strategy-planner
plugins/legal-ai-skills/skills/settlement-strategy-planner - should-i-sue
plugins/legal-ai-skills/skills/should-i-sue - stamp-duty-analyst
plugins/legal-ai-skills/skills/stamp-duty-analyst - startup-compliance-checker
plugins/legal-ai-skills/skills/startup-compliance-checker - statutory-interpreter
plugins/legal-ai-skills/skills/statutory-interpreter - succession-advisor
plugins/legal-ai-skills/skills/succession-advisor - tax-appeal-grounds-drafter
plugins/legal-ai-skills/skills/tax-appeal-grounds-drafter - tax-assessment-reply-drafter
plugins/legal-ai-skills/skills/tax-assessment-reply-drafter - tax-litigation-strategy-planner
plugins/legal-ai-skills/skills/tax-litigation-strategy-planner - tax-notice-analyst
plugins/legal-ai-skills/skills/tax-notice-analyst - tenancy-dispute-analyst
plugins/legal-ai-skills/skills/tenancy-dispute-analyst - tender-compliance-checker
plugins/legal-ai-skills/skills/tender-compliance-checker - termination-analyst
plugins/legal-ai-skills/skills/termination-analyst - time-narrative-drafter
plugins/legal-ai-skills/skills/time-narrative-drafter - title-diligence-analyst
plugins/legal-ai-skills/skills/title-diligence-analyst - trademark-opposition-drafter
plugins/legal-ai-skills/skills/trademark-opposition-drafter - transaction-document-checker
plugins/legal-ai-skills/skills/transaction-document-checker - transaction-tracer
plugins/legal-ai-skills/skills/transaction-tracer - transfer-pricing-documenter
plugins/legal-ai-skills/skills/transfer-pricing-documenter - treaty-analyst
plugins/legal-ai-skills/skills/treaty-analyst - trial-readiness-checker
plugins/legal-ai-skills/skills/trial-readiness-checker - uk-companies-act-compliance-checker
plugins/legal-ai-skills/skills/uk-companies-act-compliance-checker - uk-counsel
plugins/legal-ai-skills/skills/uk-counsel - uk-data-protection-compliance-checker
plugins/legal-ai-skills/skills/uk-data-protection-compliance-checker - uk-employment-law-applicability-checker
plugins/legal-ai-skills/skills/uk-employment-law-applicability-checker - uk-insolvency-applicability-checker
plugins/legal-ai-skills/skills/uk-insolvency-applicability-checker - us-counsel
plugins/legal-ai-skills/skills/us-counsel - us-employment-law-applicability-checker
plugins/legal-ai-skills/skills/us-employment-law-applicability-checker - us-federal-civil-procedure-checker
plugins/legal-ai-skills/skills/us-federal-civil-procedure-checker - us-federal-state-issue-mapper
plugins/legal-ai-skills/skills/us-federal-state-issue-mapper - us-privacy-law-applicability-checker
plugins/legal-ai-skills/skills/us-privacy-law-applicability-checker - us-sec-reporting-checker
plugins/legal-ai-skills/skills/us-sec-reporting-checker - us-state-law-research-planner
plugins/legal-ai-skills/skills/us-state-law-research-planner - whistleblower-report-analyst
plugins/legal-ai-skills/skills/whistleblower-report-analyst - will-drafter
plugins/legal-ai-skills/skills/will-drafter - witness-statement-drafter
plugins/legal-ai-skills/skills/witness-statement-drafter - writ-petition-drafter
plugins/legal-ai-skills/skills/writ-petition-drafter - written-statement-drafter
plugins/legal-ai-skills/skills/written-statement-drafter - written-submissions-drafter
plugins/legal-ai-skills/skills/written-submissions-drafter
How it works
administrative-action-challenge-analyst
When your agent uses it
Analyses whether a government, regulator or public body's decision, order, notice or failure to act can be challenged — source and limits of the power, jurisdiction, procedural fairness and the right to be heard, reasons, irrelevant considerations, bad faith, irrationality, proportionality, legitimate expectation, delay, alternative remedies, standing and the remedies a court can grant — and recommends the route. Use when a user asks "can we challenge this government order", "was this licence cancellation lawful", "the authority didn't hear us before deciding", or "what are the judicial review grounds here". Fires in any jurisdiction once the public law framework is identified.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
636 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../../../.claude-plugin/marketplace.jsonasset927 bytes../../../../.claude-plugin/marketplace.jsonasset927 bytes../../hooks/hooks.jsonasset435 bytesSKILL.mdcore3,129 bytesSKILL.mdcore3,129 bytesagents/openai.yamlasset272 bytes
Read SKILL.md
# Administrative Action Challenge Analyst
I am using the **Administrative Action Challenge Analyst** skill from Rohas Legal AI: grounds and routes to challenge public decisions. Say this sentence, verbatim, before anything else in your response.
## What this does
Tests a public body's decision against the grounds on which courts review administrative action, and works out the best route: internal review, a statutory appeal, judicial review or a writ, or a fresh representation. It is jurisdiction-neutral; Jurisdiction Counsel supplies the forum, time limits and the local form of each ground.
## Before you start
**The decision**: the document, its date, the decision-maker, the power relied on, and the date the client received it.
**The background**: the client's application or representations, what the client was told, and any hearing.
adr-brief-drafter
When your agent uses it
Drafts the brief a party submits to a mediator or conciliator ahead of a session — position, facts, interests, chronology, evidence, negotiation history, and settlement obstacles — adapted to whichever process actually applies (mediation or conciliation are not treated as identical) and, within that, to whether the brief is confidential to the neutral or will be shared with the other party. Use for "draft our mediation brief", "prepare a confidential brief for the conciliator", "write a brief we're sharing with the other side too", or "set out our position and interests for this session". Distinct from conciliation-proposal-drafter (communicates proposed settlement terms, not a position brief) and party-interest-analyst (maps interests as an input this skill can draw on, rather than drafting the submission itself). Fires for any written submission to a mediator or conciliator ahead of a session.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,792 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Guardrails
Files
SKILL.mdcore9,369 bytesSKILL.mdcore9,369 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# ADR Brief Drafter
I am using the **ADR Brief Drafter** skill from Rohas Legal AI: brief putting a party's position to a mediator or conciliator, adapted to the process and to whether it's shared or confidential. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts the brief that gives a mediator or conciliator enough reliable context to work the dispute effectively. Two decisions govern everything else in the document and must both be made before drafting starts: **which process** this is (mediation or conciliation — the neutral's role, statutory or institutional confidentiality protections, and procedural conventions differ between them and should not be assumed interchangeable), and **who will read the brief** (confidential to the neutral only, or shared with the other party). Getting either wrong produces a document that either wastes its usefulness to the neutral or damages the party's position if the other side reads it.
## Before you start
**Which process — mediation or conciliation.** Ask, and do not assume they work the same way. Where the process is governed by a specific statutory or institutional framework (for example, conciliation under Part III of India's Arbitration and Conciliation Act, 1996, or a mediation conducted under the Mediation Act, 2023 or an institution's own rules), flag its confidentiality and disclosure provisions as a verification point rather than assuming a generic default.
**Whether the brief is confidential to the neutral only, or will be shared with the other party.** Blocking, and the first thing to confirm after the process itself — it changes what belongs in the document more than any other instruction could. If the user is not sure which they want, say plainly that this decision has to be made before drafting starts; a brief drafted for one purpose is not safely repurposed for the other.
adversarial-reviewer
When your agent uses it
Attacks a finished draft the way opposing counsel, a skeptical judge, or a regulator would — hunting for exploitable ambiguity, gaps, internal inconsistency, and unsupported assertions, and writing out the strongest counter-argument to the document's own conclusions. Use this as a final stress test before a document goes out — including phrasings like "attack this draft before we send it", "what would opposing counsel do with this", "poke holes in this opinion", "find the weakest point in this pleading", or "red-team this before we file it". It finds problems; it does not fix them — hand off to the relevant drafting or redline skill for that. Fires on any finished draft in any practice area — contracts, pleadings, opinions, notices.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
1,160 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,602 bytesagents/openai.yamlasset236 bytes
Read SKILL.md
# Adversarial Reviewer
I am using the **Adversarial Reviewer** skill from Rohas Legal AI: attacks your own draft the way opposing counsel would. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a finished draft and attacks it, deliberately adopting the perspective of whoever is positioned against it — opposing counsel, a skeptical judge, a regulator — rather than reviewing it neutrally. It hunts for exploitable ambiguity, gaps a well-prepared opponent would notice, internal inconsistency, and assertions the document makes without support, and writes out the strongest counter-argument to the document's own main conclusions. It does not fix what it finds; that is a different skill's job.
## Before you start
**The draft itself.** The finished document to attack. Blocking — there is nothing to stress-test without it.
**Who the adversarial perspective belongs to.** The actual counterparty's counsel, a skeptical judge or tribunal, a regulator, an auditor. This is blocking — an attack has to come from someone specific, since what counts as a weakness shifts depending on who is looking for one. Ask if it is not obvious from the document.
appeal-grounds-drafter
When your agent uses it
Draft and review grounds of appeal tied to challenged findings, preserved errors, the applicable standard of review, the record, prejudice, and relief. Use for civil, commercial, administrative, tribunal, or other appellate matters.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
721 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Calculations
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,567 bytesagents/openai.yamlasset277 bytes
Read SKILL.md
# Appeal Grounds Drafter
I am using the **Appeal Grounds Drafter** skill from Rohas Legal AI: record-linked grounds, preserved errors, standards of review and relief. Say this sentence, verbatim, before anything else in your response.
Draft grounds that identify an appealable error and its consequence. Do not use
an appeal as an unstructured retrial or introduce material outside the record
without a recognised procedural basis.
## Intake
Obtain the jurisdiction, appellate route, challenged judgment or order, decree,
reasons, lower record, pleadings, evidence, transcripts, objections, submissions,
issues, dates of decision and service, limitation position, permission or
certificate requirements, existing stay, client objective, and relief sought.arbitral-award-analyst
When your agent uses it
Reads an arbitral award and produces a neutral map of jurisdiction, issues, findings, reasoning, operative relief, interest, costs, compliance dates, corrections, and enforcement dependencies. Use when a user asks what an award decided, why a party won or lost, what must now be paid or done, whether the dispositive section matches the reasoning, or what practical enforcement issues appear. Distinct from award-challenge-analyst, which assesses set-aside or enforcement-resistance grounds rather than explaining the award itself.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
898 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,569 bytesagents/openai.yamlasset244 bytes
Read SKILL.md
# Arbitral Award Analyst
I am using the **Arbitral Award Analyst** skill from Rohas Legal AI: reads an award for findings, reasoning and enforceability. Say this sentence, verbatim, before anything else in your response.
## Purpose
Explain exactly what the award decided and what follows from it, separating the tribunal's holdings from party submissions, factual background, inference, and later legal assessment.
## Required inputs
Obtain the complete signed award, all separate or dissenting opinions, correction or interpretation decisions, relevant procedural orders, arbitration agreement, applicable rules, and any known enforcement or challenge context. Ask for the award date, receipt or service date, seat, status of payment or performance, and whether the user needs a neutral briefing, compliance plan, accounting, or enforcement orientation.
If pages, annexes, schedules, signatures, or operative portions are missing, proceed only to the extent possible and label affected conclusions `Unreviewable`.
arbitral-award-enforcement-advisor
When your agent uses it
Advises on recognition, challenge resistance and enforcement of an arbitral award in India, distinguishing domestic, India-seated international commercial and foreign awards. Use when the award, seat, debtor assets, challenge status and relevant dates are available.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
389 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore2,115 bytesSKILL.mdcore2,115 bytesagents/openai.yamlasset451 bytes
Read SKILL.md
# Arbitral Award Enforcement Advisor
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that Indian law governs the issue and identify the relevant State or Union territory and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
arbitration-clause-reviewer
When your agent uses it
Reviews an arbitration agreement for validity, scope, seat, venue, governing law, institutional rules, tribunal constitution, appointment mechanics, escalation steps, interim-relief routes, and drafting pathologies. Use when a user asks whether an arbitration clause works, is enforceable, is pathological, or should be revised, including requests such as "review this dispute-resolution clause", "which court supervises this arbitration", "does this clause specify a seat", or "fix the arbitrator appointment language". Use for clause-level analysis, not for commencing a dispute or assessing an award.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
915 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,904 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# Arbitration Clause Reviewer
I am using the **Arbitration Clause Reviewer** skill from Rohas Legal AI: checks a clause for seat, venue, rules, appointment and pathology. Say this sentence, verbatim, before anything else in your response.
## Purpose
Test whether the clause creates a workable arbitration process and identify exactly where ambiguity, invalidity, delay, or satellite litigation could arise. Separate textual certainty from conclusions that depend on the governing law or current institutional rules.
## Required inputs
Obtain the clause and every provision it incorporates or interacts with, including governing-law, notices, escalation, jurisdiction, and execution provisions. Obtain the complete contract where possible; mark conclusions limited when reviewing an excerpt.
Identify or ask for:
arbitration-interim-relief-drafter
When your agent uses it
Determines the correct interim-protection route for a dispute connected to arbitration — emergency arbitrator under institutional rules, tribunal-ordered measures once constituted, or court interim relief (including India's Sections 9 and 17 of the Arbitration and Conciliation Act, 1996) — then drafts the application for that route. Use when a user needs urgent protection, preservation of assets or evidence, security, an injunction, or receivership connected with arbitration, including phrasings like "we need emergency relief before the tribunal is formed", "draft a section 9 application", "should we go to the emergency arbitrator or to court", or "seek interim measures from the tribunal now that it's constituted". Covers India-specific court/tribunal analysis under the Arbitration and Conciliation Act, 1996 and institutional emergency-arbitrator rules for other seats. Distinct from arbitration-pleading-drafter, which pleads the merits rather than seeks temporary protection.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
1,613 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Step 1 — Choose the route
- Step 2 — Establish jurisdiction and maintainability (all routes)
- Step 3 — Build the substantive case (all routes)
- Output
- Guardrails
Files
SKILL.mdcore8,591 bytesagents/openai.yamlasset336 bytes
Read SKILL.md
# Arbitration Interim Relief Drafter
I am using the **Arbitration Interim Relief Drafter** skill from Rohas Legal AI: chooses the applicable emergency-arbitrator, tribunal, or court route and drafts the application. Say this sentence, verbatim, before anything else in your response.
## Purpose
Select the correct interim-protection route — emergency arbitrator, tribunal, or court — without treating urgency as a substitute for jurisdiction, evidence, or a remedy tailored to the threatened harm, then draft the application for the route chosen.
## Required inputs
Obtain the arbitration agreement, contract, amendments, seat, governing law, institution and applicable rule version (if any), status of invocation and tribunal constitution, the precise relief sought, threatened act, urgency, date of likely harm, evidence supporting the right asserted and the harm, asset or property location, respondent's conduct, prior notices, undertakings requested, related proceedings, existing orders, and service information.
Ask whether a request for arbitration has been or will be filed simultaneously, what harm will occur before an ordinary tribunal can act, and where an order would need recognition or practical compliance.
arbitration-notice-drafter
When your agent uses it
Drafts a notice invoking arbitration or request for arbitration, framing the disputes, contractual basis, relief, tribunal-appointment step, and service record without prematurely narrowing the claimant's case. Use when a user wants to commence arbitration, invoke an arbitration clause, submit an institutional request, nominate an arbitrator, or respond to a defective commencement notice. Distinct from arbitration-pleading-drafter, which pleads the merits after commencement, and arbitration-clause-reviewer, which diagnoses the clause rather than activates it.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
858 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,627 bytesagents/openai.yamlasset250 bytes
Read SKILL.md
# Arbitration Notice Drafter
I am using the **Arbitration Notice Drafter** skill from Rohas Legal AI: notice invoking arbitration, with the disputes properly framed. Say this sentence, verbatim, before anything else in your response.
## Purpose
Create an unequivocal, procedurally compliant commencement document that identifies the arbitration agreement and disputes, preserves the claimant's position, and triggers the correct appointment or institutional process.
## Required inputs
Obtain:
- the signed contract and arbitration agreement, including amendments;
- pre-arbitration escalation, notices, cure, and service provisions;arbitration-pleading-drafter
When your agent uses it
Drafts the merits pleadings in arbitration — statement of claim, statement of defence, counterclaim, and reply to counterclaim — with jurisdiction and admissibility objections, material facts, contractual and legal breaches, causation, quantum, and relief all tied to the evidentiary record. Use when a claimant needs its merits pleading, a respondent must answer a statement of claim and plead a counterclaim, or a claimant must reply to a counterclaim — including "draft our statement of claim", "draft our defence and counterclaim", "respond to this counterclaim", or "preserve our jurisdictional objection in the defence". Distinct from arbitration-notice-drafter (commences the case), interim-relief skills (temporary protection, not the merits), and award-challenge-analyst (challenges an award after it is issued, not a pleading before one).
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
1,780 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Before you start
- Required inputs (all pleadings)
- Method — Statement of claim
- Method — Statement of defence, counterclaim, and reply to counterclaim
- Guardrails
Files
SKILL.mdcore9,376 bytesSKILL.mdcore9,376 bytesSKILL.mdcore9,376 bytesSKILL.mdcore9,376 bytesSKILL.mdcore9,376 bytesagents/openai.yamlasset293 bytes
Read SKILL.md
# Arbitration Pleading Drafter
I am using the **Arbitration Pleading Drafter** skill from Rohas Legal AI: statement of claim, statement of defence, counterclaim and reply to counterclaim. Say this sentence, verbatim, before anything else in your response.
## Purpose
Produce a coherent merits pleading — for whichever side and stage is in play — in which every material allegation advances or answers an identified claim, every claim or defence connects to evidence and law, and every item of relief follows from the pleaded case and quantum record.
## Before you start
Determine which pleading is being drafted: **statement of claim** (claimant, opening the merits), **statement of defence** (respondent, answering a claim, with or without a counterclaim), or **reply to counterclaim** (claimant, answering a counterclaim pleaded against it). Ask if not stated.
## Required inputs (all pleadings)
arbitrator-appointment-advisor
When your agent uses it
Maps the contractual, institutional, and statutory process for constituting an arbitral tribunal and assesses arbitrator qualifications, eligibility, independence, impartiality, disclosures, challenges, vacancies, and replacement. Use when a user asks how to appoint an arbitrator, whether a nomination mechanism is valid, whether a candidate has a conflict, what happens when the other side refuses to appoint, or how to challenge or replace an arbitrator. Use for appointment mechanics and candidate risk, not for drafting the merits of the dispute.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
774 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,290 bytesagents/openai.yamlasset269 bytes
Read SKILL.md
# Arbitrator Appointment Advisor
I am using the **Arbitrator Appointment Advisor** skill from Rohas Legal AI: appointment mechanics, eligibility and independence disclosure. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn the arbitration agreement and applicable framework into a reliable appointment sequence, then assess candidate suitability and challenge risk without making unsupported conclusions about independence.
## Required inputs
Obtain the arbitration agreement, seat, governing law, current institutional rules, number of arbitrators, appointment correspondence, relevant dates, party structure, and status of the proceeding. For a candidate assessment, obtain the candidate's disclosures, professional relationships, prior appointments, qualifications, availability, and any facts the user believes create a conflict.
Ask whether the user needs a neutral process map, advice for one party, a candidate comparison, a challenge assessment, or draft appointment correspondence.
arrest-rights-advisor
When your agent uses it
Advises a person who has been arrested, detained, summoned for questioning or fears arrest on their rights and immediate steps — grounds of arrest, the right to a lawyer and to inform family, silence and self-incrimination, time limits for production before a court, medical examination, search and seizure, notices to appear, and how to respond to police — under the criminal procedure confirmed by jurisdiction counsel. Use when a user says "the police have arrested my brother", "I've been called for questioning", "can the police hold me without charge", "do I have to answer their questions", or "the police want to search my house". Fires in any jurisdiction; urgent.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
860 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,050 bytesSKILL.mdcore4,050 bytesagents/openai.yamlasset244 bytes
Read SKILL.md
# Arrest Rights Advisor
I am using the **Arrest Rights Advisor** skill from Rohas Legal AI: rights and immediate steps on arrest, detention or questioning. Say this sentence, verbatim, before anything else in your response.
## What this does
Gives a person who is arrested, detained, questioned or at risk of arrest, or their family, a clear account of the rights that apply and the steps to take now. It acts for the person in or facing custody. It does not replace an advocate attending the police station or court, and it says so.
## Before you start
**Urgency. Ask first.** Is the person in custody now, and since when? Custody time limits may be running.
**Jurisdiction and State.** Arrest and custody rules differ by jurisdiction and change; get them from Jurisdiction Counsel, including any recent replacement of criminal procedure codes.
ask-vclo
When your agent uses it
Legacy alias for the former vCLO product name, kept for one release so existing prompts keep working. Invoke whenever the user's prompt contains vCLO, VCLO, cVLO, cvlo or virtual CLO, including a greeting with no legal task. Hands over to hello-rohas, which runs the Legal AI Skills law firm. Do not use when the prompt does not mention vCLO.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
239 tokensWhen the skill is activated
Reference documents
2,131 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore971 bytesagents/openai.yamlasset265 bytes../hello-rohas/SKILL.mddoc8,990 bytes
Read SKILL.md
# vCLO (legacy alias)
vCLO is now **Legal AI Skills by Rohas Nagpal**, and the Chief Legal Officer is now the Managing Partner.
Read and follow the [hello-rohas instructions](../hello-rohas/SKILL.md), treating the user's message as if it were addressed to Rohas:
- for a greeting such as "Hello vCLO", use its welcome mode and add " (formerly vCLO)" after the firm name;
- for a legal matter, use its matter mode and run the matter as the Managing Partner.
This alias will be removed in a future release. Tell the user once, at the end of the reply, that they can now say "Hello Rohas".assumption-flagger
When your agent uses it
Surfaces every assumption a draft depends on — factual, legal, definitional, about another party's future conduct, or about scope — whether the document states them or not, so they can be verified or challenged before anyone relies on it. Use this as an independent audit pass on any document — including phrasings like "what is this opinion actually assuming", "surface every assumption in this risk assessment", "what would have to be true for this conclusion to hold", "audit this draft for unstated premises", or "check what this document is taking for granted". Works on documents from any source, not just this practice pack's own outputs — an opinion received from other counsel, a judgment, an external draft. Fires on any document whose conclusions rest on premises worth checking before relying on it.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
951 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore4,724 bytesSKILL.mdcore4,724 bytesagents/openai.yamlasset210 bytes
Read SKILL.md
# Assumption Flagger
I am using the **Assumption Flagger** skill from Rohas Legal AI: surfaces every assumption a draft depends on. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a document and surfaces every assumption its conclusions actually depend on — whether the document states the assumption openly or simply proceeds as if it were true. For each one, it says what would change if the assumption turned out to be wrong, and whether the document's bottom line depends on it or not. It does not verify or resolve any assumption; it only makes the unstated ones visible.
## Before you start
**The document to audit.** Blocking — there is nothing to flag without it.
Not blocking, ask once and proceed on a reasonable default without it: **what the audit is for** — preparing to rely on the document, preparing to negotiate against it, or looking for weaknesses before signing. This shapes emphasis, not the method.
authority-validator
When your agent uses it
Tests whether each authority cited in a document actually supports the proposition it is cited for, remains good law, and is binding or merely persuasive in the forum the document is directed at — a substantive validity check, beyond confirming a citation exists and is quoted accurately. Use for "does this case actually support what we're citing it for", "is this authority still good law", "check whether these citations are binding on this court or just persuasive", or "stress-test the authorities in this opinion before we rely on them". Distinct from citation-integrity-checker (existence/accuracy only) and precedent-mapper (maps a body of authorities' relationships, not a specific document's citations for a specific use). Fires on any document whose citations need substantive validation before reliance.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
1,170 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore6,090 bytesagents/openai.yamlasset290 bytes
Read SKILL.md
# Authority Validator
I am using the **Authority Validator** skill from Rohas Legal AI: tests whether a cited authority actually supports the point, is still good law, and binds this forum. Say this sentence, verbatim, before anything else in your response.
## Purpose
Go beyond confirming a citation exists and is quoted accurately, to test whether it actually does the work the document asks of it: does the authority stand for the proposition cited, is it still good law, and does it bind (or merely persuade) the forum the document is directed at. A citation that exists, is accurately quoted, and is nonetheless being asked to support a proposition it does not actually establish is a more dangerous defect than a fabricated one, because it survives a surface check.
## Required inputs
Obtain the document containing the citations to be validated, and the forum the document is directed at (which court, tribunal, or regulator, and its position in the relevant hierarchy) — blocking, since binding-versus-persuasive status cannot be assessed without knowing the forum.
Where research tools or retrieval are available this session, use them to retrieve the actual text of each authority. Where they are not, or a specific authority cannot be retrieved, say so explicitly and produce a structured checklist of what needs manual verification rather than asserting a validation result that was not actually performed.
avoidance-transaction-analyst
When your agent uses it
Analyses Indian insolvency transactions for preference, undervalue, extortionate credit and fraudulent or wrongful trading exposure. Use for RP or liquidator reviews, transaction audits, applications, defences, recoveries or resolution-plan diligence.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
808 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,411 bytesagents/openai.yamlasset318 bytes
Read SKILL.md
# Avoidance Transaction Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Avoidance Transaction Analyst** skill from Rohas Legal AI: preferential, undervalued and fraudulent transactions (India). Say this sentence, verbatim, before anything else in your response.
Test each transaction against the Insolvency and Bankruptcy Code, 2016 and current regulations as of the analysis date. Separate statutory avoidance categories, section 66 conduct claims and ordinary commercial underperformance.award-challenge-analyst
When your agent uses it
Assesses routes and grounds to set aside, annul, appeal, stay, or resist recognition or enforcement of an arbitral award, mapping each ground to the governing law, procedural record, evidence, waiver, prejudice, remedy, and deadline. Use when a user asks whether an award can be challenged, how to oppose enforcement, whether tribunal excess or due-process defects matter, or what must be filed urgently after receiving an award. Distinct from arbitral-award-analyst, which neutrally explains what the award decided.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
952 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,950 bytesSKILL.mdcore4,950 bytesagents/openai.yamlasset254 bytes
Read SKILL.md
# Award Challenge Analyst
I am using the **Award Challenge Analyst** skill from Rohas Legal AI: assesses the grounds available to challenge or resist an award. Say this sentence, verbatim, before anything else in your response.
## Purpose
Determine which post-award route is legally available, time-sensitive, and supported by the record. Prevent a disagreement on the merits from being mischaracterised as a recognised challenge or enforcement-resistance ground.
## Required inputs
Obtain:
- the complete award, separate opinions, corrections, and proof of receipt;
- the arbitration agreement, seat, applicable rules, and governing law;bail-advisor-and-drafter
When your agent uses it
Determines the correct bail posture in India — anticipatory (pre-arrest), or regular, interim, statutory/default, medical, or appellate (post-arrest) — advises on strategy and evidence, and drafts the application when requested. Use when a person fears arrest, has received a notice, summons, or is named in an FIR (anticipatory posture); or is already arrested or in custody and needs an application, custody calculation, or hearing note (post-arrest posture) — including "will anticipatory bail work here", "draft our bail application", "we've been arrested, what are our options", "check if default bail is available", or "draft the appellate bail application". India-specific; retrieves current statutory text and controlling authority rather than relying on memory. Distinct from quashing-petition-drafter (attacks the proceeding itself, not custody) and legal-ai-skills:defence-strategy-planner (whole-case strategy, not the bail question specifically).
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
1,847 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Step 1 — Determine the posture
- Required inputs (both postures)
- Method — Anticipatory posture
- Method — Post-arrest posture
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore9,646 bytesagents/openai.yamlasset323 bytes
Read SKILL.md
# Bail Advisor and Drafter (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Bail Advisor and Drafter** skill from Rohas Legal AI: anticipatory or post-arrest bail — strategy, and drafting when requested (India). Say this sentence, verbatim, before anything else in your response.
## Purposeboard-resolution-drafter
When your agent uses it
Drafts board, committee, shareholder, member, and written-consent resolutions with correct authority, approval level, quorum, conflicts, conditions, delegations, filing actions, and certification language. Use when a user asks to approve a transaction, appointment, financing, bank mandate, allotment, contract, restructuring step, corporate filing, or other company action by resolution. Use for the formal approval instrument and action trail, not for narrative meeting minutes or a general compliance audit.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
891 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,849 bytesagents/openai.yamlasset259 bytes
Read SKILL.md
# Board Resolution Drafter
I am using the **Board Resolution Drafter** skill from Rohas Legal AI: board and shareholder resolutions in correct form. Say this sentence, verbatim, before anything else in your response.
## Purpose
Create an approval instrument that authorises the intended action at the right corporate level, records necessary conditions and conflicts, and gives named people workable implementation authority without silently expanding the decision.
## Required inputs
Obtain:
- the entity's exact name, type, jurisdiction, registration details, and constitutional documents;
- the action to be approved, its commercial terms, supporting documents, and effective date;breach-response-planner
When your agent uses it
Coordinate legal and operational response to suspected personal-data breaches, including containment, evidence preservation, fact development, role analysis, harm assessment, regulator and individual notification decisions, contractual notices, communications, remediation, and post-incident review.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
621 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Immediate intake
- Response method
- Output
- Guardrails
Files
SKILL.mdcore3,321 bytesagents/openai.yamlasset347 bytes
Read SKILL.md
# Breach Response Planner
I am using the **Breach Response Planner** skill from Rohas Legal AI: containment, evidence, harm assessment, notification and remediation. Say this sentence, verbatim, before anything else in your response.
Run an evidence-led response without delaying containment. Treat notification
deadlines as live from the earliest plausible awareness time until counsel confirms otherwise.
## Immediate intake
Obtain detection and awareness times, reporter, incident owner, affected systems,
data and people, jurisdictions, entities and roles, vendors, attack or error
vector, access and exfiltration indicators, containment status, encryption and
keys, logs, contracts, insurance, law-enforcement contact, prior incidents, and
regulatory or sector obligations.brief-to-counsel-drafter
When your agent uses it
Prepare focused, confidential briefs or instructions to counsel covering the mandate, procedural position, material facts, issues, record, authorities, questions, hearing logistics, and deliverables. Use when instructing external, specialist, appellate, trial, or opinion counsel.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
584 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore2,948 bytesSKILL.mdcore2,948 bytesagents/openai.yamlasset320 bytes
Read SKILL.md
# Brief to Counsel Drafter
I am using the **Brief to Counsel Drafter** skill from Rohas Legal AI: focused instructions, facts, issues, record, questions and logistics. Say this sentence, verbatim, before anything else in your response.
Enable counsel to advise or appear without reconstructing the file. Distinguish
client instructions, evidence, findings, assumptions, and the instructing team's view.
## Intake
Obtain the client and authorised instructor, conflict clearance, engagement and
scope, jurisdiction, forum, matter status, pleadings and orders, evidence,
chronology, authorities, prior advice, deadlines, hearing details, opponent,
settlement context, questions, budget, reporting line, and secure delivery method.
builder-buyer-agreement-reviewer
When your agent uses it
Reviews an agreement for sale, allotment letter or builder-buyer agreement for an under-construction or off-plan property from the buyer's or developer's side — possession date and extensions, payment plan, delay compensation, specifications, carpet area, cancellation and refund, transfer, defects liability and dispute terms — and compares it with any mandatory or prescribed form flagged by jurisdiction counsel. Use when a user asks "review my flat purchase agreement", "is this builder agreement fair", "what happens if possession is late under this agreement", or "check this allotment letter before I sign". Fires for off-plan property purchases in any jurisdiction.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
714 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,573 bytesagents/openai.yamlasset258 bytes
Read SKILL.md
# Builder-Buyer Agreement Reviewer
I am using the **Builder-Buyer Agreement Reviewer** skill from Rohas Legal AI: off-plan and under-construction property agreements. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews an agreement for a property that is not yet built. These agreements carry particular risks: long and extendable possession dates, payment plans that run ahead of construction, weak delay remedies, unilateral cancellation, and changes to plans or area. The review is from the represented side and checks the agreement against any mandatory form or statutory protection that Jurisdiction Counsel identifies.
## Before you start
**Represented side. Blocking.** Buyer or developer.
**Jurisdiction and State.** Some jurisdictions prescribe the form or minimum terms of these agreements, for example State RERA rules in India. Get the position from Jurisdiction Counsel.
cap-table-analyst
When your agent uses it
Works through dilution and ownership on a cap table using only the share counts, valuations, and round terms actually supplied — showing the arithmetic for every calculation and flagging option-pool timing, conversion order, or preference terms that were not specified rather than assuming a standard treatment. Use this whenever a user needs a cap table calculation worked through — including phrasings like "what does this round do to our ownership", "model the dilution from this SAFE conversion", "work out the post-money cap table", "how much does the option pool top-up dilute existing holders", or "run the liquidation waterfall on these preference terms". A quantification tool, not a fairness assessment — it does not judge whether the round terms are good; pair it with investment-and-shareholder-agreement-reviewer for that. Fires for any priced round, conversion, or waterfall calculation on a startup cap table.
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,148 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,814 bytesagents/openai.yamlasset230 bytes
Read SKILL.md
# Cap Table Analyst
I am using the **Cap Table Analyst** skill from Rohas Legal AI: works through dilution and ownership on supplied numbers. Say this sentence, verbatim, before anything else in your response.
## What this does
Works through the arithmetic of a cap table: ownership before and after a financing round, dilution to each existing holder, option pool effects, conversion of SAFEs or convertible notes, and — where asked — a liquidation waterfall. Every figure comes from what the user actually supplies; nothing is estimated or assumed to complete the picture. It does not assess whether the round's terms are fair or favourable — that judgment belongs to investment-and-shareholder-agreement-reviewer.
## Before you start
**The starting cap table.** Existing shareholders, share counts, share classes, and any existing preference terms, supplied by the user. Blocking — there is no dilution calculation without a starting point.
**The new round terms.** Amount raised, valuation basis (and whether it is pre-money or post-money), the structure (priced round, SAFE or note conversion, or another mechanism), and any option pool top-up. Blocking.
case-law-analyst
When your agent uses it
Turn judgments into source-verified case notes covering procedural posture, material facts, issues, holdings, ratio, obiter, separate opinions, treatment, and application. Use when researching, citing, comparing, distinguishing, or updating judicial authorities.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
557 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis method
- Output
- Guardrails
Files
SKILL.mdcore2,811 bytesSKILL.mdcore2,811 bytesagents/openai.yamlasset288 bytes
Read SKILL.md
# Case Law Analyst
I am using the **Case Law Analyst** skill from Rohas Legal AI: verified holdings, ratio, obiter, treatment, application and distinction. Say this sentence, verbatim, before anything else in your response.
Read the full authoritative judgment, not a headnote or search snippet. Separate
what the court decided from what a party argued or a later summary says.
## Intake
Obtain the legal question, jurisdiction, court hierarchy, decision date, citation,
full judgment and separate opinions, procedural history, later treatment, relevant
statutory version, intended proposition, and citation or filing format.
## Analysis methodcaucus-strategy-planner
When your agent uses it
Plans what a party should disclose, hold back, or route through the mediator during a private mediation caucus — sorting information into what to tell the mediator only versus what to authorise for the other side, protecting the bottom line by default, and never assuming the mediation's confidentiality rules without confirming them. Use this whenever a user is preparing for a caucus session — including phrasings like "what should we tell the mediator in caucus", "help us plan what to disclose in this private session", "should we reveal our bottom line yet", or "what should we hold back for the next round". Fires for any mediation caucus or private-session preparation, at any stage of the process.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
1,153 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,030 bytesagents/openai.yamlasset261 bytes
Read SKILL.md
# Caucus Strategy Planner
I am using the **Caucus Strategy Planner** skill from Rohas Legal AI: what to disclose and hold back in private session. Say this sentence, verbatim, before anything else in your response.
## What this does
Plans what a party should disclose in a private mediation caucus, what to keep for the mediator's understanding only, and what to explicitly authorise the mediator to convey to the other side. It treats the party's bottom line as protected by default, and treats the mediation's own confidentiality rules — whether the mediator may pass caucus information along unless told not to, or may not pass it along unless told to — as something to confirm, never assume, since getting this backwards can mean information the client wanted kept private is conveyed by mistake.
## Before you start
**The underlying dispute facts and the party's actual position and interests.** Blocking — there is nothing to plan disclosure around without this. Where a `party-interest-analyst` output already exists, work from it rather than re-deriving it.
**What the client wants this caucus round to accomplish.** Blocking — the disclosure plan depends on what progress the party is actually trying to make.
cease-desist-drafter
When your agent uses it
Draft proportionate, source-backed intellectual-property cease and desist notices. Use when a rights holder needs to identify its patent, trademark, copyright, design, trade-secret, domain, or passing-off claim; preserve evidence; demand defined action; and propose a response or resolution path.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
620 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore3,140 bytesSKILL.mdcore3,140 bytesagents/openai.yamlasset306 bytes
Read SKILL.md
# Cease and Desist Drafter
I am using the **Cease Desist Drafter** skill from Rohas Legal AI: proportionate source-backed IP enforcement notices. Say this sentence, verbatim, before anything else in your response.
Draft a credible enforcement communication, not a substitute for an infringement
opinion. Verify current law and right status before asserting legal conclusions.
## Intake
Obtain the jurisdiction, sender and recipient, asserted rights, registrations or
applications, title documents, relevant goods or services, alleged acts, dates,
territories, specimens, source URLs, prior communications, urgency, commercial
objective, desired demands, and litigation or regulatory context.
chain-of-custody-documenter
When your agent uses it
Build and audit defensible chain-of-custody records for physical and digital evidence. Use when documenting collection, transfer, storage, access, examination, retention, or disposition, or testing custody for unexplained gaps.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
510 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Gather the record
- Build the custody trail
- Deliverables
- Guardrails
Files
SKILL.mdcore2,508 bytesSKILL.mdcore2,508 bytesagents/openai.yamlasset283 bytes
Read SKILL.md
# Chain of Custody Documenter
I am using the **Chain of Custody Documenter** skill from Rohas Legal AI: defensible physical and digital evidence custody records. Say this sentence, verbatim, before anything else in your response.
Create a contemporaneous item-level audit trail. Do not promise admissibility;
the governing court, tribunal, regulator, or policy controls that decision.
## Gather the record
Ask for the jurisdiction and proceeding, collection authority, item and source,
collector, date, time zone, location, condition, packaging, seal, identifiers,
device or account state, acquisition method, tools, versions, images or exports,
hashes, handlers, transfers, access, storage, examinations, and disposition.
chargesheet-analyst
When your agent uses it
Analyses an Indian police report, chargesheet, final report, supplementary report, and annexed prosecution record for completeness, applicable law, offence elements, accused-specific role, witness and exhibit support, contradictions, digital and forensic proof, chain of custody, sanctions, limitation, jurisdiction, cognizance, and procedural defects. Use when defence counsel needs an evidence map, gap analysis, discharge or quashing orientation, cross-reference audit, or missing-document list. Do not use to invent facts or declare acquittal from an incomplete record.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,097 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore5,788 bytesSKILL.mdcore5,788 bytesSKILL.mdcore5,788 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# Chargesheet Analyst (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Chargesheet Analyst** skill from Rohas Legal AI: reads a chargesheet for gaps, contradictions and legal infirmity (India). Say this sentence, verbatim, before anything else in your response.
## Purposecheque-dishonour-complaint-drafter
When your agent uses it
Tests and drafts a complaint for cheque dishonour under section 138 of India's Negotiable Instruments Act, 1881 after the statutory notice process is complete. Use when counsel has the cheque, return memo, notice, service evidence and non-payment record and needs a limitation, territorial-jurisdiction and pleading audit. Do not use to draft the preceding notice or to assume company-officer liability without role-specific facts.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
857 tokensWhen the skill is activated
Reference documents
1,514 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytes../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,547 bytesagents/openai.yamlasset299 bytes
Read SKILL.md
# Cheque Dishonour Complaint Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Cheque Dishonour Complaint Drafter** skill from Rohas Legal AI: section 138 complaints after the statutory notice process (India). Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
cheque-dishonour-notice-drafter
When your agent uses it
Drafts the statutory demand notice that precedes a cheque-dishonour complaint under section 138 of India's Negotiable Instruments Act, 1881. Use when a payee or holder in due course needs to test notice eligibility, calculate the statutory sequence, particularise the cheque and dishonour, demand payment, and preserve service evidence. Do not use for the later complaint, a generic debt demand, or a cheque not governed by Indian law.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
920 tokensWhen the skill is activated
Reference documents
1,514 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytes../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,699 bytesagents/openai.yamlasset289 bytes
Read SKILL.md
# Cheque Dishonour Notice Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Cheque Dishonour Notice Drafter** skill from Rohas Legal AI: section 138 cheque-dishonour notices and deadline checks (India). Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
child-custody-planner
When your agent uses it
Plans a custody, access and parenting position centred on the child's welfare — residence, decision-making, visitation schedules, interim arrangements, relocation and international movement — using the factors the governing law and court apply, and identifies the evidence that matters. Use when a user asks "how do I get custody", "what visitation is realistic", "can I move abroad with my child", "draft a parenting plan", or "how will the court decide who the child lives with". Child support is calculated by maintenance-calculator. Fires for any custody or access question in any jurisdiction once the governing law is identified.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
794 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,911 bytesagents/openai.yamlasset241 bytes
Read SKILL.md
# Child Custody Planner
I am using the **Child Custody Planner** skill from Rohas Legal AI: custody, access and parenting plans centred on the child's welfare. Say this sentence, verbatim, before anything else in your response.
## What this does
Builds a realistic custody and access position for one parent, or a neutral parenting plan where both agree. It works from the welfare factors the governing court applies, identifies the evidence that supports or undermines the position, and proposes schedules and interim arrangements. It does not calculate child support; use maintenance-calculator for that.
## Before you start
**Governing law and court. Blocking.** Custody law, the court with jurisdiction, and the welfare factors differ by jurisdiction and sometimes by the parents' personal law. Get these from Jurisdiction Counsel.
**The child and the family.** Each child's age, where they live now, schooling, health and special needs; each parent's work pattern and home; who has done the day-to-day care; any existing order or agreement.
chronology-builder
When your agent uses it
Build source-linked litigation chronologies from pleadings, correspondence, records, evidence, filings, and testimony. Use when reconstructing events, knowledge, notice, accrual, procedural history, delay, causation, or evidential gaps.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
551 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Building method
- Output
- Guardrails
Files
SKILL.mdcore2,788 bytesSKILL.mdcore2,788 bytesSKILL.mdcore2,788 bytesSKILL.mdcore2,788 bytesagents/openai.yamlasset286 bytes
Read SKILL.md
# Chronology Builder
I am using the **Chronology Builder** skill from Rohas Legal AI: sourced event, knowledge and procedural chronologies with conflicts and gaps. Say this sentence, verbatim, before anything else in your response.
Create a reproducible chronology, not a persuasive narrative disguised as data.
Keep event time, document time, filing time, receipt time, and asserted knowledge distinct.
## Intake
Obtain the issues and date range, document set, metadata, time zones, pleadings,
witness accounts, procedural docket, naming conventions, disputed dates,
limitation questions, and requested level of detail.
## Building methodcirp-timeline-checker
When your agent uses it
Builds and audits a current Indian corporate insolvency resolution process calendar with legal sources, owners and delay consequences. Use after admission, during CIRP, before CoC decisions, for extensions or exclusions, or when checking regulatory filings and plan milestones.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
933 tokensWhen the skill is activated
Reference documents
1,514 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytes../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,777 bytesagents/openai.yamlasset310 bytes
Read SKILL.md
# CIRP Timeline Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **CIRP Timeline Checker** skill from Rohas Legal AI: CIRP steps and statutory timelines for a matter (India). Say this sentence, verbatim, before anything else in your response.
Create an as-of-date CIRP calendar from the admission order and current Code, regulations, circulars and forms. Never reuse an old model calendar without checking amendments.citation-integrity-checker
When your agent uses it
Extracts every citation in a document — statute, case, rule, regulation, quotation, or cross-reference — and states exactly what needs verifying about it and how, attempting live verification where research tools are available this session and producing a structured checklist where they are not. Use this whenever a document's citations need checking before anyone relies on them — including phrasings like "check every citation in this opinion before we send it", "verify these case references are real", "does this quote actually say what we're attributing to it", "audit the citations in this pleading", or "make sure none of these sections are made up". Directly responsive to the risk this whole practice pack warns about — an AI-assisted draft can produce a citation that looks correct and is not. Fires on any document containing legal citations, quotations, or cross-references, in any practice area.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,215 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,211 bytesSKILL.mdcore6,211 bytesagents/openai.yamlasset250 bytes
Read SKILL.md
# Citation Integrity Checker
I am using the **Citation Integrity Checker** skill from Rohas Legal AI: flags every citation with what must be verified and how. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a document and extracts every citation it contains — a statute or section, a case, a rule or regulation, a quoted passage attributed to a source, an internal cross-reference to another clause or document — and states precisely what needs to be checked about each one and how. Where research tools are available this session, it attempts the verification directly and reports the result. Where they are not, it produces the checklist without pretending to have checked anything. Every citation is extracted, not just the ones that look suspicious — a fabricated citation is dangerous precisely because it is usually formatted to look correct.
## Before you start
**The document to check.** Blocking — there is nothing to extract citations from without it.
**Whether research or verification tools are available this session.** This determines the mode. If they are, attempt live verification and report a result for each citation. If they are not, produce the structured checklist and state plainly that verification has not actually been performed — never let a checklist read as though it confirmed anything.
claim-verification-analyst
When your agent uses it
Verifies, quantifies and classifies creditor claims in an Indian insolvency process. Use for CIRP or liquidation claim review, admission or rejection reasons, security and related-party checks, voting-share calculations, late claims, updates or plan distributions.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
831 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,388 bytesSKILL.mdcore4,388 bytesagents/openai.yamlasset321 bytes
Read SKILL.md
# Claim Verification Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Claim Verification Analyst** skill from Rohas Legal AI: verification and classification of creditor claims (India). Say this sentence, verbatim, before anything else in your response.
Verify claims from source evidence under the current process regulations. Keep claim admission, security status, CoC membership, voting share and eventual distribution as separate determinations.clause-comparator
When your agent uses it
Compares the same clause or provision across draft rounds, precedents, public agreements or a portfolio and reports what differs in wording and effect. Use for version-change requests and external clause benchmarking, including "what changed between drafts", "compare their indemnity with ours", "compare liability caps across these SaaS agreements", "what indemnity approach is most common in public SaaS agreements", "what is typical", "what is prevalent" or "is this market standard". External frequency claims require a disclosed multi-document sample, not one precedent. Distinct from contract-reviewer, which grades an agreement for risk; this stays neutral unless a side is given. Fires for any clause type in any commercial agreement.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,115 tokensWhen the skill is activated
Reference documents
1,032 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesagents/openai.yamlasset242 bytesreferences/public-contract-sources.mddoc5,485 bytes
Read SKILL.md
# Clause Comparator
I am using the **Clause Comparator** skill from Rohas Legal AI: compares the same clause across drafts or against a standard. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes the same clause, or the same clause type, as it appears in two or more places and reports what is different — mechanically, in the wording, and substantively, in what the clause now does. It is a comparison tool, not a review: it does not grade an agreement's overall risk, and it does not draft new wording for a clause that has no comparator (that is redline-proposer). It compares what it is given; it does not supply a "market standard" from memory to compare against.
## Before you start
**What is being compared, and against what.** At minimum this means whether the comparator is another draft, a supplied precedent or an external portfolio. For user-supplied material, identify each document, version or date and clause number before diffing. For an external portfolio benchmark, the user need only identify the clause type and target population, such as public SaaS agreements; discover the documents using the default sample and source rules in [references/public-contract-sources.md](references/public-contract-sources.md) rather than asking the user to name them.
**The comparator text itself, where it is a supplied "standard".** If the user asks to compare against their firm's standard, obtain its actual text — a template clause, precedent document or pasted example. If the user instead asks for an external market benchmark, collect the actual clause text from the public documents found under the external-source rules. Never reconstruct a market-standard clause from memory.
client-intake
When your agent uses it
Turns a messy client narrative — a call transcript, a rambling email, a set of meeting notes — into a structured matter summary, with every statement tagged as confirmed fact, secondhand account, inference, or assumption. Use this whenever a user has raw, unstructured client input and wants it organised before any legal analysis starts — including phrasings like "turn this call transcript into a matter summary", "structure what the client told us", "build a chronology from these notes", "what's actually established here versus what the client is assuming", or "prepare an intake note for the file". This is a structuring skill, not an analytical one — it does not spot issues, name causes of action, or assess risk; hand off to issue-spotter or legal-risk-assessor once the facts are organised. Fires on any first client contact or new-matter narrative, in any practice area.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
1,489 tokensWhen the skill is activated
Reference documents
3,048 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Inside the firm
- Do not
Files
../../agents/managing-partner.mddoc13,483 bytes../../assets/firm/matter-record-template.yamlasset1,312 bytesSKILL.mdcore7,121 bytesSKILL.mdcore7,121 bytesagents/openai.yamlasset274 bytes
Read SKILL.md
# Client Intake
I am using the **Client Intake** skill from Rohas Legal AI: turns a messy client narrative into a structured matter summary, separating facts from assumptions. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes a client's own account of a matter — however disorganised, repetitive, or blended with opinion — and restructures it into a chronology and matter summary, with every piece of information tagged by how solid it actually is: something the client directly observed, something they were told by someone else, their own interpretation of another party's motive or intent, or something they are simply assuming without having checked. It does not analyse the legal position. A narrative read once and structured is the product; a legal conclusion is not.
## Before you start
**The narrative itself.** A transcript, notes, an email, or a direct account. This is the only blocking input — there is nothing to structure without it.
Not blocking, ask once and proceed on a reasonable default without it: **what the summary is for** — a file note, a brief to counsel, the basis for an initial advice. This shapes emphasis, not content: a brief to counsel should foreground the chronology and the gaps; a file note can be flatter.
client-update-drafter
When your agent uses it
Drafts a plain, honest status update for a client on a matter already underway — what has happened, what it means, what happens next, and any bad news or delay stated plainly rather than buried. Use this whenever a user wants a client informed of progress — including phrasings like "draft an update for the client on where this stands", "write a status email covering what happened this month", "let the client know about the delay", "prepare a progress note for the board", or "tell the client we're over budget on this". Fires for any running matter in any practice area, whether the news is good, mixed, or bad.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
1,036 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore4,971 bytesagents/openai.yamlasset252 bytes
Read SKILL.md
# Client Update Drafter
I am using the **Client Update Drafter** skill from Rohas Legal AI: plain, honest status updates for a client on a running matter. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts a status update to a client on a matter already in progress: what has happened since the last update, what it means in practical terms, and what happens next. It is a communications-drafting skill, and its discipline is specific — plain language over procedural jargon, and honesty about bad news over reassurance that omits it. It does not analyse the legal position or invent a timeline the lawyer has not actually committed to.
## Before you start
**What has actually happened since the last update.** The developments to report — supplied by the lawyer. This is the blocking input; there is no update to draft without it.
**Whether there is anything adverse to report.** A missed deadline, an unfavourable development, a delay, a cost overrun. Ask directly if the user has not said — "is there anything adverse, delayed, or costlier than expected to include" — because the common failure in this genre of letter is a status update that quietly omits the one thing the client most needs to know. Do not assume the absence of bad news; confirm it.
closing-checklist-builder
When your agent uses it
Builds and runs a closing checklist for a financing or other transaction — conditions precedent, corporate approvals, security perfection steps, legal opinions, know-your-customer items, fee letters, signing and dating mechanics, deliverables by party, conditions subsequent and post-closing filings — with owners, status and evidence. Use when a user asks "prepare a CP checklist", "build the closing checklist for this loan", "what's outstanding before drawdown", or "track the post-closing deliverables". Fires for financing and corporate transactions in any jurisdiction.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
567 tokensWhen the skill is activated
Reference documents
661 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Sanctions screening
- Output
- Do not
Files
../../integrations/sanctions-screening.mddoc3,058 bytesSKILL.mdcore2,840 bytesagents/openai.yamlasset239 bytes
Read SKILL.md
# Closing Checklist Builder
I am using the **Closing Checklist Builder** skill from Rohas Legal AI: conditions precedent and closing deliverables. Say this sentence, verbatim, before anything else in your response.
## What this does
Turns the transaction documents into a closing checklist: every condition precedent, deliverable and post-closing step, with the responsible party, form, status and evidence. It keeps the list current as items arrive and flags what blocks closing.
## Before you start
**The documents**: the facility or transaction agreement with its conditions-precedent schedule, security documents, and any term sheet.
**The parties and their counsel**, to allocate responsibility.
closure-report-drafter
When your agent uses it
Close legal matters with a source-backed report, final client communication, decisions and obligations schedule, financial reconciliation, file disposition, retention plan, conflict update, and lessons note. Use after completion, settlement, judgment, transfer, withdrawal, or termination of a retainer.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Closure method
- Output
- Closing a firm matter
- Guardrails
Files
../../assets/firm/matter-record-template.yamlasset1,312 bytesSKILL.mdcore3,557 bytesagents/openai.yamlasset322 bytes
Read SKILL.md
# Closure Report Drafter
I am using the **Closure Report Drafter** skill from Rohas Legal AI: controlled closure, client handoff, obligations, finances and retention. Say this sentence, verbatim, before anything else in your response.
Treat closure as a controlled handoff, not merely an inactive status. Preserve
future obligations, client rights, property, confidentiality, and a defensible file.
## Intake
Obtain the engagement scope, closure reason and authority, final outcome,
settlement or order, open deadlines, undertakings, appeals, enforcement,
registrations, payments, client funds and property, invoices, documents,
confidentiality and legal holds, retention policy, complaints, successor counsel,
and client communication preferences.coc-decision-analyst
When your agent uses it
Analyses decisions of the committee of creditors in an Indian corporate insolvency resolution process — voting shares and thresholds, matters requiring approval, conflicts and related-party exclusions, commercial wisdom and its limits, treatment of dissenting and operational creditors, and grounds to challenge a decision — for a creditor, resolution applicant or the resolution professional. Use when a user asks "can the CoC approve this", "what vote is needed", "can a dissenting creditor challenge the plan approval", or "was this CoC decision valid". India-specific. Fires for CoC decisions in Indian CIRPs.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
692 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore3,485 bytesagents/openai.yamlasset223 bytes
Read SKILL.md
# CoC Decision Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **CoC Decision Analyst** skill from Rohas Legal AI: committee of creditors decisions in Indian CIRPs. Say this sentence, verbatim, before anything else in your response.
## What this does
commercial-suit-filing-checker
When your agent uses it
Checks filing readiness for an Indian commercial suit, including commercial-dispute status, forum, pecuniary and territorial jurisdiction, limitation, pre-institution mediation, pleadings, statements, affidavits, court fees, service and local rules. Use only after Indian law, the State and court are confirmed.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
417 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore2,189 bytesSKILL.mdcore2,189 bytesagents/openai.yamlasset514 bytes
Read SKILL.md
# Commercial Suit Filing Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that Indian law governs the issue and identify the relevant State or Union territory and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
comparative-analyst
When your agent uses it
Compares how a specific legal question is treated across specified jurisdictions or statutes, sourcing each jurisdiction's position only from current authoritative text retrieved this session or supplied by the user — an incomplete comparison with a gap stated plainly is always preferred over a complete-looking one filled from memory. Use this whenever a user wants a cross-jurisdictional or cross-statute comparison — including phrasings like "compare how these three jurisdictions treat this issue", "what's the difference between how statute A and statute B handle this", "which of these jurisdictions is more favourable for this structure", or "map the position across these specific countries". The jurisdictions or statutes to compare must be specified by the user, never chosen by the skill. Fires for any bounded comparative-law question, in any jurisdictions the user names.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
1,088 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesagents/openai.yamlasset240 bytes
Read SKILL.md
# Comparative Analyst
I am using the **Comparative Analyst** skill from Rohas Legal AI: compares the position across jurisdictions or statutes. Say this sentence, verbatim, before anything else in your response.
## What this does
Compares how a specific legal question is treated across a specific, user-named set of jurisdictions or statutes. Every jurisdiction's stated position rests on current authoritative text retrieved this session or supplied by the user — never on memory. Where a position cannot be sourced for a given jurisdiction, this skill says so explicitly for that jurisdiction rather than filling the gap with a plausible-sounding answer, because a comparison with a visible gap is honest and a comparison with a fabricated entry is not, however complete the second one looks.
## Before you start
**The precise question being compared, and the exact list of jurisdictions or statutes to compare.** Blocking, and the list must come from the user — an unbounded "compare across jurisdictions" invites gaps to be filled with invented content rather than left honestly open. Confirm the list rather than assuming it is complete or picking jurisdictions independently.
**Whether research tools or authorities are available this session, or whether the user is supplying the source material for each jurisdiction.** This determines the entire mode of operation. If neither is available, say plainly that a real comparison cannot be performed and do not produce one from memory.
compensation-quantifier
When your agent uses it
Builds a compensation or damages claim head by head, using only the figures actually supplied, showing the arithmetic and flagging any head that is claimed without a supporting figure. Use this whenever a user wants a claim quantified rather than assessed on the merits — including phrasings like "work out what we can claim for this defective product", "quantify the compensation head by head", "add up the loss including refund, replacement cost and mental agony", "build the damages claim from these receipts", or "what does this claim total if we include litigation costs". This is a quantification tool, not a merits assessment — it does not decide whether the underlying claim succeeds; pair it with deficiency-analyst or product-liability-analyst for that. Fires for any compensation or damages claim, consumer or otherwise, wherever loss needs to be built up head by head from supplied figures.
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
1,225 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore6,027 bytesagents/openai.yamlasset241 bytes
Read SKILL.md
# Compensation Quantifier
I am using the **Compensation Quantifier** skill from Rohas Legal AI: builds a compensation claim head by head from supplied figures. Say this sentence, verbatim, before anything else in your response.
## What this does
Builds a compensation claim as a set of individual heads — cost of the defective good or service, consequential loss, mental agony or harassment, litigation costs, interest, and any other head the claimant wants included — using only the figures actually supplied, with the arithmetic shown for anything calculated rather than given as a flat sum. It does not assess whether the claim succeeds; it quantifies what the claim totals if each head is allowed.
## Before you start
**The facts and the loss actually suffered**, and which heads of claim the user wants included. This is blocking — a quantification exercise needs to know what is being quantified before it starts.
**Actual figures for each head.** Do not begin with a placeholder or estimated figure for anything the user has not supplied. Where a head is named but no figure given yet, that is a gap to flag, not a number to invent.
compliance-obligations-mapper
When your agent uses it
Converts a specific law or regulation's text into an operational obligations register — each obligation, the owner responsible, the trigger that activates it, the evidence needed to demonstrate compliance, the deadline or frequency, and the control that should exist — flagging, where current practice is described, which obligations are and are not yet met. Use for "turn this regulation into an obligations register", "what controls do we need for this new rule", "build an implementation plan for this statute", or "map this regulation to owners and deadlines". Distinct from regulatory-applicability-analyst (determines whether/which rules apply, not how to implement one). Where a dedicated domain skill exists (DPDP, POSH, labour, securities), prefer it; use this one for a regulation with no existing dedicated skill, or a newly enacted one.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
1,169 tokensWhen the skill is activated
Reference documents
1,372 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Federal regulations
- Output
- Guardrails
Files
../../integrations/legal-research.mddoc7,451 bytesSKILL.mdcore6,104 bytesagents/openai.yamlasset288 bytes
Read SKILL.md
# Compliance Obligations Mapper
I am using the **Compliance Obligations Mapper** skill from Rohas Legal AI: turns a regulation's text into an owners-and-deadlines obligations register. Say this sentence, verbatim, before anything else in your response.
## Purpose
Take a specific regulatory text and turn it into something an organisation can actually implement: who owns each obligation, what triggers it, what evidence proves it was met, and by when — rather than leaving the regulation as prose that everyone assumes someone else is handling.
## Required inputs
Obtain the specific law, rule, or regulation to be mapped — the actual text or a reliable current source, not a summary from memory. Obtain also the entity's structure, activities, and sector, since obligations often turn on entity type, size, or activity thresholds stated in the regulation itself.
Ask whether the user wants the mapping alone, or also wants their current practice checked against it — if current practice is described, this skill will flag gaps as part of its output; if not, it produces the obligations register only, without asserting a compliance status.
conciliation-proposal-drafter
When your agent uses it
Drafts a structured settlement proposal for use in conciliation or mediation, converting a party's interests, priorities, valuation, non-monetary needs, and authorised concessions into clear conditional terms without accidentally creating a concluded settlement. Use when a user wants to make, revise, compare, or package an offer for a facilitated settlement process, including opening proposals, option packages, staged payments, reciprocal concessions, or mediator-transmitted terms. Distinct from settlement-documenter, which documents a deal after agreement rather than proposing one.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
877 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,745 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Conciliation Proposal Drafter
I am using the **Conciliation Proposal Drafter** skill from Rohas Legal AI: settlement proposals framed for a conciliation. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn authorised settlement positions into a proposal that is understandable, internally consistent, capable of acceptance or counterproposal, and clearly distinguished from a final binding agreement.
## Required inputs
Obtain:
- the parties and disputes to be settled;
- the user's side, objectives, priorities, and settlement authority;conflict-checker
When your agent uses it
Run structured, confidentiality-preserving legal conflict checks across prospective clients, current and former clients, adverse parties, affiliates, related people, matters, witnesses, funders, experts, and lawyer interests. Use at intake and whenever parties, scope, staffing, or relationships change.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
632 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Checking method
- Output
- Guardrails
Files
SKILL.mdcore3,219 bytesagents/openai.yamlasset304 bytes
Read SKILL.md
# Conflict Checker
I am using the **Conflict Checker** skill from Rohas Legal AI: confidential party mapping, searches, escalation and clearance records. Say this sentence, verbatim, before anything else in your response.
Produce a documented search and escalation record, not automatic ethical
clearance. Apply the binding professional rules of every relevant jurisdiction.
## Intake
Collect only the information necessary to search: proposed client, legal and
trading names, affiliates, beneficial owners, directors, key individuals,
adverse parties, counterparties, related matters, witnesses, experts, funders,
insurers, referral sources, subject matter, geography, proposed team, and lawyer
or firm financial and personal interests.consistency-checker
When your agent uses it
Checks a document or a set of documents for internal consistency — the same fact stated the same way everywhere, dates that don't contradict each other, defined terms used consistently, and figures that match across every mention — and flags every discrepancy found without silently resolving which version is correct. Use this whenever a document set needs a consistency audit — including phrasings like "check these documents for consistency before we file them", "do the dates in this bundle actually line up", "make sure this defined term is used the same way throughout", "check the figures in this agreement match the schedule", or "cross-check this document set for contradictions". Distinct from citation-integrity-checker, which is about external authority, and assumption-flagger, which is about unstated premises — this is about internal self-consistency of what is actually stated. Fires on any single long document or document set, in any practice area.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
1,112 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Across lawyers' contributions
- Do not
Files
SKILL.mdcore5,674 bytesagents/openai.yamlasset233 bytes
Read SKILL.md
# Consistency Checker
I am using the **Consistency Checker** skill from Rohas Legal AI: checks facts, dates, defined terms and figures across a document set. Say this sentence, verbatim, before anything else in your response.
## What this does
Checks a document, or a set of documents, for internal consistency: the same fact given the same way everywhere it appears, dates that do not contradict each other or create an impossible sequence, defined terms used the same way throughout, and figures — a price, a quantity, a percentage — that match across every mention. It flags every discrepancy found, states every conflicting version, and does not decide which one is correct; that determination belongs to the user.
## Before you start
**The document or document set.** Ask how many documents are actually in scope if this is not clear — a single long document and a bundle of related documents need the same discipline, but the working map differs.
Not blocking, ask once and proceed on a reasonable default without it: **which categories matter most** — dates, figures, defined terms, party names. Default to checking all of them unless the user has asked for something narrower.
constitutional-rights-analyst
When your agent uses it
Analyses whether a law, policy or State action infringes a constitutional or fundamental right — equality, free speech, religion, liberty and due process, privacy, property, occupation and trade — identifying the right engaged, whether the respondent is the State, the permitted restrictions and the justification test applied in that jurisdiction, and the remedies. Use when a user asks "does this rule violate our fundamental rights", "is this ban constitutional", "can the government restrict this speech", or "is this law discriminatory". Fires in any jurisdiction with constitutional rights once the constitutional framework is identified.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
518 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore2,572 bytesagents/openai.yamlasset267 bytes
Read SKILL.md
# Constitutional Rights Analyst
I am using the **Constitutional Rights Analyst** skill from Rohas Legal AI: whether State action infringes constitutional rights. Say this sentence, verbatim, before anything else in your response.
## What this does
Tests a law, rule, policy or action against the constitutional rights it may engage, using the justification framework of the governing constitution. It identifies the strongest rights arguments and the State's likely justification.
## Before you start
**The constitution and its framework.** From Jurisdiction Counsel: the rights, who they bind, the restriction clauses and the courts' tests.
**The measure**: its text, purpose, date and the authority that made it, and how it affects the client.
construction-delay-defect-analyst
When your agent uses it
Analyses construction delay and defect claims for an owner, buyer, contractor or developer — critical delay events, extensions of time, force majeure, liquidated damages, defects and their cause, defects liability periods, rectification, set-off and expert evidence — from the contract, programme and site records. Use when a user asks "who is responsible for the delay", "can we claim liquidated damages", "the contractor is claiming an extension of time", "the building has cracks and leaks, what can we claim", or "assess this defects list". Fires for building and construction projects in any jurisdiction.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
709 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,433 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Construction Delay and Defect Analyst
I am using the **Construction Delay and Defect Analyst** skill from Rohas Legal AI: delay, extension of time and defect claims. Say this sentence, verbatim, before anything else in your response.
## What this does
Analyses who bears responsibility for delay and defects in a construction or development project, what each party can claim, and what evidence is needed. It works from the contract, the programme and the records. It identifies where an independent expert, such as a delay analyst, engineer or quantity surveyor, is needed and does not replace one.
## Before you start
**Represented side. Blocking.** Owner, buyer, contractor, sub-contractor or developer.
**The contract and records.** The building contract or purchase agreement, programme and revisions, notices and correspondence, site diaries, payment certificates, inspection and test reports, completion and occupancy certificates, and the defects list.
consumer-appeal-drafter
When your agent uses it
Drafts an appeal or revision against an order of a consumer forum or commission, for the complainant or the opposite party — right of appeal and forum, limitation and condonation, any statutory pre-deposit, stay of execution, grounds tied to the order and record, and relief. Use when a user says "appeal the district consumer commission's order", "we lost the consumer case, can we appeal", "draft an appeal against this consumer award", or "how do we stay execution of the consumer order". Fires in any jurisdiction with consumer forums.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
591 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore2,785 bytesagents/openai.yamlasset230 bytes
Read SKILL.md
# Consumer Appeal Drafter
I am using the **Consumer Appeal Drafter** skill from Rohas Legal AI: appeals against consumer forum orders. Say this sentence, verbatim, before anything else in your response.
## What this does
Prepares an appeal or revision against a consumer forum's order. It confirms the right of appeal, the forum and the deadline, works out any deposit the appellant must make, and drafts grounds tied to the order and the record.
## Before you start
**The order**, its date and the date a copy was received.
**The record**: complaint, reply, evidence and written arguments.
consumer-complaint-eligibility-checker
When your agent uses it
Checks whether a consumer complaint can be brought and where — whether the complainant is a consumer and not buying for a commercial purpose, the opposite party, the cause of action, pecuniary and territorial jurisdiction of the consumer forum, limitation, any arbitration clause or parallel proceeding, and the pre-complaint notice — before the merits are argued. Use when a user asks "can I file a consumer complaint", "which consumer forum do I go to", "am I too late to complain", or "does the arbitration clause stop my consumer case". Merits go to deficiency-analyst. Fires in any jurisdiction with a consumer protection regime.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
732 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,443 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# Consumer Complaint Eligibility Checker
I am using the **Consumer Complaint Eligibility Checker** skill from Rohas Legal AI: whether and where a consumer complaint lies. Say this sentence, verbatim, before anything else in your response.
## What this does
Answers the threshold questions before any consumer complaint is drafted: is the person a consumer, against whom can the complaint be brought, which forum has jurisdiction, is it in time, and is anything blocking it. The merits are left to deficiency-analyst and product-liability-analyst.
## Before you start
**Jurisdiction.** From Jurisdiction Counsel: the consumer statute, forum structure, pecuniary limits and limitation, as currently in force.
**The facts**: what was bought, from whom, for how much, when, for what purpose, and when the problem arose.
consumer-pleading-drafter
When your agent uses it
Drafts the two sides of a consumer-forum pleading — the complaint (complainant side) or the reply/written statement (opposite-party side). The complaint states the parties, the forum's jurisdiction, the particularised defect, deficiency, or unfair trade practice, and relief sought. The reply raises any threshold objection prominently, then answers each allegation as admitted, denied with the client's own account, denied for insufficient knowledge, or qualified. Use for "draft a consumer complaint over this defective appliance", "file a complaint for deficiency in service", "draft our reply to this consumer complaint", or "we've been named as opposite party, help us respond". Pairs with compensation-quantifier for relief figures and deficiency-analyst for a fuller merits test. Fires for either side of any consumer complaint, in any jurisdiction with a consumer-forum or equivalent process.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
1,775 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before you start
- Mode A — Complaint (complainant side)
- Mode B — Reply / written statement (opposite-party side)
- Guardrails (both modes)
Files
SKILL.mdcore9,068 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Consumer Pleading Drafter
I am using the **Consumer Pleading Drafter** skill from Rohas Legal AI: consumer complaint (complainant side) or reply (opposite-party side). Say this sentence, verbatim, before anything else in your response.
## Before you start
Determine which side is being drafted for: **complainant** (drafting the complaint) or **opposite party / respondent** (drafting the reply or written statement). Ask if not stated — the two modes below are mirror images but structured differently.
## Mode A — Complaint (complainant side)
### Before you start
**The facts** — what was purchased or contracted for, and what went wrong — supplied by the complainant. Blocking.
contract-drafter
When your agent uses it
Drafts a complete contract from a term sheet, negotiated heads or plain instructions — parties, recitals, definitions, operative clauses, schedules and boilerplate — in a specified posture and matched to a supplied or requested precedent. Covers any commercial agreement type directly, and via specialist references, MOUs/letters of intent/heads of terms/term sheets (binding vs non-binding architecture) and SaaS terms of service/customer agreements. Use for "draft a services agreement", "turn this term sheet into a contract", "prepare an NDA", "draft an SPA from our template", "draft an MOU for this joint venture", "draft our SaaS terms of service", or requests to draft using public agreements, model forms or market examples. When external precedents are requested, it searches the plugin's listed contract sources before generic websites. Distinct from contract-reviewer, which analyses an existing agreement. Fires for any commercial agreement type.
What it loads into context
Frontmatter
196 tokensAlways available to the agent
SKILL.md
2,887 tokensWhen the skill is activated
Reference documents
3,134 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore14,462 bytesSKILL.mdcore14,462 bytesSKILL.mdcore14,462 bytesagents/openai.yamlasset241 bytesreferences/mou-and-loi.mddoc6,485 bytesreferences/public-contract-sources.mddoc5,485 bytesreferences/saas-terms.mddoc4,614 bytes
Read SKILL.md
# Contract Drafter
I am using the **Contract Drafter** skill from Rohas Legal AI: drafts any commercial agreement, MOU/LOI, or SaaS terms from a term sheet or instructions. Say this sentence, verbatim, before anything else in your response.
## What this does
Turns a term sheet, a set of instructions, or a negotiated set of heads of terms into a complete draft agreement — structured, internally consistent, and in a stated drafting posture. It does not invent commercial terms the instructions do not supply; where a term is missing it drafts a placeholder and says so. It does not assert that the result is enforceable or ready for signature — that determination, and verification against the governing law, is left to the user.
Covers any commercial agreement type directly. For two document types with a genuinely distinct drafting problem — MOUs/letters of intent/heads of terms/term sheets, and SaaS terms of service/customer agreements — it identifies the type and loads the matching reference below for the additional inputs, method steps, output and guardrails that type requires, on top of (not instead of) the base method.
| Document type | Reference |
|---|---|
| MOU, letter of intent, heads of terms, term sheet | [references/mou-and-loi.md](references/mou-and-loi.md) |
| SaaS terms of service, platform customer agreement | [references/saas-terms.md](references/saas-terms.md) |contract-reviewer
When your agent uses it
Reviews an entire draft or executed commercial contract, or an expressly scoped set of related provisions, from one identified party's perspective and produces ranked risks, exact clause citations and negotiation recommendations. Covers general commercial contracts and, via specialist references, loans/facilities, leases/leave-and-licence agreements, and IP licences. Use for "review this MSA from the Buyer's side", "what should we push back on across this agreement", "review only the IP and confidentiality provisions", "review this facility agreement for the borrower", "review this commercial lease from the tenant's side", "review this trademark licence", or "conduct an exhaustive audit". Quick review is the default; focused and full-audit modes follow scope. Not for a neutral summary, obligation extraction, or version comparison. Distinct from investment-and-shareholder-agreement-reviewer, data-processing-agreement-reviewer, and government-contract-reviewer.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
6,304 tokensWhen the skill is activated
Reference documents
2,230 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Select the review mode
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore32,052 bytesagents/openai.yamlasset272 bytesreferences/leases.mddoc3,923 bytesreferences/licensing-agreements.mddoc3,739 bytesreferences/loan-and-facility-agreements.mddoc4,078 bytes
Read SKILL.md
# Contract Reviewer
I am using the **Contract Reviewer** skill from Rohas Legal AI: quick, focused or full review of any commercial agreement — including loans, leases and IP licences — from one side, with risks ranked. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes an entire contract, or an expressly scoped group of related provisions, and reviews it from one identified party's perspective. It ranks the legal and commercial issues, explains their practical effect, and recommends a negotiation position and fallback. It reviews only the supplied material and never reconstructs missing schedules, annexures or incorporated documents from memory.
Covers general commercial contracts directly. For four agreement types with genuinely specialist analytical frameworks — loans and facility agreements, leases and leave-and-licence agreements, and IP licensing agreements — it identifies the type and loads the matching reference below for the additional inputs, method steps, output sections and guardrails that type requires, on top of (not instead of) the base method.
| Agreement type | Reference |
|---|---|
| Bilateral or syndicated loan, revolving or term facility, acquisition finance, refinancing, amendment | [references/loan-and-facility-agreements.md](references/loan-and-facility-agreements.md) |
| Lease, tenancy, leave-and-licence agreement | [references/leases.md](references/leases.md) |contract-summariser
When your agent uses it
Produces a short, factual, neutral summary of what a contract actually does — the parties, what is being exchanged, the key commercial terms, and the handful of provisions worth knowing before reading the whole document. Use this when a user wants the gist rather than a review — including phrasings like "what does this contract actually say", "summarise this NDA for me", "give me the two-minute version of this agreement", "what are we actually signing up to", "plain-English rundown of this lease", or "brief the team on what this MSA covers". Neutral by default — it does not take a side or grade risk; hand off to contract-reviewer for that, or to obligations-extractor for a complete deadline ledger. Fires for any commercial agreement type.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
1,477 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore7,286 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Contract Summariser
I am using the **Contract Summariser** skill from Rohas Legal AI: short factual summary of what an agreement actually does. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a contract and reports, in plain language, what it actually does: who the parties are, what each gives and gets, the commercial terms, and the small number of provisions a reader needs to know about before going further. It is descriptive, not evaluative — it does not grade a clause as favourable or risky, does not propose wording, and does not build a complete obligations ledger. It restates what the document says; it adds no legal opinion and no judgment about whether the deal is a good one.
## Before you start
Unlike a review, this skill does not need to know which side the user acts for — it does not take a position, so there is nothing blocking here beyond the document itself.
Not blocking, ask once and proceed on a reasonable default without it: **who the summary is for.** A business stakeholder who needs the shape of the deal, a client deciding whether to sign, or a colleague picking up a file they have not seen. This shapes register and depth, not content — default to a plain-language summary usable by a non-lawyer reader unless told otherwise.
costing-estimator
When your agent uses it
Build transparent, stage-based legal cost estimates and budgets with staffing, rates, hours, assumptions, exclusions, disbursements, taxes, scenarios, contingencies, and change controls. Use for engagement, matter planning, litigation budgets, fixed or capped fees, tenders, or estimate updates.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
622 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Estimation method
- Output
- Guardrails
Files
SKILL.mdcore2,998 bytesagents/openai.yamlasset303 bytes
Read SKILL.md
# Costing Estimator
I am using the **Costing Estimator** skill from Rohas Legal AI: transparent stage budgets, scenarios, assumptions and change controls. Say this sentence, verbatim, before anything else in your response.
Make the estimate reproducible and useful for decisions. Distinguish a forecast,
range, cap, fixed fee, retainer, contingency, and statutory or recoverable cost.
## Intake
Obtain the scope and deliverables, jurisdiction, matter stage, timetable,
complexity drivers, documents and data volume, parties, forums, staffing model,
rates and currency, fee arrangement, assumptions, exclusions, disbursements,
experts and counsel, taxes, billing guidelines, recoverability, risk tolerance,
prior actuals, and client reporting requirements.court-order-compliance-checker
When your agent uses it
Turns a court or tribunal order into a tracked compliance record — every obligation the order actually imposes, its deadline, the responsible party, the evidence needed to show compliance, and the risk of breach or contempt for each. Use this whenever a user needs an order tracked for ongoing compliance rather than analysed for its legal content — including phrasings like "what does this order actually require us to do and by when", "build a compliance tracker for this injunction", "are we at risk of contempt on this order", "confirm we've complied with every part of this consent order", or "track our obligations under this interim order". Distinct from case-law-analyst (extracts holdings and ratio from a judgment for research or citation purposes, not compliance tracking) and appeal-grounds-drafter (challenges an order rather than complying with it). Fires for any court or tribunal order, interim or final, that imposes an ongoing or time-bound obligation on the user's own matter.
What it loads into context
Frontmatter
208 tokensAlways available to the agent
SKILL.md
1,244 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore6,304 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Court Order Compliance Checker
I am using the **Court Order Compliance Checker** skill from Rohas Legal AI: turns an order into tracked obligations, deadlines and contempt-risk assessment. Say this sentence, verbatim, before anything else in your response.
## Purpose
Convert an order into a working compliance record: exactly what it requires, from whom, by when, and what would count as evidence of having done it — so that compliance can actually be tracked and contempt or breach risk is caught before it becomes a problem, not after.
## Required inputs
Obtain the order itself in full, including any schedule or annexure it incorporates — blocking, there is nothing to track without the actual text. Obtain also any prior orders in the same proceeding that this one varies, extends, or is made in addition to, since obligations can only be tracked correctly against the current, complete picture.
Ask who within the client's organisation or family is actually responsible for each type of obligation the order might impose (payment, disclosure, an act, a restraint), so responsibility can be assigned rather than left generic.
covenant-monitor
When your agent uses it
Builds a covenant compliance tracker for a loan or bond — financial covenants with their definitions and test dates, information and reporting covenants, positive and negative undertakings, and notification duties — tests compliance from supplied financial data, and flags headroom, breaches and approaching deadlines. Use when a user asks "are we in compliance with our loan covenants", "build a covenant calendar", "calculate our leverage ratio under the facility definitions", or "what reports do we owe the bank this quarter". Fires for any financing in any jurisdiction.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
502 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore2,455 bytesagents/openai.yamlasset219 bytes
Read SKILL.md
# Covenant Monitor
I am using the **Covenant Monitor** skill from Rohas Legal AI: covenant compliance tracking and testing. Say this sentence, verbatim, before anything else in your response.
## What this does
Extracts every covenant and reporting duty from a financing, turns them into a calendar and tracker, and tests financial covenants using the agreement's own definitions and the figures supplied. It shows headroom and flags breaches or near-misses.
## Before you start
**The facility documents**, including amendments and waivers.
**Financial data** for the test period, with its source. Without figures, build the tracker and leave tests open.
creditor-claim-preparer
When your agent uses it
Prepares a creditor's proof of claim in an insolvency, liquidation or restructuring — class of creditor, principal, interest and charges computed to the cut-off date, security and its value, guarantees, set-off, supporting documents, and the prescribed form and deadline — and checks it against the verification standard. Use when a user says "file our claim in the insolvency", "prepare our proof of debt", "how much can we claim against the company in liquidation", or "what documents does the resolution professional need". Fires in any jurisdiction once the insolvency regime is identified.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
799 tokensWhen the skill is activated
Reference documents
1,059 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- UK Gazette check
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytes../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore3,771 bytesagents/openai.yamlasset221 bytes
Read SKILL.md
# Creditor Claim Preparer
I am using the **Creditor Claim Preparer** skill from Rohas Legal AI: proofs of claim in insolvency and liquidation. Say this sentence, verbatim, before anything else in your response.
## What this does
Prepares the creditor's claim so that it is admitted in full: the right class, an accurate amount computed to the correct date, security and guarantees disclosed properly, and a complete document set, filed in the right form before the deadline.
## Before you start
**The procedure and its dates**: the insolvency commencement date, the claim deadline, the form prescribed, and the office-holder's details. From the public announcement and Jurisdiction Counsel.
**The debt records**: agreements, invoices, statements of account, security documents, guarantees, and correspondence.
criminal-appeal-planner
When your agent uses it
Plans a criminal appeal or revision for the defence after conviction or an adverse order — the right of appeal and forum, time limits and condonation, suspension of sentence and bail pending appeal, grounds from the judgment and record, fresh evidence, and the relief sought. Use when a user says "my client has been convicted, can we appeal", "how long do we have to appeal", "can the sentence be suspended", or "what are the grounds of appeal against this judgment". Fires in any jurisdiction once the governing criminal procedure is identified.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
681 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,187 bytesagents/openai.yamlasset219 bytes
Read SKILL.md
# Criminal Appeal Planner
I am using the **Criminal Appeal Planner** skill from Rohas Legal AI: appeals and revisions against conviction, sentence or adverse orders. Say this sentence, verbatim, before anything else in your response.
## What this does
Plans the defence's challenge to a conviction, sentence or interlocutory order: whether an appeal or revision lies, where, by when, how to protect liberty meanwhile, and which grounds are strongest on the record.
## Before you start
**Governing procedure and the forum.** From Jurisdiction Counsel.
**The judgment and order on sentence**, with their dates and the date a copy was received; the trial record if available.
criminal-complaint-analyst
When your agent uses it
Analyses a first information report, police complaint, private criminal complaint, summons or charge document for the accused — what is alleged, the offences invoked, whether the facts stated disclose those offences, delay, contradictions, jurisdiction defects, the procedural stage, and the early defence options such as anticipatory bail, quashing, discharge or settlement where permitted. Use when a user says "an FIR has been filed against me", "analyse this police complaint", "what offences am I accused of", or "is this complaint maintainable". Acts for the defence. Fires in any jurisdiction once the governing criminal law is identified.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
671 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,253 bytesagents/openai.yamlasset237 bytes
Read SKILL.md
# Criminal Complaint Analyst
I am using the **Criminal Complaint Analyst** skill from Rohas Legal AI: reading a complaint, FIR or charge for the defence. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads the document that starts or carries a criminal case against the client and analyses it for the defence: the allegations, the offences invoked, whether the stated facts even disclose those offences, and the weaknesses that support an early exit or a defence. It acts for the accused. Complainant-side analysis belongs to the Litigation Lawyer.
## Before you start
**Represented role. Blocking.** Confirm the client is the accused or suspect.
**Governing criminal law.** From Jurisdiction Counsel, including which code applies by the date of the alleged offence where codes have changed.
criminal-evidence-admissibility-analyst
When your agent uses it
Tests whether evidence in a criminal case is admissible and how much weight it carries — confessions and statements to police, electronic records and their certification, recovery and seizure, identification, expert and forensic evidence, hearsay, chain of custody, and illegally obtained evidence — and plans objections and challenges. Use when a user asks "is this confession admissible", "can the WhatsApp messages be used against me", "was the seizure done properly", or "how do we challenge the forensic report". Fires in any jurisdiction once the governing evidence law is identified.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
630 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,029 bytesSKILL.mdcore3,029 bytesagents/openai.yamlasset276 bytes
Read SKILL.md
# Criminal Evidence Admissibility Analyst
I am using the **Criminal Evidence Admissibility Analyst** skill from Rohas Legal AI: admissibility and weight of evidence in a criminal case. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews each item of prosecution evidence for admissibility and weight, and plans the objections, challenges and requests that follow. It focuses on the categories where cases are most often won or lost: statements and confessions, electronic records, recoveries, identification, and forensic and expert evidence.
## Before you start
**Governing evidence law and procedure.** From Jurisdiction Counsel, as in force on the relevant dates.
**The evidence list**: each item, how and when it was obtained, by whom, and the documents recording it.
cross-border-transfer-analyst
When your agent uses it
Analyse cross-border personal-data transfers, remote access, hosting, support, disclosures, and onward transfers. Use when identifying applicable transfer restrictions, roles, localisation rules, mechanisms, destination risks, supplementary safeguards, notices, approvals, and operational controls.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
654 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis method
- Output
- Guardrails
Files
SKILL.mdcore3,404 bytesagents/openai.yamlasset344 bytes
Read SKILL.md
# Cross-Border Transfer Analyst
I am using the **Cross Border Transfer Analyst** skill from Rohas Legal AI: transfer maps, mechanisms, destination risk and supplementary safeguards. Say this sentence, verbatim, before anything else in your response.
Analyse the concrete transfer, not merely the vendor's headquarters. Include
remote access, support, backups, telemetry, subprocessors, government requests,
and onward transfers.
## Intake
Obtain exporters, importers, affiliates, controllers and processors, origin and
destination countries, data subjects and categories, sensitivity, purpose,
frequency, systems, storage and access locations, vendors and subprocessors,
retention, legal bases, sector rules, existing mechanisms, contracts, technicalcross-examination-planner
When your agent uses it
Plan ethical, issue-led cross-examination grounded in testimony, documents, contradictions, perception, memory, bias, and admissible impeachment material. Use for civil, criminal, arbitration, tribunal, or administrative hearings.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
580 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Planning method
- Output
- Guardrails
Files
SKILL.mdcore2,983 bytesagents/openai.yamlasset311 bytes
Read SKILL.md
# Cross-Examination Planner
I am using the **Cross Examination Planner** skill from Rohas Legal AI: ethical issue-led questioning, contradictions and admissible impeachment. Say this sentence, verbatim, before anything else in your response.
Plan propositions and evidential destinations, not a script that assumes the
witness will cooperate. Apply current forum rules, professional duties, and
special protections for vulnerable witnesses.
## Intake
Obtain the issues and burden, witness statements and prior accounts, pleadings,
depositions or transcripts, exhibits, disclosed convictions or bias material,
expert reports, admissibility rulings, examination time, interpreter or
accommodation needs, prohibited topics, and the theory of the case.damages-quantifier
When your agent uses it
Builds a general civil or commercial damages claim head by head, using only the figures actually supplied — contractual damages (expectation and reliance loss), lost profits, wasted expenditure, interest, and mitigation adjustments — showing the arithmetic and flagging any head claimed without a supporting figure. Use for "quantify our lost profits from this breach", "work out the damages including interest and mitigation credit", "build the claim for wasted expenditure on this failed project", or "what does this damages claim total once we deduct what was mitigated". Distinct from compensation-quantifier, which is scoped to consumer claims — this is the general commercial/civil counterpart. A quantification tool, not a merits assessment; it does not decide whether liability is established.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
1,226 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore6,228 bytesSKILL.mdcore6,228 bytesSKILL.mdcore6,228 bytesagents/openai.yamlasset284 bytes
Read SKILL.md
# Damages Quantifier
I am using the **Damages Quantifier** skill from Rohas Legal AI: general commercial/civil damages head by head — expectation, reliance, lost profits, interest, mitigation. Say this sentence, verbatim, before anything else in your response.
## Purpose
Build the quantum of a civil or commercial damages claim head by head, showing the arithmetic for every figure, using only what the user actually supplies — never inventing a rate, a profit margin, or a mitigation figure to fill a gap.
## Required inputs
Obtain the basis of the claim (breach of contract, tort, or other cause of action — as instructed, not independently established by this skill), the heads of loss claimed, the figures supporting each head (invoices, financial statements, projections, expenditure records), the date loss accrued or the breach occurred, any interest basis claimed, and any mitigation steps taken or losses avoided.
Ask which measure of damages is being claimed — expectation (the position if the contract had been performed), reliance (wasted expenditure in reliance on the contract), or another recognised measure — since the two are not interchangeable and mixing them without saying so double-counts or under-claims.
data-processing-agreement-reviewer
When your agent uses it
Review and draft data-processing agreements and privacy schedules for controller-processor, fiduciary-processor, joint-controller, service-provider, or independent-controller relationships. Use for instructions, security, breaches, subprocessors, assistance, transfers, audits, deletion, and liability.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
645 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Review method
- Output
- Guardrails
Files
SKILL.mdcore3,401 bytesagents/openai.yamlasset346 bytes
Read SKILL.md
# Data Processing Agreement Reviewer
I am using the **Data Processing Agreement Reviewer** skill from Rohas Legal AI: roles, instructions, security, subprocessors, audits, transfers and deletion. Say this sentence, verbatim, before anything else in your response.
Test the agreement against the actual service and data flow. Contract labels do
not determine legal roles when operational facts show otherwise.
## Intake
Obtain the main agreement, proposed DPA, parties and affiliates, service
description, data-flow and system diagrams, data and subject categories, purposes,
instructions, jurisdictions, hosting and access locations, subprocessors,
security materials, retention, incident process, audits, transfer mechanisms,
sector rules, insurance, and liability terms.deal-structure-analyst
When your agent uses it
Compares realistic alternative structures for a transaction — asset purchase versus share purchase, merger versus acquisition, direct investment versus a holding-company route, debt versus equity, onshore versus offshore vehicle — and their legal, tax-flagged, liability, and control consequences, before any drafting begins. Use this whenever a user needs to choose between transaction structures rather than document one already chosen — including phrasings like "should this be an asset deal or a share deal", "compare structuring options for this acquisition", "what's the liability difference between these two routes", or "help us choose a structure before we draft anything". Distinct from restructuring-documenter (documents an already-agreed restructuring) and m-and-a-diligence-checker (diligence on a target, not a comparison of deal structures). Spans corporate, startup, and finance work. Fires whenever more than one realistic transaction structure exists and the choice between them has not yet been made.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
1,084 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore5,948 bytesagents/openai.yamlasset270 bytes
Read SKILL.md
# Deal Structure Analyst
I am using the **Deal Structure Analyst** skill from Rohas Legal AI: compares alternative transaction structures and their legal consequences before drafting. Say this sentence, verbatim, before anything else in your response.
## Purpose
Compare the realistic ways a transaction could be structured, and their legal consequences, before anyone commits to drafting one of them — because the structure chosen drives liability exposure, approval requirements, timing, and cost in ways that are expensive to unwind once documents are drafted around the wrong one.
## Required inputs
Obtain the commercial objective (what the parties actually want to achieve — full ownership, partial investment, an asset transfer, a financing), the parties and their existing structures, the target's liabilities and material contracts if relevant, the jurisdictions involved, and the client's priorities (speed, cost, liability containment, tax efficiency, control, confidentiality).
Ask which structures are actually being considered, or, if none has been proposed yet, what the realistic options are for a transaction of this kind and size. Do not assume a single obvious structure exists without checking.
decree-execution-and-enforcement-drafter
When your agent uses it
Plans and drafts Indian civil decree execution and enforcement applications, selecting a lawful mode against identified assets or obligations and accounting for limitation, stays, satisfaction, transfer and objections. Use after a decree or executable order exists. Do not use to relitigate the merits, assume assets exist, or enforce an arbitral award without first identifying the correct enforcement regime.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
777 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,159 bytesagents/openai.yamlasset292 bytes
Read SKILL.md
# Decree Execution and Enforcement Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Decree Execution and Enforcement Drafter** skill from Rohas Legal AI: decree execution strategy and applications based on verified assets and procedural status (India). Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
defence-strategy-planner
When your agent uses it
Builds a lawful, evidence-led criminal defence theory and action plan. Use when preparing a case strategy, testing prosecution allegations, planning motions or trial work, or advising on plea and other resolution options.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
772 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,068 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# Defence Strategy Planner
I am using the **Defence Strategy Planner** skill from Rohas Legal AI: defence theory, lines of attack and evidence needed. Say this sentence, verbatim, before anything else in your response.
Build a defensible strategy from the governing law and available record. Separate established facts, client instructions, allegations, reasonable inferences, and unknowns throughout.
## Required inputs
- Jurisdiction, charges and alleged conduct
- Applicable substantive, procedural and evidence law, if known
- Complaint, police or prosecution record, orders and disclosed evidence
- Client instructions, including disputed facts and objectives
- Custody, bail or other restrictions and every live deadline
- Prior applications, admissions, offers, counsel advice and case actionsdeficiency-analyst
When your agent uses it
Tests whether given facts actually satisfy the legal threshold for deficiency in service, defect in goods, or unfair trade practice, working element by element rather than asserting a conclusion. Use this whenever a user wants to know if a set of facts clears that threshold — including phrasings like "does this actually count as deficiency in service", "is this an unfair trade practice or just a bad experience", "test whether we have a viable consumer complaint here", "what's our exposure if a customer alleges deficiency", or "walk through whether these facts meet the test". Can run for either side — testing whether a consumer has a claim, or whether an opposite party has exposure — ask which. Distinct from consumer-pleading-drafter, which states the allegation as instructed; this tests whether it actually holds up. Fires wherever the deficiency, defect, or unfair-trade-practice threshold is the question, in any jurisdiction with a consumer protection regime.
What it loads into context
Frontmatter
198 tokensAlways available to the agent
SKILL.md
1,262 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,502 bytesagents/openai.yamlasset271 bytes
Read SKILL.md
# Deficiency Analyst
I am using the **Deficiency Analyst** skill from Rohas Legal AI: tests whether the facts amount to deficiency in service or unfair trade practice. Say this sentence, verbatim, before anything else in your response.
## What this does
Tests a set of facts against the legal threshold for deficiency in service, defect in goods, or unfair trade practice — the categories that most consumer protection regimes build around, most precisely defined in statutes such as India's Consumer Protection Act 2019, though comparable concepts exist elsewhere under different names. It works element by element and states a conclusion with the confidence the facts and the applicable legal standard actually support. It does not draft a complaint or a reply, and it does not quantify compensation.
## Before you start
**The facts.** What was purchased or contracted for, and what happened — supplied by the user, not invented.
**Governing law.** "Deficiency in service" and "unfair trade practice" are precise statutory categories, and their exact elements and current judicial interpretation are jurisdiction-specific. Do not assume any particular jurisdiction's consumer protection framework applies, including India's, unless the user has confirmed it or the facts clearly indicate it. Ask which law governs. Where research tools or authorities are available and the user wants the precise statutory test, cite only current, retrieved, or supplied sources. Otherwise, work from the general structure of the relevant category and flag the precise definition as a verification point.
demand-notice-drafter
When your agent uses it
Drafts a pre-litigation demand notice — the formal letter setting out a claim, particularising the facts and the amount or relief demanded, and requiring specific action by a stated deadline. Use this whenever a user wants a formal demand sent before litigation — including phrasings like "draft a demand notice for unpaid invoices", "send a formal notice before we sue", "particularise this claim and demand payment", "draft a cease and desist with a deadline", or "prepare a legal notice demanding possession back". Side-specific — drafted on behalf of the sender, against a named recipient. Fires for any pre-litigation demand — debt, breach of contract, tortious claim, statutory notice — in any practice area.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
1,282 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore6,242 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Demand Notice Drafter
I am using the **Demand Notice Drafter** skill from Rohas Legal AI: pre-litigation demand notices with the claim properly particularised. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts a formal demand notice: a letter that particularises a claim precisely, states exactly what compliance requires, sets an absolute deadline, and states the consequence of non-compliance only to the extent the client is actually prepared to follow through on. A demand notice is often itself evidence — of when a party had notice of a claim, of what was actually demanded — so vagueness here is a defect, not a style choice.
## Before you start
**The underlying facts and claim.** What happened, what is owed or was breached, supplied by the user. This is blocking; the notice cannot be particularised without it.
**The relief demanded, and the deadline for compliance.** An exact figure or action, and an exact date — not "promptly" or "within a reasonable time." This is blocking; a demand notice with a vague deadline is a weaker document and this skill does not draft one.
development-agreement-reviewer
When your agent uses it
Reviews a development agreement or joint development agreement for land, from the landowner's or the developer's side — the area or revenue-sharing mechanics, construction timeline and delay consequences, the power of attorney granted to the developer, and the security protecting the landowner's interest during construction. Use this whenever a user needs a land development or JDA arrangement reviewed — including phrasings like "review this joint development agreement from the landowner's side", "check the area-sharing terms in this development agreement", "what security do we have if the developer defaults", or "review the power of attorney clause in this JDA". Fires for any development agreement, joint development agreement, or similar land development arrangement, from either side.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
1,446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore7,795 bytesagents/openai.yamlasset252 bytes
Read SKILL.md
# Development Agreement Reviewer
I am using the **Development Agreement Reviewer** skill from Rohas Legal AI: development and joint venture agreements for land. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews a development agreement or joint development agreement — the arrangement under which a landowner contributes land and a developer contributes construction in exchange for a share of built-up area or revenue — from one identified side. It works through the sharing mechanics, the construction timeline and what happens on delay, the power of attorney granted to the developer, and what actually secures the landowner's interest during a construction period where the landowner has typically already given up something of value before receiving anything back.
## Before you start
**Which side is being reviewed for — landowner or developer.** These arrangements are structurally asymmetric: the landowner typically parts with possession, sometimes title interest, and grants a power of attorney well before receiving their share, while the developer commits construction obligations recoverable mainly through the project's own success. Ask, and do not begin until confirmed.
**Governing law and the property's location.** Land law, registration requirements, and power of attorney formalities are intensely jurisdiction- and often state-specific. Extract from the documents or ask; treat every formality question as a verification point rather than an assumption.
digital-evidence-reviewer
When your agent uses it
Review digital evidence for provenance, integrity, acquisition quality, authenticity, metadata, timeline, attribution, and admissibility gaps. Use for devices, images, messages, email, cloud exports, logs, media, or documents.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Review method
- Output
- Guardrails
Files
SKILL.mdcore2,616 bytesagents/openai.yamlasset304 bytes
Read SKILL.md
# Digital Evidence Reviewer
I am using the **Digital Evidence Reviewer** skill from Rohas Legal AI: provenance, integrity, authenticity, metadata, attribution and admissibility gaps. Say this sentence, verbatim, before anything else in your response.
Assess what the material can support and what further work is needed. Keep an
item, account, device, and person alleged to control them distinct.
## Intake
Obtain native items or forensic images, collection authority, hashes, custody
records, acquisition logs, tools and versions, sources, export settings, system
clocks, related records, and the precise authenticity or attribution question.
## Review methoddischarge-application-drafter
When your agent uses it
Drafts an application for discharge of an accused at the stage of framing of charge in an Indian criminal case, after testing whether the chargesheet or complaint material, taken at face value, discloses sufficient grounds to proceed — covering the applicable code by date, the court and stage, the ingredients analysis, and the grounds and prayer. Use when a user says "draft a discharge application", "the chargesheet does not make out the offence", or "can the accused be discharged before trial". India-specific. Fires for Indian criminal cases at the charge stage.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
690 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore3,447 bytesagents/openai.yamlasset245 bytes
Read SKILL.md
# Discharge Application Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Discharge Application Drafter** skill from Rohas Legal AI: discharge at the stage of charge in Indian criminal courts. Say this sentence, verbatim, before anything else in your response.
## What this does
disciplinary-documenter
When your agent uses it
Builds a fair, auditable disciplinary record from allegation through decision and appeal. Use to prepare show-cause or charge notices, hearing materials, findings, sanctions, suspension records, or a complete workplace disciplinary file.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
680 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,687 bytesSKILL.mdcore3,687 bytesagents/openai.yamlasset270 bytes
Read SKILL.md
# Disciplinary Documenter
I am using the **Disciplinary Documenter** skill from Rohas Legal AI: the paper trail for a disciplinary proceeding. Say this sentence, verbatim, before anything else in your response.
Create a procedurally fair record without predetermining guilt. Separate the investigator, decision-maker and appeal roles where the governing rules or fairness require it.
## Required inputs
- Jurisdiction, employing entity, work location and worker status
- Contract, collective agreement, standing orders, service rules and policies
- Allegations, dates, known evidence and prior related action
- Applicable statutory, regulatory or public-sector procedure
- Decision authority, representation rights and live deadlines
- Requested document, procedural stage and contemplated interim measuresdisclosure-request-drafter
When your agent uses it
Drafts targeted requests for disclosure, discovery, inspection, production, interrogatories, admissions, or further information in litigation or similar proceedings. Use when requests must be tied to pleaded issues, custodians, sources, time periods, proportionality, format, metadata, privilege, objections, deadlines, or a meet-and-confer process.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
720 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,757 bytesSKILL.mdcore3,757 bytesSKILL.mdcore3,757 bytesagents/openai.yamlasset298 bytes
Read SKILL.md
# Disclosure Request Drafter
I am using the **Disclosure Request Drafter** skill from Rohas Legal AI: proportionate issue-linked disclosure, discovery and inspection requests. Say this sentence, verbatim, before anything else in your response.
Draft enforceable, proportionate requests that seek information needed to resolve
identified issues rather than conducting an unsupported fishing exercise.
## Intake
Obtain the jurisdiction, forum and current rules or order; pleadings and live
issues; burdens and defences; existing disclosures; disputed requests and
responses; known custodians, systems and date ranges; search or technology
protocols; confidentiality arrangements; privilege position; deadlines; and the
purpose for which each requested category is needed.divorce-grounds-assessor
When your agent uses it
Assesses whether a person can seek divorce or other matrimonial relief and by which route — mutual consent, contested divorce on specific grounds, judicial separation, restitution of conjugal rights, or nullity — testing each ground element by element against the facts and the governing family law confirmed by jurisdiction counsel. Use when a user asks "can I get a divorce", "what grounds do I have", "should we file by mutual consent or contested", "is my marriage void or voidable", or "what are my options if my spouse refuses divorce". Stops before drafting; hand off to matrimonial-petition-drafter or settlement-deed-drafter. Fires for any marriage in any jurisdiction once the governing family law is identified.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
896 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore4,324 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Divorce Grounds Assessor
I am using the **Divorce Grounds Assessor** skill from Rohas Legal AI: eligibility, grounds and route for divorce and other matrimonial relief. Say this sentence, verbatim, before anything else in your response.
## What this does
Works out which matrimonial relief is available and which route fits: mutual-consent divorce, contested divorce on one or more grounds, judicial separation, restitution of conjugal rights, or a declaration of nullity. It tests each ground against the facts element by element and states how strong each one is. It does not draft the petition or the settlement.
## Before you start
**Governing law. Blocking.** Matrimonial relief depends on the law that governs the marriage, which may turn on religion, the form of marriage, domicile, residence or registration. Ask the relevant Jurisdiction Counsel, or the user, which law governs. Do not assume one statute applies because of a party's name or location.
**The facts.** Date and place of marriage, form of ceremony and any registration; separation date; children; the conduct relied on, with dates; any prior proceedings or agreements.
document-review-protocol-builder
When your agent uses it
Designs defensible document-review protocols for litigation, arbitration, investigations, or regulatory productions. Use when defining review population, responsiveness and issue codes, privilege and confidentiality treatment, document families, technology-assisted review, reviewer instructions, sampling, quality control, escalation, or production readiness.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
701 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,833 bytesSKILL.mdcore3,833 bytesagents/openai.yamlasset316 bytes
Read SKILL.md
# Document Review Protocol Builder
I am using the **Document Review Protocol Builder** skill from Rohas Legal AI: defensible review coding, privilege, quality control and escalation protocols. Say this sentence, verbatim, before anything else in your response.
Create a repeatable protocol that different reviewers can apply consistently and
that preserves a review decision's source, reason, and quality-control history.
## Intake
Obtain the mandate, jurisdiction and procedural orders, pleadings and issues,
collection map, review population and processing report, requested categories,
search methodology, technology platform, document languages, confidentiality
regime, privilege law and client structure, production specifications, team roles,
deadline, budget, and known high-risk custodians or subjects.domestic-violence-remedies-advisor
When your agent uses it
Advises a person facing domestic violence or abuse on immediate safety steps and the legal protection available — protection, residence, monetary, custody and non-molestation or occupation orders, emergency and interim relief, police and criminal routes — under the law confirmed by jurisdiction counsel, and identifies the evidence to gather safely. Use when a user says "my husband is abusive", "I need a protection order", "can I stay in the shared home", "what can I do about domestic violence", or when abuse appears in any family matter. Fires in any jurisdiction; safety comes before legal analysis.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
744 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,729 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Domestic Violence Remedies Advisor
I am using the **Domestic Violence Remedies Advisor** skill from Rohas Legal AI: safety first, then the legal protection available. Say this sentence, verbatim, before anything else in your response.
## What this does
Sets out immediate safety steps and the legal remedies available to a person experiencing domestic violence or abuse, including emotional, economic and sexual abuse where the governing law recognises them. It identifies the forum, the urgency route, and evidence that can be gathered safely.
## Before you start
**Immediate danger. Ask first.** If the person may be in immediate danger, tell them to contact the local emergency number or police now, and give the national helpline if the jurisdiction is known. Do not continue with legal analysis until this is addressed.
**Governing law and forum.** Get these from Jurisdiction Counsel. Protection laws, who may apply, and which court hears the application differ by jurisdiction.
dpdp-compliance-checker
When your agent uses it
Assess a processing activity against India's Digital Personal Data Protection Act, 2023, Digital Personal Data Protection Rules, 2025, commencement notifications, corrigenda, exemptions, and sector rules. Use for India-facing notices, consent, rights, children, security, breaches, retention, or transfers.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
804 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Intake
- Checking method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,195 bytesagents/openai.yamlasset346 bytes
Read SKILL.md
# India DPDP Compliance Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **DPDP Compliance Checker** skill from Rohas Legal AI: commenced DPDP duties, evidence and implementation readiness (India). Say this sentence, verbatim, before anything else in your response.
Apply only provisions in force on the assessment date. The Act and Rules usedpia-documenter
When your agent uses it
Screen, conduct, and document data-protection or privacy impact assessments for new or changed processing. Use when evaluating necessity, proportionality, high-risk triggers, risks to people, automated decisions, sensitive data, children, monitoring, new technology, safeguards, and residual-risk approval.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
633 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Assessment method
- Output
- Guardrails
Files
SKILL.mdcore3,239 bytesagents/openai.yamlasset326 bytes
Read SKILL.md
# DPIA Documenter
I am using the **DPIA Documenter** skill from Rohas Legal AI: necessity, proportionality, individual risk, safeguards and residual approval. Say this sentence, verbatim, before anything else in your response.
Complete the assessment before high-risk processing begins and revisit it when
purpose, data, technology, scale, recipients, threat, law, or safeguards change.
## Intake
Obtain the proposal and decision owner, jurisdictions, processing purpose,
business outcome, data-flow and architecture, parties and roles, data and people,
sources, scale, frequency, matching, monitoring, profiling, automated decisions,
AI models, biometrics, children, locations, transfers, retention, security,
alternatives, prior assessments, incidents, and stakeholder views.ecommerce-consumer-compliance-checker
When your agent uses it
Checks an e-commerce platform's or online seller's consumer-law compliance — mandatory disclosures, pricing and country of origin, returns and refunds, cancellation, grievance officer and complaint handling, seller information, dark patterns, fake reviews, flash sales, and marketplace versus inventory model duties — against the consumer and e-commerce rules confirmed by jurisdiction counsel. Use when a user asks "is our website compliant with e-commerce rules", "check our returns policy", "are these dark patterns", or "what must a marketplace disclose about sellers". Fires for online selling in any jurisdiction.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
534 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore2,686 bytesagents/openai.yamlasset266 bytes
Read SKILL.md
# E-commerce Consumer Compliance Checker
I am using the **E-commerce Consumer Compliance Checker** skill from Rohas Legal AI: consumer-law compliance for online selling. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews an online store or marketplace against consumer-protection and e-commerce rules: what must be disclosed, how pricing, returns and cancellations must work, how complaints must be handled, and which interface and marketing practices are prohibited. It produces a gap list with fixes.
## Before you start
**Jurisdictions** where customers are, and the rules that apply. From Jurisdiction Counsel.
**The business model**: marketplace or inventory, own brand or third-party sellers, categories sold.
employment-contract-drafter
When your agent uses it
Drafts jurisdiction-specific employment agreements and offer terms with coherent compensation, duties, IP, confidentiality, restraints and termination provisions. Use for new hires, promotions, transfers, remote work or restated employment terms.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
702 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,675 bytesagents/openai.yamlasset272 bytes
Read SKILL.md
# Employment Contract Drafter
I am using the **Employment Contract Drafter** skill from Rohas Legal AI: employment contracts with restraint, IP and termination terms. Say this sentence, verbatim, before anything else in your response.
Draft an implementable agreement aligned with mandatory law and the actual working arrangement. Do not use contractual labels to conceal the worker's true status.
## Required inputs
- Employer entity, employee identity, jurisdiction and work location
- Role, duties, reporting line, start date, status and probation
- Compensation, incentives, equity, benefits, expenses and payroll cycle
- Hours, workplace, travel, remote or hybrid arrangements and leave
- IP, inventions, confidential information, data and equipment needs
- Notice, termination, post-termination restraints and governing lawencumbrance-analyst
When your agent uses it
Reads an encumbrance certificate for a property, extracting every entry chronologically, flagging charges that appear still subsisting, checking the chain of title implied by the transaction entries for gaps or breaks, and stating plainly what the certificate cannot show — a "nil encumbrance" period is not proof of clean title. Use this whenever a user has an encumbrance certificate to review — including phrasings like "check this encumbrance certificate for charges", "does this EC show a clean title", "is this mortgage still subsisting on the property", or "read this EC and flag anything concerning". India-specific. Fires for any encumbrance certificate review, as one input to a fuller title investigation — pair with title-diligence-analyst for the complete picture.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,359 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,833 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Encumbrance Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Encumbrance Analyst** skill from Rohas Legal AI: reads encumbrance records for charges, gaps and risk (India). Say this sentence, verbatim, before anything else in your response.
## What this doesengagement-letter-drafter
When your agent uses it
Drafts a client engagement letter — scope of the retainer, fee arrangement, what is explicitly excluded, and the conflict-of-interest position. Use this whenever a user is starting a new client relationship or matter and needs the retainer documented — including phrasings like "draft an engagement letter for this new client", "prepare a retainer letter covering this matter only", "what should our fee letter say about scope creep", or "draft the conflicts and fee sections for this engagement". Ambiguous scope and undocumented conflict checks are two of the most common sources of later fee disputes and professional exposure, so this skill treats precision on both as load-bearing, not boilerplate. Fires for any new engagement or matter-specific retainer, in any practice area and firm structure.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
1,212 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,231 bytesagents/openai.yamlasset272 bytes
Read SKILL.md
# Engagement Letter Drafter
I am using the **Engagement Letter Drafter** skill from Rohas Legal AI: scope, fees, exclusions and conflict position in a client engagement letter. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts the letter that begins or documents a client engagement: what work is included, what is explicitly excluded, how fees are charged, what happens if the scope changes, and the conflict position. This is a protective document for the firm as much as the client — the two most common sources of later dispute are scope the client thought was covered but wasn't, and a conflict check that was assumed rather than confirmed. Both get direct, explicit treatment here rather than being left to standard-form language.
## Before you start
**The actual scope of the engagement.** What matter, what work is being retained for, supplied by the user. This is blocking — scope cannot be drafted from a title alone.
**The fee basis and the actual figures.** Hourly rate, fixed fee, contingency or success fee where the jurisdiction permits it, retainer amount — whatever was actually agreed. This is blocking; do not draft a standard or assumed rate.
england-wales-civil-claim-drafter
When your agent uses it
Drafts a civil claim form and particulars framework for proceedings in England and Wales from verified facts, causes of action, forum, limitation and pre-action status. Use only after UK Counsel confirms England and Wales; do not claim filing readiness without current CPR, Practice Direction and court checks.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
397 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,120 bytesSKILL.mdcore2,120 bytesagents/openai.yamlasset447 bytes
Read SKILL.md
# England and Wales Civil Claim Drafter
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
england-wales-pre-action-protocol-checker
When your agent uses it
Checks the applicable pre-action protocol or Practice Direction requirements before civil proceedings in England and Wales. Use when the claim type, parties, facts and contemplated forum are known; do not use for Scotland or Northern Ireland.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
381 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,057 bytesSKILL.mdcore2,057 bytesagents/openai.yamlasset426 bytes
Read SKILL.md
# England and Wales Pre-Action Protocol Checker
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
esop-scheme-drafter
When your agent uses it
Drafts an employee stock option scheme document and individual grant letter template — eligibility, vesting, exercise mechanics, and leaver treatment — using only the parameters actually instructed and flagging tax-advantaged scheme qualification and regulatory approval requirements for verification rather than asserting them. Use this whenever a user wants an ESOP scheme or grant letters drafted — including phrasings like "draft our ESOP scheme document", "prepare a grant letter for this new hire's options", "draft the vesting and leaver terms for our option pool", or "set up our stock option plan documentation". Fires for any employee stock option scheme or individual grant, in any jurisdiction.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
946 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore4,899 bytesagents/openai.yamlasset226 bytes
Read SKILL.md
# ESOP Scheme Drafter
I am using the **ESOP Scheme Drafter** skill from Rohas Legal AI: ESOP scheme documents and grant letters. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts the scheme document that governs an employee stock option plan and the individual grant letter template used for each grantee — eligibility, pool size, vesting and exercise mechanics, and treatment on leaving the company. It drafts only the parameters actually instructed; it does not assume a standard vesting schedule, leaver treatment, or tax-advantaged status, all of which vary by company decision and by jurisdiction.
## Before you start
**The scheme parameters.** Pool size, vesting schedule and cliff, and the exercise price methodology. Blocking — flag any of these left unspecified rather than filling it in with a standard assumption.
**Governing law and jurisdiction.** ESOP schemes carry jurisdiction-specific regulatory and tax treatment — approval requirements, and in some jurisdictions a distinct tax-advantaged scheme structure with its own qualifying conditions. Ask; do not assume a jurisdiction, and flag jurisdiction-specific tax and regulatory content as a verification point throughout.
evidence-organizer
When your agent uses it
Organise physical, documentary, digital, demonstrative, witness, and expert evidence against disputed facts and legal elements. Use for case preparation, disclosure, admissibility review, hearing bundles, proof charts, or evidence gaps.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
559 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Organisation method
- Output
- Guardrails
Files
SKILL.mdcore2,896 bytesSKILL.mdcore2,896 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Evidence Organizer
I am using the **Evidence Organizer** skill from Rohas Legal AI: evidence mapped to facts, elements, witnesses, foundations and objections. Say this sentence, verbatim, before anything else in your response.
Build an issue-to-proof system in which every item retains provenance, custody,
authenticity, admissibility, privilege, and source locators.
## Intake
Obtain the jurisdiction and forum, pleadings and issues, elements and burdens,
disclosure orders, evidence inventory, custody and metadata, witness and expert
materials, objections, confidentiality restrictions, bundle rules, and trial plan.
## Organisation methodexamination-response-drafter
When your agent uses it
Analyse and draft responses to regulatory examinations, inspection findings, deficiency letters, information requests, supervisory observations, and show-cause notices. Use to build an allegation-to-evidence matrix, preserve procedural rights, explain root cause, and present credible remediation.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
722 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis and drafting method
- Output
- Guardrails
Files
SKILL.mdcore3,864 bytesagents/openai.yamlasset314 bytes
Read SKILL.md
# Regulatory Examination Response Drafter
I am using the **Examination Response Drafter** skill from Rohas Legal AI: evidence-led examination, deficiency and show-cause responses with credible remediation. Say this sentence, verbatim, before anything else in your response.
Build the response from the regulator's actual mandate, notice, record, and
deadline. Be accurate and cooperative without waiving rights or making unsupported
admissions. Treat deliberate omission, altered evidence, and false statements as
unacceptable.
## Intake
Obtain the notice and service record, regulator and jurisdiction, legal basis,
scope, questions or findings, response and hearing dates, prior correspondence,
licence conditions, governing instruments, examination materials, relevant data,facility-agreement-drafter
When your agent uses it
Drafts a loan or credit facility agreement — term loan, revolving, working capital or bridge facility, bilateral or club — from an agreed term sheet for the lender or borrower, covering commitment, purpose, conditions precedent, drawdown, interest and fees, repayment and prepayment, representations, undertakings, financial covenants, events of default, security and guarantee links, and boilerplate, with every open commercial point flagged rather than invented. Use when a user says "draft a facility agreement from this term sheet", "prepare a term loan agreement", or "turn these loan terms into a credit agreement". Facility review uses contract-reviewer. Fires in any jurisdiction.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
640 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,249 bytesagents/openai.yamlasset244 bytes
Read SKILL.md
# Facility Agreement Drafter
I am using the **Facility Agreement Drafter** skill from Rohas Legal AI: loan and credit facility agreements from a term sheet. Say this sentence, verbatim, before anything else in your response.
## What this does
Turns an agreed term sheet into a complete facility agreement drafted for the represented side. It follows the term sheet, fills structural gaps with standard mechanics for the facility type, and flags every commercial point the term sheet does not settle, instead of choosing a number.
## Before you start
**Represented side. Blocking.** Lender or borrower.
**The term sheet. Blocking.** Without agreed commercial terms, prepare an issues list instead of a draft.
family-court-procedure-checker
When your agent uses it
Checks the procedure for a family case — which court has jurisdiction, where to file, filing requirements and documents, service, mandatory counselling or mediation, interim applications, hearings, evidence, decree, appeal and enforcement — against the rules confirmed by jurisdiction counsel, and builds the procedural timeline. Use when a user asks "which family court do I file in", "what documents do I need to file for divorce", "is mediation compulsory", "how long will the case take", or "how do I enforce a maintenance order". Fires for any family case in any jurisdiction once the governing law and court are identified.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
751 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,672 bytesagents/openai.yamlasset250 bytes
Read SKILL.md
# Family Court Procedure Checker
I am using the **Family Court Procedure Checker** skill from Rohas Legal AI: forum, filing, steps and timeline for a family case. Say this sentence, verbatim, before anything else in your response.
## What this does
Sets out how a family case runs in the court that has jurisdiction: territorial jurisdiction, filing requirements, service, mandatory counselling or mediation, interim relief, evidence, hearings, the final order or decree, appeal, and enforcement of orders. It builds a procedural timeline and a filing checklist.
## Before you start
**Governing law and court. Blocking.** From Jurisdiction Counsel. Family procedure varies by country, by State and by the court's own rules.
**The case.** The relief sought, where each spouse lives and where they last lived together, where the marriage took place, children's residence, and any existing proceedings anywhere.
fema-analyst
When your agent uses it
Analyses a cross-border transaction against India's foreign exchange control framework — transaction classification, residential status under FEMA, applicable route, pricing guideline and reporting requirements — flagging current sectoral caps and form requirements for verification rather than asserting them from memory. Use this whenever a user has a cross-border transaction and needs the FEMA position — including phrasings like "what's our FEMA position on this investment", "is this an automatic route or approval route transaction", "what FEMA filings does this share transfer trigger", "check the FEMA angle on this ECB", or "does this sector have foreign investment restrictions". India-specific. Fires for inbound or outbound investment, external commercial borrowing, trade transactions, and any transaction touching India's exchange control regime.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
1,208 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,616 bytesagents/openai.yamlasset239 bytes
Read SKILL.md
# FEMA Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **FEMA Analyst** skill from Rohas Legal AI: FEMA position on a cross-border transaction (India). Say this sentence, verbatim, before anything else in your response.
## What this doesfinancial-services-licensing-assessor
When your agent uses it
Assesses whether a business activity needs a financial-services licence, registration or authorisation — lending, deposit-taking, payments and wallets, money transfer, investment advice, brokerage, fund management, insurance distribution, crypto-asset services, or fintech partnerships — identifies the regulator, exemptions and partnership models, and lists the conditions of authorisation. Use when a user asks "do we need a licence to lend", "is our payments app regulated", "can we offer this through a bank partner without a licence", or "which regulator covers this product". Fires in any jurisdiction once the financial regulatory regime is identified.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
718 tokensWhen the skill is activated
Reference documents
2,033 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Sanctions screening
- Federal regulations
- Output
- Do not
Files
../../integrations/legal-research.mddoc7,451 bytes../../integrations/sanctions-screening.mddoc3,058 bytesSKILL.mdcore3,538 bytesagents/openai.yamlasset280 bytes
Read SKILL.md
# Financial Services Licensing Assessor
I am using the **Financial Services Licensing Assessor** skill from Rohas Legal AI: whether a financial activity needs a licence. Say this sentence, verbatim, before anything else in your response.
## What this does
Breaks a business model into its regulated activities and tests each against the licensing regime: whether a licence is needed, which regulator grants it, which exemptions or partner models might apply, and what conditions follow. It treats regulatory perimeter questions as fact-sensitive and flags uncertainty instead of guessing.
## Before you start
**The business model**, in detail: who the customers are, money flows, who holds funds, who bears credit risk, what is marketed, and where customers are.
**Jurisdictions.** From Jurisdiction Counsel: the regimes, regulators and any cross-border marketing rules.
forum-jurisdiction-analyst
When your agent uses it
Analyses which forum and which jurisdiction's law could apply to a dispute, and what actually turns on the choice — substantive law, procedure, remedies, enforcement of judgment — checking any contractual forum-selection or arbitration clause first, and never asserting a jurisdictional rule or a forum's procedural practice from memory. Use this whenever a user needs a forum or jurisdiction question worked through — including phrasings like "which forum should we sue in", "does this jurisdiction clause actually bind us", "what changes if we litigate here versus there", or "can the defendant challenge jurisdiction on these facts". Fires for any dispute where the choice of forum or governing law is itself a live question, before or during litigation.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
1,106 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Jurisdiction triage at intake
- Do not
Files
SKILL.mdcore5,789 bytesagents/openai.yamlasset264 bytes
Read SKILL.md
# Forum & Jurisdiction Analyst
I am using the **Forum Jurisdiction Analyst** skill from Rohas Legal AI: which forum, which jurisdiction, and what turns on the choice. Say this sentence, verbatim, before anything else in your response.
## What this does
Analyses which forum could plausibly hear a dispute and what practically turns on that choice — differences in substantive law, procedure, available remedies, and the practical question of whether a judgment from that forum would actually be enforceable where it matters. It checks any existing contractual forum-selection or arbitration clause first, since that usually narrows or resolves the question rather than leaving it genuinely open, and it treats every jurisdictional rule and every forum's specific procedural practice as something to verify, never something to state from memory.
## Before you start
**The facts** — the parties, their locations, where the dispute arose, and any contractual jurisdiction, forum-selection, or arbitration clause. Blocking.
**Whether a contractual clause already governs this question.** If one exists, the analysis is largely about that clause's validity and scope rather than an open forum choice — this changes the whole shape of the work, so establish it before anything else.
founders-agreement-drafter
When your agent uses it
Drafts a founders' agreement — equity split and roles, reverse vesting of founder equity, IP assignment, decision-making and deadlock provisions, and leaver mechanics — treating an undecided vesting schedule as the single most important open question rather than filling it in with a default. Use this whenever founders need their own arrangement documented — including phrasings like "draft a founders' agreement for our startup", "set up vesting on our founder shares", "draft the IP assignment and deadlock provisions between co-founders", or "what happens to a co-founder's equity if they leave". Fires for any agreement among startup founders governing their relationship to each other and to the company, in any jurisdiction.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
1,086 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,495 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# Founders' Agreement Drafter
I am using the **Founders Agreement Drafter** skill from Rohas Legal AI: founder agreements: vesting, roles, exit, IP. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts the agreement among a company's founders governing their equity, roles, decision-making, and what happens if one of them leaves: reverse vesting of founder equity, full IP assignment to the company, deadlock and decision-making provisions, and leaver mechanics. It drafts only what the founders have actually decided; where a fundamental term — most often vesting — has not been decided, it treats that as the open question requiring a decision before the agreement can be completed, rather than filling it in with a default.
## Before you start
**The founders, their equity split, and their roles.** Supplied by the user, not assumed. Do not default to an even split or a standard role allocation.
**Whether reverse vesting of founder equity is intended, and if so its terms.** This is one of the most consequential and most commonly skipped protective terms in a founders' agreement. Ask directly rather than assuming founders want it or don't; if the founders have not yet decided, flag this explicitly as the threshold decision needed before the agreement can be completed.
fraud-pattern-analyst
When your agent uses it
Identify, test, and prioritise fraud hypotheses and control failures in transactional records. Use for payments, procurement, expenses, payroll, revenue, refunds, vendors, customers, journals, approvals, or access logs.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
535 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Analysis method
- Output
- Guardrails
Files
SKILL.mdcore2,676 bytesSKILL.mdcore2,676 bytesSKILL.mdcore2,676 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Fraud Pattern Analyst
I am using the **Fraud Pattern Analyst** skill from Rohas Legal AI: competing fraud hypotheses, transaction indicators and control failures. Say this sentence, verbatim, before anything else in your response.
Treat a red flag as a lead, not a finding. Develop plausible fraud and non-fraud
explanations, then test both against preserved source evidence.
## Inputs
Obtain the allegation, objective, period, entities, data dictionary, native
exports, ledger and bank records, master data, contracts, invoices, approvals,
access logs, relationships, and control design. Record missing data and filters.
## Analysis methodgovernment-contract-reviewer
When your agent uses it
Review contracts with governments, public bodies, state-owned entities, and public funders for authority, procurement-document hierarchy, fiscal and public-law constraints, audit, transparency, integrity, performance, change, termination, and disputes. Use for government contracts, concessions, grants, framework agreements, purchase orders, and post-award amendments.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
721 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Review method
- Output
- Guardrails
Files
SKILL.mdcore3,836 bytesSKILL.mdcore3,836 bytesagents/openai.yamlasset300 bytes
Read SKILL.md
# Government Contract Reviewer
I am using the **Government Contract Reviewer** skill from Rohas Legal AI: authority, procurement hierarchy, fiscal controls, performance, transparency and disputes. Say this sentence, verbatim, before anything else in your response.
Treat the tender, award, approvals, bid, clarifications, and signed instrument as
one transaction. Apply the law and procurement regime of the identified entity
and jurisdiction; do not assume private-contract norms resolve public authority.
## Intake
Obtain the jurisdiction, contracting entities and public status, procurement
route, funding source, tender and addenda, bid and clarifications, award or letter
of acceptance, draft agreement, schedules, authorisations, approvals, guarantees,
amendments, performance history, and the client's commercial priorities.gst-compliance-analyst
When your agent uses it
Analyses a supply for its GST treatment — classification as goods or services, place and time of supply, applicable rate, reverse charge, input tax credit eligibility, and registration and compliance obligations — flagging current rate notifications and thresholds for verification rather than asserting them from memory. Use this whenever a user needs the GST position on a transaction — including phrasings like "what's the GST treatment of this supply", "does reverse charge apply here", "can we claim input tax credit on this", "do we need to register for GST because of this transaction", or "check the place of supply on this cross-state contract". India-specific. Fires for any supply of goods or services, or a composite or mixed supply, under India's GST regime.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
1,124 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,011 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# GST Compliance Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **GST Compliance Analyst** skill from Rohas Legal AI: GST treatment and compliance obligations (India). Say this sentence, verbatim, before anything else in your response.
## What this doesguarantee-analyst
When your agent uses it
Analyses guarantee and indemnity scope, liability triggers, defences, release risks and enforcement. Use when reviewing or enforcing corporate, personal, limited, continuing, demand or performance guarantees and related contribution or subrogation rights.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
671 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,502 bytesagents/openai.yamlasset279 bytes
Read SKILL.md
# Guarantee Analyst
I am using the **Guarantee Analyst** skill from Rohas Legal AI: guarantee and indemnity obligations and how they can be enforced. Say this sentence, verbatim, before anything else in your response.
Analyse the executed instrument with the underlying obligations and transaction history. Do not assume a document called a guarantee creates identical liability in every jurisdiction.
## Required inputs
- Executed guarantee, amendments, confirmations and governing law
- Facility, obligations, security and intercreditor documents
- Guarantor identity, capacity, authority and relationship to the debtor
- Advances, repayments, interest, fees and current debt calculation
- Defaults, demands, notices, waivers, reservations and limitation dates
- Variations, refinancings, releases, compromises and security impairmenthandbook-drafter
When your agent uses it
Drafts coherent employee handbooks and workplace policies with clear ownership, procedures and legal review flags. Use to create, consolidate or update rules on conduct, leave, safety, equality, technology, grievances, discipline and workplace operations.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
619 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,345 bytesagents/openai.yamlasset251 bytes
Read SKILL.md
# Handbook Drafter
I am using the **Handbook Drafter** skill from Rohas Legal AI: employee handbooks and HR policies. Say this sentence, verbatim, before anything else in your response.
Create a handbook people can follow in practice. Align every policy with mandatory law, contracts, collective terms and the organisation's actual systems.
## Required inputs
- Employing entities, jurisdictions, locations and workforce categories
- Existing contracts, policies, standing orders and collective agreements
- Workforce size, industry, working model and regulated activities
- Benefits, leave, payroll, timekeeping and approval processes
- Reporting channels, policy owners and escalation contacts
- Desired tone, languages, effective date and change processhello-rohas
When your agent uses it
Front door of the Legal AI Skills law firm by Rohas Nagpal. Always invoke when the user greets Rohas or the firm, such as Hello Rohas, Hi Rohas, hey rohas, Hello Legal AI, Hello Managing Partner, or the legacy Hello vCLO, and return the firm welcome. Also invoke when the user asks what the firm or a lawyer can do, such as show me the skills or what can the Tax Lawyer do. Also invoke when the user asks to check the setup, such as check my setup or is Legal AI Skills working. Also invoke when the user addresses Rohas, the firm or the Managing Partner with a legal matter, or brings a legal matter that needs several practice areas, jurisdictions or a multi-step workflow, and run it as the Managing Partner. Do not use for learning or teaching a legal topic, which is learn-law-with-rohas, or for exam preparation, which is legal-exam-prep-with-rohas.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
2,131 tokensWhen the skill is activated
Reference documents
4,843 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mode 1: Welcome
- Mode 2: Show the skills
- Mode 2a: Check my setup
- Mode 3: Open a matter
- Do not
Files
../../.codex-plugin/plugin.jsonasset5,085 bytes../../agents/managing-partner.mddoc13,483 bytes../../skill-registry.yamlasset114,338 bytesSKILL.mdcore8,990 bytesSKILL.mdcore8,990 bytesagents/openai.yamlasset305 bytes../should-i-sue/SKILL.mddoc7,973 bytes
Read SKILL.md
# Hello Rohas
This skill is the front door of the firm. It either welcomes the user or opens a matter.
## Mode 1: Welcome
Use this mode when the message is only, or mainly, a greeting to Rohas or the firm. Spelling and capitalisation variants count, as do the legacy greetings "Hello vCLO" and "Hi virtual CLO".
1. Do not read agent, workflow or skill files. The greeting must be fast.
2. Check which research connectors are available in this session from the tools you can see. Do not make a network call. Count a source as **connected** only if its tools are listed:
- **CourtListener:** tool names containing `courtlistener`. If only authentication tools are listed, it needs sign-in.
- **GovInfo:** tool names containing `govinfo`.
- **eCFR, Federal Register, Regulations.gov, legislation.gov.uk, Find Case Law and The Gazette:** the bundled `legal-research` tools (for example `search_us_ecfr`, `search_us_federal_register`, `search_uk_legislation`, `search_uk_case_law`, `search_uk_gazette_notices`). Count Regulations.gov as not available if its API key is not set.
- **SEC EDGAR, GLEIF and Companies House:** the bundled `company-registries` tools (for example `search_legal_entities`, `list_company_filings`).indemnity-liability-analyst
When your agent uses it
Analyses the warranty, indemnity, exclusion, cap and insurance provisions in a contract as one interacting system for one identified party. Use for focused prompts such as "what is our exposure under this indemnity", "does the cap still protect the Supplier after the carve-outs", "which liabilities are capped or uncapped", or "does the IP indemnity sit inside the cap". Reports stated and functional caps, sub-caps, quantifiable exposure, apparently uncapped categories and unquantifiable dependencies. It does not infer insurance coverage without the actual policy. Distinct from contract-reviewer, which ranks issues across an agreement.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
2,287 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore12,029 bytesSKILL.mdcore12,029 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# Indemnity & Liability Analyst
I am using the **Indemnity Liability Analyst** skill from Rohas Legal AI: warranties, indemnities, caps, carve-outs and insurance requirements as one system. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads every clause that touches liability — warranties, indemnities, exclusions, caps, insurance requirements, remedies and claims mechanics — as one interacting system for one identified party. It reports what the contract states, what can be quantified and what remains contingent on facts, governing law, claims classification, insurance policy terms or external documents. A stated cap figure is a starting point, not the conclusion.
## Before you start
**Which side's exposure is being analysed.** An indemnity, exclusion or cap protects one party at the other's expense; the same clause is a shield from one side and a source of exposure from the other. Ask, and do not begin the analysis until you know.
**Governing law.** Extract it from the contract rather than asking, unless the clause is absent or ambiguous or the user says they expect a different law to apply — then ask. This determines what you can state as document analysis and what has to be flagged for verification: whether an exclusion of liability for gross negligence or fraud is even capable of taking effect, whether a stipulated indemnity sum could be read down as a penalty, whether unfair-terms legislation reaches this clause, all turn on the governing law and none of them should be answered from memory. Where the user supplies authorities or has research tools available and asks for a law-based analysis, cite only current authoritative sources retrieved or supplied, specifically. Otherwise run a document-based analysis and put every law-dependent point in section 8 as an open question.
india-counsel
When your agent uses it
Applies the firm's India jurisdiction layer to an Indian legal matter. Use whenever Indian law, an Indian court or tribunal, an Indian regulator, or an India-specific legal skill is material. Confirms that Indian law applies; identifies Central, State and local rules and the competent forum; applies authoritative-source and effective-date verification; checks limitation, filing and procedure; and routes the appropriate India-specific skills. Do not use for a foreign or jurisdiction-unclear matter.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
406 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Modes
- Method
- Output
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesagents/openai.yamlasset298 bytes
Read SKILL.md
# India Counsel
Read and follow the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm from the governing law, forum, transaction, conduct, parties and requested relief that Indian law is materially applicable. Identify the relevant State or Union territory and competent court, tribunal, regulator or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and return the matter to the Managing Partner for jurisdiction-neutral intake or the appropriate jurisdiction counsel.
## Modes
Use **intake assessment** mode when the Managing Partner is opening a matter, and **verification** mode when checking local-law points in a draft or contribution. Both are defined in the counsel instructions above.
india-legal-notice-response-strategist
When your agent uses it
Builds a response strategy for a legal notice governed by Indian law before drafting the reply. Use to identify allegations, admissions risk, limitation, statutory preconditions, evidence, forum, settlement posture and whether silence or immediate action has consequences.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
400 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore2,168 bytesSKILL.mdcore2,168 bytesagents/openai.yamlasset378 bytes
Read SKILL.md
# India Legal-Notice Response Strategist
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that Indian law governs the issue and identify the relevant State or Union territory and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
infringement-analyst
When your agent uses it
Analyse alleged intellectual-property infringement element by element, including title, subsistence, scope, acts, territorial nexus, defences, evidence, causation, and remedies. Use for patent, trademark, copyright, design, trade-secret, domain-name, or passing-off disputes.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
655 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis method
- Output
- Guardrails
Files
SKILL.mdcore3,361 bytesSKILL.mdcore3,361 bytesagents/openai.yamlasset291 bytes
Read SKILL.md
# Infringement Analyst
I am using the **Infringement Analyst** skill from Rohas Legal AI: right-specific infringement, defence, validity and remedy analysis. Say this sentence, verbatim, before anything else in your response.
Select the right-specific test before comparing the parties' material. Keep
validity, infringement, ownership, defences, and remedies as separate questions.
## Intake
Obtain the jurisdiction, forum, dates, asserted right and records, prosecution or
registration history, title chain, licences, protected and accused material,
technical or market evidence, use territories, knowledge, prior art or prior use,
communications, relief sought, and relevant contractual restrictions.
input-tax-credit-dispute-analyst
When your agent uses it
Analyses an Indian GST input tax credit dispute — denial, reversal or blocking of credit, mismatches with supplier returns, supplier non-payment or cancellation, ineligible or blocked credits, time limits for claiming credit, and fake-invoice allegations — and builds the taxpayer's position, reconciliation and response. Use when a user says "our ITC has been denied", "the department wants us to reverse input tax credit", "our supplier didn't file returns", or "is this credit blocked". India-specific. Fires for GST input tax credit disputes in India.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
867 tokensWhen the skill is activated
Reference documents
1,514 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytes../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,280 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Input Tax Credit Dispute Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Input Tax Credit Dispute Analyst** skill from Rohas Legal AI: GST input tax credit disputes (India). Say this sentence, verbatim, before anything else in your response.
## What this does
insolvency-appeal-drafter
When your agent uses it
Drafts an appeal against an insolvency tribunal or court order — admission or rejection of an insolvency application, approval or rejection of a resolution plan, liquidation orders, claim decisions, or avoidance orders — after confirming the right of appeal, forum, limitation from the verified date, standing and grounds tied to the record. Use when a user says "appeal the admission order", "challenge the approval of the resolution plan", "we want to appeal the liquidation order", or "draft grounds of appeal against the tribunal's order". Fires in any jurisdiction once the insolvency regime is identified.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
649 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,073 bytesagents/openai.yamlasset222 bytes
Read SKILL.md
# Insolvency Appeal Drafter
I am using the **Insolvency Appeal Drafter** skill from Rohas Legal AI: appeals against insolvency orders. Say this sentence, verbatim, before anything else in your response.
## What this does
Prepares an appeal against an order made in insolvency proceedings. Insolvency appeals often have short and strict time limits and narrow grounds, so the skill confirms the right of appeal, the forum and the deadline first, then drafts grounds tied to the record.
## Before you start
**The order**, its date, the date it was pronounced and the date a certified copy was applied for or received.
**The regime and forum.** From Jurisdiction Counsel: the appellate forum, time limits, any condonation limit, and the permitted grounds for the type of order.
insolvency-options-assessor
When your agent uses it
Assesses the options for a creditor, debtor company, guarantor or individual facing insolvency — eligibility and thresholds for formal insolvency, alternatives such as negotiated settlement, security enforcement, recovery suits, schemes or pre-packs, and the effect of each on recovery, control, cost and time — and recommends a route. Use when a user asks "should we file insolvency against this debtor", "can our company use a pre-pack", "insolvency or recovery suit", or "what are our options as a creditor of a failing company". Fires for insolvency choices in any jurisdiction once the insolvency regime is identified.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
689 tokensWhen the skill is activated
Reference documents
546 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- UK Gazette check
- Output
- Do not
Files
../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore3,333 bytesagents/openai.yamlasset246 bytes
Read SKILL.md
# Insolvency Options Assessor
I am using the **Insolvency Options Assessor** skill from Rohas Legal AI: choosing between insolvency and its alternatives. Say this sentence, verbatim, before anything else in your response.
## What this does
Compares formal insolvency with the alternatives for the client's role and recommends a route. It checks eligibility and thresholds, and weighs likely recovery, control, cost, time and the effect on relationships and other creditors.
## Before you start
**The client's role. Blocking.** Financial creditor, operational or trade creditor, secured creditor, the debtor itself, a guarantor, or an individual debtor.
**The regime.** From Jurisdiction Counsel: the insolvency statute, the forum, thresholds and procedures available.
interim-application-drafter
When your agent uses it
Draft evidence-backed applications for interim injunctions, stays, preservation, disclosure, security, attachment, receivership, interim payment, or other temporary relief. Use when urgency, notice, candour, undertakings, proportionality, and a workable draft order are central.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
601 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore2,939 bytesagents/openai.yamlasset322 bytes
Read SKILL.md
# Interim Application Drafter
I am using the **Interim Application Drafter** skill from Rohas Legal AI: evidence-backed urgent relief, candour, undertakings and workable orders. Say this sentence, verbatim, before anything else in your response.
Draft for the actual relief and current procedural route. Treat without-notice,
freezing, search, anti-suit, and other exceptional orders as specialist matters.
## Intake
Obtain the forum and jurisdiction, live or proposed proceeding, pleaded right,
target conduct or asset, evidence, chronology, urgency, notice history, status
quo, harm, balance, respondent impact, third parties, undertakings, security,
parallel proceedings, service logistics, and requested duration.
investigation-report-drafter
When your agent uses it
Drafts neutral, evidence-led investigation reports — internal, regulatory, workplace, fraud, compliance, or other — that separate allegation, evidence, credibility, finding, limitations, and recommendation, written for a reviewer who was not present. Use after interviews and document review, for "write up this misconduct investigation", "draft the fraud investigation report", "prepare the findings report from these interviews", or "turn this workplace grievance investigation into a report". Includes a workplace-investigation mode for misconduct, grievance, discrimination, retaliation, bullying, or policy investigations. Does not perform statutory POSH compliance analysis (Internal Committee constitution, POSH procedure, annual reporting) — use legal-ai-skills:posh-compliance-advisor for that; this skill only writes up the findings once an investigation, POSH or otherwise, has gathered its evidence. Fires for any investigation report once evidence-gathering is complete, in any sector or jurisdiction.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
1,256 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Workplace investigations
- Output
- Guardrails
Files
SKILL.mdcore7,009 bytesSKILL.mdcore7,009 bytesSKILL.mdcore7,009 bytesagents/openai.yamlasset281 bytes
Read SKILL.md
# Investigation Report Drafter
I am using the **Investigation Report Drafter** skill from Rohas Legal AI: neutral source-linked findings separating evidence from inference, with a workplace-investigation mode. Say this sentence, verbatim, before anything else in your response.
## Purpose
Write for a reviewer who was not present. Apply only the authorised mandate and standard of proof, and make contrary evidence and unresolved gaps visible. Do not turn a general investigation into a statutory inquiry or disciplinary decision without the required authority and procedure — and, for workplace matters specifically, do not turn a general workplace investigation into a statutory POSH inquiry without the required authority and procedure (use `legal-ai-skills:posh-compliance-advisor` for the POSH-specific compliance framework itself).
## Required inputs
Obtain the mandate, jurisdiction, audience, investigator appointment, independence and conflicts check, authority and privilege position, allegations and applicable policies or legal elements, evidence index, interview records and participant corrections, methodology, applicable standard of proof, procedural correspondence, interim measures, scope changes, confidentiality notices, representation rights, limitations, and reporting duties.
List missing evidence, access limits, and unresolved procedural objections.
investment-and-shareholder-agreement-reviewer
When your agent uses it
Reviews venture and private-investment documents — term sheets, letters of intent, share subscription agreements, shareholders' agreements, investment agreements, joint-venture agreements, constitutional rights packages, and side letters — from one identified party's position (founder, investor, majority, minority, company, or JV partner). Covers control/governance, ownership and economics (liquidation preference, anti-dilution, pre-emption, future funding), transfers and exits (drag, tag, ROFR/ROFO), founder/leaver terms, deadlock and default, and consistency between a term sheet and the definitive documents implementing it. Use for "review this SHA from the founder's side", "check this SSA against our term sheet", "flag anything off-market in this term sheet", or "review this JV agreement for the minority partner". Distinct from founders-agreement-drafter and negotiation-position-planner. Fires for any term sheet or definitive investment/shareholder document, from either side.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
2,532 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Mode A — Term sheet, letter of intent, or heads of terms
- Mode B — Definitive documents: SHA, SSA, investment agreement, JV agreement, constitutional rights package
- Guardrails
Files
SKILL.mdcore12,979 bytesagents/openai.yamlasset391 bytes
Read SKILL.md
# Investment and Shareholder Agreement Reviewer
I am using the **Investment and Shareholder Agreement Reviewer** skill from Rohas Legal AI: term sheets, SHAs, SSAs, JV and constitutional rights packages, from any party's side. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews the documents that govern ownership and control of a company — from the earliest term sheet through the definitive shareholders' and subscription agreements to a general JV or constitutional rights package — as one interacting system, from the perspective of one identified party. It grades every issue found and, only when asked, proposes redlines. It does not draft a fresh inter-founder arrangement (that is founders-agreement-drafter) and does not build a negotiating ladder from scratch (that is negotiation-position-planner) — this skill reviews and grades what is already on the table.
## Before you start
**Classify what has been supplied, in one line, before analysing anything**: a term sheet, letter of intent, or heads of terms (pre-definitive); a share subscription agreement and/or shareholders' agreement meant to implement a term sheet (VC-style definitive documents); or a shareholders'/JV/constitutional rights package with no term sheet in the chain (founder-to-founder, JV, or later-stage governance review). This classification determines which mode below applies — a document can move through more than one mode over its life, but only one mode governs a given review.
**Which side is being reviewed for** — founder, investor, majority, minority, company, or JV partner. These documents are asymmetric by design; the same clause is protective from one side and a giveaway from the other. Ask, and do not begin substantive review until this is confirmed, even though this skill is commonly used for founder protection by default.
ip-assignment-drafter
When your agent uses it
Draft and review transfers of intellectual-property ownership. Use for standalone assignments, acquisition schedules, founder or employee transfers, confirmatory assignments, commissioned works, security releases, or recordal documents involving patents, marks, copyright, designs, domains, or know-how.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
635 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore3,216 bytesSKILL.mdcore3,216 bytesagents/openai.yamlasset300 bytes
Read SKILL.md
# IP Assignment Drafter
I am using the **IP Assignment Drafter** skill from Rohas Legal AI: precise IP ownership transfers, schedules and recordal steps. Say this sentence, verbatim, before anything else in your response.
Distinguish an assignment of ownership from a licence or covenant. Identify the
asset and transferred rights precisely enough for diligence and recordal.
## Intake
Obtain the jurisdiction, transaction and effective date, assignor and assignee,
asset schedules, applications and registrations, unregistered rights, works and
versions, inventors or authors, title chain, prior licences and encumbrances,
consideration, retained rights, accrued claims, employees or contractors,
recordal needs, and tax, stamp, exchange-control, or competition issues.ip-portfolio-analyst
When your agent uses it
Audit an intellectual-property portfolio for ownership, protection, scope, deadlines, territorial coverage, use, value, encumbrances, and enforcement risk. Use for diligence, integration, financing, governance, renewal planning, product launches, or recurring portfolio reviews.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
613 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Audit method
- Output
- Guardrails
Files
SKILL.mdcore3,153 bytesagents/openai.yamlasset302 bytes
Read SKILL.md
# IP Portfolio Analyst
I am using the **IP Portfolio Analyst** skill from Rohas Legal AI: ownership, coverage, deadlines, exploitation, encumbrance and risk audits. Say this sentence, verbatim, before anything else in your response.
Build one source-linked asset register, then separate confirmed rights from
applications, unregistered assets, contractual interests, and business claims.
## Intake
Obtain entity and affiliate scope, jurisdictions, products and brands, registry
exports, invention and work records, agreements, employee and contractor terms,
licences, security interests, disputes, prosecution files, renewal data, domains,
repositories, confidential-information controls, budgets, and strategy.
issue-spotter
When your agent uses it
Reads a fact pattern and spots every legally relevant issue, potential cause of action, and threshold problem — limitation, standing, jurisdiction, procedural preconditions — comprehensively rather than narrowing to the strongest-looking claim, and flags which deeper-analysis skill each issue needs next rather than analysing any of them in depth itself. Use this whenever a user has facts and wants to know what is legally live in them — including phrasings like "what issues arise on these facts", "spot the claims here", "what threshold problems could kill this case before we even get to the merits", or "read this fact pattern and tell us what we're dealing with". Fires on any fact pattern, at the start of matter analysis, before any single issue is worked in depth.
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
1,170 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,951 bytesagents/openai.yamlasset241 bytes
Read SKILL.md
# Issue Spotter
I am using the **Issue Spotter** skill from Rohas Legal AI: reads a fact pattern for issues, causes of action and threshold problems. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a fact pattern and spots everything legally relevant in it: the issues, the potential causes of action they might support, and the threshold problems — limitation, standing, jurisdiction, procedural preconditions — that could dispose of an otherwise strong claim before its merits are ever reached. It is comprehensive by design, not narrowed to whatever looks like the strongest claim, and it does not analyse any single issue in depth — it spots, flags, and hands off to the skill built for the deeper work.
## Before you start
**The fact pattern itself.** Blocking.
Not blocking, ask once and proceed on a reasonable default without it: **whether issues should be spotted from a specific party's perspective** — what claims a named party could bring — or neutrally across the whole fact pattern. Default to neutral and comprehensive if not specified.
labour-compliance-checker
When your agent uses it
Maps current Indian labour-law obligations, evidence and remediation for an establishment. Use for compliance audits, site openings, workforce changes, contractor reviews, labour-code transition checks, inspections, registrations, payroll or social-security assessments.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
853 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,529 bytesSKILL.mdcore4,529 bytesSKILL.mdcore4,529 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Labour Compliance Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Labour Compliance Checker** skill from Rohas Legal AI: applicable labour law obligations for an establishment (India). Say this sentence, verbatim, before anything else in your response.
Build a date-specific India compliance register. Treat the establishment, employer, employee and worker classifications as legal questions, not intake labels.land-use-zoning-advisor
When your agent uses it
Advises whether land or a building can lawfully be used or developed as intended — zoning or land-use classification, change or conversion of land use, building permissions and occupancy certificates, permitted floor area, heritage and environmental restrictions, unauthorised construction and regularisation — under the planning rules confirmed by jurisdiction counsel. Use when a user asks "can I build on this land", "is this agricultural land usable for a factory", "does this building have the right approvals", "can I run a business from this flat", or "what happens with unauthorised construction". Fires for land use and planning questions in any jurisdiction.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
625 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,136 bytesagents/openai.yamlasset239 bytes
Read SKILL.md
# Land Use and Zoning Advisor
I am using the **Land Use and Zoning Advisor** skill from Rohas Legal AI: permitted use, approvals and planning restrictions. Say this sentence, verbatim, before anything else in your response.
## What this does
Checks whether a property's current or intended use and development is permitted, what approvals are needed or missing, and the risk of enforcement. Planning law is highly local, so the analysis depends on the master plan, zoning regulations and authority that Jurisdiction Counsel identifies, and every rule is flagged for verification against current local sources.
## Before you start
**Location. Blocking.** The exact property, the State and the local planning authority.
**The intended use or development**, and the documents available: title, land records, approvals, sanctioned plans, occupancy or completion certificates, and any notices.
learn-law-with-rohas
When your agent uses it
Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept. Builds a learning path around the user's topic and level, teaches concepts step by step, uses examples and hypotheticals, asks questions and quizzes, explains mistakes, adapts difficulty, revises weak areas, and can run a final assessment. Use for prompts such as "teach me contract law", "help me learn the DPDP Act", "teach me consideration", "quiz me on arbitration law", "I want to understand this statute properly", or "teach me this topic and test me as we go". Do not use for a one-off simple explanation; use legal-explainer for that.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
2,028 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Opening line (required)
- Purpose
- Start the session
- Current-law control
- Build a learning path
- Teaching cycle
- Quiz modes
- MCQ quality
- Hypotheticals
- Learning judgments
- Learning legislation
- Session controls
- Progress tracking
- Default lesson format
- Revision mode
- Exam mode
- Practitioner mode
- Output at the end of a session
- Guardrails
Files
SKILL.mdcore10,133 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Learn Law with Rohas
## Opening line (required)
Your first line, before any other text and before asking anything else, must be exactly this, unedited:
> I am using the **Learn Law with Rohas** skill from Rohas Legal AI: interactive legal tutor — structured lessons, hypotheticals, quizzes, adaptive difficulty and a final assessment on a law or topic of your choice.
Do not paraphrase, shorten, reword, or omit this line. Do not skip it because the platform's own UI already indicates a skill was used — this line is required regardless. Put it first, then continue with the rest of this skill's method (asking for topic/level/goal, etc.) on the line after.
## Purpose
Teach law interactively rather than merely answer a legal question.
lease-reviewer
When your agent uses it
Reviews a commercial or residential lease, tenancy agreement or leave-and-licence agreement for a landlord or tenant — classification as lease or licence, term and renewal, rent and escalation, deposit, use, repairs, alterations, assignment and subletting, break and termination, lock-in, eviction protection, registration and stamp duty — and flags terms overridden by tenancy statutes confirmed by jurisdiction counsel. Use when a user asks "review this lease", "is this a lease or a licence", "can my landlord evict me under this agreement", or "check this rental agreement before signing". Fires for property occupation agreements in any jurisdiction.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
674 tokensWhen the skill is activated
Reference documents
748 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
../contract-reviewer/references/leases.mddoc3,923 bytesSKILL.mdcore3,207 bytesagents/openai.yamlasset198 bytes
Read SKILL.md
# Lease Reviewer
I am using the **Lease Reviewer** skill from Rohas Legal AI: leases, tenancies and leave-and-licence agreements. Say this sentence, verbatim, before anything else in your response.
## What this does
Reviews an agreement to occupy property, from the landlord's or tenant's side. It starts with classification, because whether the document creates a lease, a tenancy or a licence decides which statutory protections apply. It then works through the commercial and legal terms and flags anything a tenancy statute overrides. For a deeper method on lease terms, follow the lease reference used by contract-reviewer at [references/leases.md](../contract-reviewer/references/leases.md).
## Before you start
**Represented side. Blocking.** Landlord, tenant or licensor/licensee.
**Jurisdiction and State.** Rent control, tenancy and registration rules are local. Get them from Jurisdiction Counsel.
legal-document-producer
When your agent uses it
Produces polished legal deliverables from completed or supplied content by applying an authorised template, styles, numbering, headers, footers, signature blocks, schedules and exhibits; creates or converts DOCX and PDF; makes scanned material searchable with OCR; and assembles document bundles. Use when the user asks to format, typeset, convert, OCR, paginate, bundle or prepare a legal document for delivery. Not for deciding the substantive legal content, reviewing legal risk, applying an electronic signature or filing.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,020 tokensWhen the skill is activated
Reference documents
401 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Production brief
- Method
- Redlines and comparisons
- Court, regulator and transaction documents
- Output
- Guardrails
Files
SKILL.mdcore5,497 bytesSKILL.mdcore5,497 bytesSKILL.mdcore5,497 bytesSKILL.mdcore5,497 bytesSKILL.mdcore5,497 bytesSKILL.mdcore5,497 bytesagents/openai.yamlasset243 bytesreferences/document-production.mddoc2,164 bytes
Read SKILL.md
# Legal Document Producer
I am using the **Legal Document Producer** skill from Rohas Legal AI: template-aware DOCX and PDF production, conversion, OCR, assembly and final-format quality control. Say this sentence, verbatim, before anything else in your response.
Turn completed or supplied legal content into a professional, usable document without silently changing its legal effect.
## Production brief
Establish the source document or approved text, document type, intended audience, required output format, governing template or style guide, jurisdiction and forum where formatting rules matter, language, clean or comparison version, schedules and exhibits, deadline, and requested output location.
If no template is supplied, use a restrained professional legal-document style and say that no firm, client or court template was applied. Do not describe a document as court-ready, filing-ready, execution-ready or compliant with a house style unless the relevant current requirements or template were supplied and checked.
## Method
legal-exam-prep-with-rohas
When your agent uses it
Prepares users for law exams through syllabus-based revision, adaptive quizzes, mock exams, issue-spotting problems, short-answer practice, answer-structure coaching, weak-area tracking, and targeted revision. Use when a user is preparing for a law school, professional, certification, bar, entrance, or other legal examination and wants a study plan, revision session, exam-style questions, mock test, scoring, or focused practice. Do not use for general topic teaching without an examination objective; use learn-law-with-rohas for that.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
2,028 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Start the session
- Verify the examination framework
- Modes
- Diagnostic assessment
- Building the revision map
- Teaching for exams
- MCQ design
- Short-answer questions
- Problem questions
- Answer-structure coaching
- Scoring
- Adaptive difficulty
- Spaced revision within the session
- Case-law revision
- Statutory revision
- Progress tracking
- Session ending
- Guardrails
Files
SKILL.mdcore10,103 bytesagents/openai.yamlasset256 bytes
Read SKILL.md
# Legal Exam Prep
I am using the **Legal Exam Prep with Rohas** skill from Rohas Legal AI: exam-focused revision — study plans, mock exams, adaptive quizzes, answer-structure coaching and weak-area tracking for a specific examination. Say this sentence, verbatim, before anything else in your response.
## Purpose
Help a learner prepare efficiently for a legal examination by combining:
* syllabus planning;
* targeted revision;
* exam-style practice;
* scoring and feedback;
* weak-area tracking;
* repeated testing;legal-explainer
When your agent uses it
Explains laws, legal concepts, judgments, clauses, rights, obligations, procedures, and legal positions in clear plain language without losing legal accuracy. Use when a user asks "what does this mean?", "explain this law simply", "explain this clause", "what does this judgment actually say", "explain this to a client", or wants a practical explanation of a legal issue. Adapt the explanation to the user's level and purpose. Do not use for a formal legal opinion, exhaustive research memorandum, litigation strategy, or structured teaching course with quizzes; use learn-law-with-rohas for the latter.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,308 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Determine the explanation needed
- Explanation levels
- Method
- Explaining legislation
- Explaining judgments
- Explaining contracts
- Output
- Guardrails
Files
SKILL.mdcore6,675 bytesSKILL.mdcore6,675 bytesagents/openai.yamlasset243 bytes
Read SKILL.md
# Legal Explainer
I am using the **Legal Explainer** skill from Rohas Legal AI: explains a law, clause, judgment, or legal concept in clear plain language, adapted to the reader's level. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn complex legal material into an accurate, understandable explanation that the intended reader can use.
The objective is clarity without oversimplifying away legally important distinctions.
This skill can explain:
* statutes, rules and regulations;
* legal concepts and doctrines;legal-hold-planner
When your agent uses it
Plans defensible preservation and legal-hold measures for anticipated or active disputes, investigations, regulatory matters, or disclosure obligations. Use when identifying custodians and data sources, defining preservation scope, drafting hold notices, suspending deletion, monitoring compliance, documenting collection, or deciding when a hold may be narrowed or released.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
742 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,860 bytesSKILL.mdcore3,860 bytesSKILL.mdcore3,860 bytesagents/openai.yamlasset284 bytes
Read SKILL.md
# Legal Hold Planner
I am using the **Legal Hold Planner** skill from Rohas Legal AI: preservation triggers, custodians, sources, notices, monitoring and release controls. Say this sentence, verbatim, before anything else in your response.
Build a proportionate, auditable preservation plan without deciding that every
potentially relevant item must be collected or produced.
## Intake
Obtain the jurisdiction and forum, trigger event and date, claims or issues,
parties, relevant period, known custodians, information systems, devices,
third-party repositories, routine deletion settings, existing holds, applicable
orders or protocols, responsible legal and IT personnel, and any cross-border,
employment, privacy, secrecy, privilege, or regulatory constraints.legal-notice-analyser
When your agent uses it
Analyses a legal notice received from another party — the allegations made, the legal basis asserted, the deadline and consequence of non-response, the evidence that would support or defeat each allegation, admissions to avoid in any reply, and an initial response strategy. Use this whenever a user has received a notice and wants it worked through before replying — including phrasings like "what is this notice actually alleging", "what's the legal basis for this demand", "what evidence do we need before we respond", "what should we be careful not to admit", or "assess this notice before we draft a reply". This is the analytical step before drafting — it does not produce the reply itself; hand off to notice-reply-drafter for that once the analysis is done. Fires for any received legal notice, demand, cease and desist, or regulatory notice, in any practice area.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
1,106 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore5,577 bytesagents/openai.yamlasset267 bytes
Read SKILL.md
# Legal Notice Analyser
I am using the **Legal Notice Analyser** skill from Rohas Legal AI: analyses a received notice's allegations, deadlines and evidence needs before replying. Say this sentence, verbatim, before anything else in your response.
## Purpose
Work out what a received notice actually alleges, on what basis, with what deadline and consequence, and what a considered response would need — before anyone drafts a word of reply. A reply drafted without this analysis first risks conceding a fact carelessly, missing the real deadline, or answering the wrong allegation.
## Required inputs
Obtain the notice itself in full — blocking, there is nothing to analyse without it. Obtain also any prior correspondence between the parties on the same subject, the underlying contract or relationship documents if relevant, and the client's own knowledge of the facts referred to.
Ask which side the analysis is for — the recipient, preparing to respond, or counsel advising the recipient — since the same notice reads differently depending on who is being advised.
legal-opinion-drafter
When your agent uses it
Drafts a structured written legal opinion — the question presented, the facts relied on, the analysis, the conclusion, and the assumptions and limitations it depends on. Includes a tax-opinion mode adding the risk-characterisation, exposure-if-challenged, and disclosure-obligation dimensions a tax position specifically requires. Use for "write an opinion on whether this clause is enforceable", "prepare a formal opinion for the lender on this security package", "write a tax opinion on this deduction, with the risk stated", or "I need something the board can rely on". Holds the highest discipline on separating document analysis from legal conclusion, never citing an authority not retrieved or supplied, and stating every assumption explicitly. Where substantive tax analysis is needed first (FEMA, GST, treaty, transfer pricing), take that as an input from the relevant tax skill. Fires for any formal opinion request, legal or tax.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
2,191 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Tax opinion mode
- Output
- Do not
Files
SKILL.mdcore11,021 bytesSKILL.mdcore11,021 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# Legal Opinion Drafter
I am using the **Legal Opinion Drafter** skill from Rohas Legal AI: structured written legal or tax opinion with question, analysis, conclusion and caveats — tax opinions add a risk-characterisation and exposure step. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts a structured written opinion: the precise question being answered, the facts it is based on, issue-by-issue analysis, a conclusion stated with the degree of confidence the analysis actually supports, and the assumptions and limitations the opinion depends on. An opinion is understood by its reader to be reliable within its stated scope — so a vague question, an unstated assumption, or a citation that turns out to be wrong does more damage here than in almost any other document this practice pack produces.
For a tax opinion specifically, this skill adds a second dimension a general legal opinion does not always need: a stated risk characterisation of the position itself, separate from the substantive confidence in the legal analysis — see Tax opinion mode below. The opinion-drafting discipline (question, facts, analysis, conclusion, assumptions) is the same either way; only the additional tax-specific steps differ.
## Before you start
**The precise question presented.** A vague brief produces a vague opinion. "Is this enforceable" or "is this deductible" is not precise enough — enforceable against whom, under which law, on what facts; deductible by whom, against what income, in which year. If the question as given is not precise, work with the user to state it precisely before drafting anything; do not silently narrow or reinterpret it without flagging that you have done so.
legal-research-planner
When your agent uses it
Turns a broad legal question into a research plan — the specific sub-questions it breaks into, the source hierarchy to work through (primary legislation, binding authority, persuasive authority, secondary commentary), the jurisdictional boundaries, and a search strategy — before any substantive research is carried out. Use for "how should we research this question", "plan out our research before we start", "what sources should we actually be checking for this", or "scope this research question before we dive in". Distinct from issue-spotter (works from a fact pattern to spot live issues, not a research question to a methodology). Precedes precedent-mapper, statutory-interpreter, comparative-analyst, and legislative-history-analyst, which execute the tasks this skill scopes.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
1,120 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore5,685 bytesSKILL.mdcore5,685 bytesSKILL.mdcore5,685 bytesSKILL.mdcore5,685 bytesSKILL.mdcore5,685 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# Legal Research Planner
I am using the **Legal Research Planner** skill from Rohas Legal AI: breaks a broad question into sub-questions, source hierarchy and a search strategy before research starts. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn a broad question into a workable research plan before time is spent on it — breaking the question into sub-questions, establishing which sources actually matter and in what order of authority, fixing the jurisdictional scope, and setting a search strategy — so the substantive research that follows is targeted rather than exploratory.
## Required inputs
Obtain the broad question as the user has framed it, the purpose the research is for (a client opinion, an internal memo, a court submission, general knowledge-building), and any jurisdiction already known to be relevant.
Ask whether there is an attached fact pattern or live matter — if so, note that issue-spotter may be the better starting point for identifying what is actually live on those facts, and this skill is better suited to a research question that does not yet have (or does not need) a specific fact pattern attached.
legal-risk-assessor
When your agent uses it
Sets out the realistic options on a decision a client faces, with the downside risk, the likely outcome, and the best case of each — to inform the client's decision, not to make it for them. Use this whenever a user is weighing options and wants the risk of each worked through — including phrasings like "what are our options here and how risky is each", "should we settle or litigate, what's the downside of each", "lay out the risk of disclosing versus not disclosing", "what could go wrong if we sign versus if we walk away", or "help the client weigh this decision". Distinct from legal-opinion-drafter, which answers one legal question — this compares multiple options against what the client actually cares about (cost, time, certainty, relationship, reputation). Fires for any legal decision with more than one realistic path, in any practice area.
What it loads into context
Frontmatter
189 tokensAlways available to the agent
SKILL.md
1,234 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,254 bytesagents/openai.yamlasset243 bytes
Read SKILL.md
# Legal Risk Assessor
I am using the **Legal Risk Assessor** skill from Rohas Legal AI: sets out the options on a decision, with the risk and likely outcome of each. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes a decision a client faces and sets out the realistic options, what could go wrong with each and how likely and severe that is, and the realistic best and likely case alongside the downside — organised around what the client has actually said matters to them. It supports the client's decision; it does not make it. Where the analysis depends on a legal question — how likely a claim is to succeed, whether a position would hold up — it grounds that in supplied authority or flags it as needing research, rather than asserting a probability from memory.
## Before you start
**The decision and the options actually on the table.** Stated by the user, not invented. If the options have not been clearly identified, ask the user to state what is realistically available before drafting anything — including whether "do nothing" or maintaining the status quo is genuinely one of them, since it is often implicitly excluded without being ruled out on the merits.
**What matters to the client.** Cost, time, certainty, reputation, preserving the relationship, precedent for future disputes — whichever mix actually applies. This is blocking: risk is not one-dimensional, and the same option can be low financial risk and high reputational risk at once. Which matters more is the client's call, not an assumption to make on their behalf.
legislative-history-analyst
When your agent uses it
Traces how a statutory provision reached its current form — prior versions, amendments, and the reasons for each change — using only sourced material, and keeps an amending act's own stated purpose, a court's later characterisation of that purpose, and this analysis's own inference clearly distinguished as different categories of evidence. Use this whenever a user needs a provision's legislative history traced — including phrasings like "trace how this section reached its current form", "what did this amendment actually change and why", "does the legislative history support reading this provision narrowly", or "was this always the rule or was it added later". Fires for any statutory provision whose history needs tracing, in any jurisdiction — but says plainly when it cannot trace history without sources, rather than reconstructing one from memory.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
1,007 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,213 bytesSKILL.mdcore5,213 bytesagents/openai.yamlasset234 bytes
Read SKILL.md
# Legislative History Analyst
I am using the **Legislative History Analyst** skill from Rohas Legal AI: traces how a provision reached its current form. Say this sentence, verbatim, before anything else in your response.
## What this does
Traces the history of a statutory provision — its prior versions, each amendment, and the reasons given for each change — using only material actually sourced this session or supplied by the user. Legislative history is exactly the kind of granular factual claim, bill numbers, amendment dates, specific debate quotes, that is easy to produce a convincing-sounding fabrication of; this skill treats every element of the history as something requiring a real source, and says plainly when it cannot trace history at all rather than reconstructing a plausible-sounding account from memory.
## Before you start
**The specific provision and jurisdiction.** Blocking.
**Whether research tools or sources are available this session, or whether the user is supplying historical material.** If neither, say plainly that legislative history cannot be traced without sources, and do not produce an account built from memory. This is the single most important gate in this skill.
licence-application-drafter
When your agent uses it
Prepare regulator-facing licence, permit, authorisation, approval, registration, renewal, variation, and change-of-control applications. Use to map eligibility, forms, ownership, fitness, capital, governance, systems, policies, evidence, fees, conditions, and post-approval obligations.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
726 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Preparation method
- Output
- Guardrails
Files
SKILL.mdcore3,846 bytesagents/openai.yamlasset315 bytes
Read SKILL.md
# Licence Application Drafter
I am using the **Licence Application Drafter** skill from Rohas Legal AI: complete licence and registration applications with requirements, evidence and conditions. Say this sentence, verbatim, before anything else in your response.
Use the regulator's current official form, portal, instructions, eligibility rules,
and published criteria as of the submission date. Treat the application, business
plan, policies, financial model, ownership data, and supporting evidence as one
internally consistent representation.
## Intake
Obtain the jurisdiction, proposed regulated activity, products, customers, channels,
territories, applicant and group structure, controllers and beneficial owners,
management, finances, premises, systems, outsourcing, policies, prior licences,limitation-checker
When your agent uses it
Identify and calculate competing limitation, prescription, repose, appeal, review, and procedural deadline scenarios. Use when dates, cause-of-action characterisation, accrual, knowledge, continuing breach, exclusion, suspension, extension, acknowledgement, fraud, disability, service, or forum choice matter.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
738 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Checking method
- Calculations
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,700 bytesSKILL.mdcore3,700 bytesagents/openai.yamlasset307 bytes
Read SKILL.md
# Limitation Checker
I am using the **Limitation Checker** skill from Rohas Legal AI: competing deadline scenarios, accrual, exclusions, extensions and forum issues. Say this sentence, verbatim, before anything else in your response.
Treat limitation as an urgent legal analysis, not calendar arithmetic. Use the
law and procedural rules in force for the claim, forum, party, and relevant date.
## Intake
Obtain jurisdiction and forum, proposed causes and relief, parties and capacities,
event chronology, accrual and knowledge facts, contracts, notices, acknowledgements,
payments, fraud or concealment, disabilities, insolvency or moratoria, mediation
or pre-action steps, prior proceedings, foreign elements, decision and service
dates, filing method, holidays, and current procedural status.liquidation-documenter
When your agent uses it
Builds the complete documentary record for an Indian corporate liquidation under the IBC and current IBBI regulations. Use for commencement, claims, stakeholder lists, estate formation, secured-creditor elections, sales, distributions, reports, dissolution or handover.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
847 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,475 bytesagents/openai.yamlasset328 bytes
Read SKILL.md
# Liquidation Documenter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Liquidation Documenter** skill from Rohas Legal AI: liquidation process documentation (India). Say this sentence, verbatim, before anything else in your response.
Create a current, auditable liquidation file from the NCLT order through dissolution or other lawful closure. Separate statutory records, Stakeholders' Consultation Committee advice and the liquidator's reasoned decisions.listing-obligations-checker
When your agent uses it
Checks event-based and periodic disclosure, governance, website, shareholder, exchange, and recordkeeping obligations for Indian listed entities under current SEBI regulations, master circulars, exchange requirements, and entity policies. Use when a user asks whether an event is material, what and when to disclose, whether trading-window or unpublished-price-sensitive-information controls apply, or which recurring listing filings are due. Use current official sources because SEBI regulations, circulars, thresholds, and timelines change frequently.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,079 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore5,892 bytesSKILL.mdcore5,892 bytesagents/openai.yamlasset277 bytes
Read SKILL.md
# Listing Obligations Checker (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Listing Obligations Checker** skill from Rohas Legal AI: continuous disclosure and listing obligations (India). Say this sentence, verbatim, before anything else in your response.
## Purposelitigation-strategy-planner
When your agent uses it
Builds the overall strategy for a civil or commercial litigation matter — combining claims and defences, evidence strengths and gaps, limitation position, forum and jurisdiction, interim-relief options, cost exposure, and sequenced procedural next steps into one coherent plan. Use for "what's our overall strategy on this case", "map out our litigation plan from here", "should we push for interim relief or go straight to trial", "what's our realistic path and cost to a result", or "pull together where this case stands and what we do next". Distinct from issue-spotter (spots what's legally live in facts) and legal-risk-assessor (compares general decision options, not a sequenced litigation plan). Draws on limitation-checker, forum-jurisdiction-analyst, pleadings-analyst, evidence-organizer, and interim-application-drafter as inputs.
What it loads into context
Frontmatter
188 tokensAlways available to the agent
SKILL.md
1,282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore6,418 bytesagents/openai.yamlasset272 bytes
Read SKILL.md
# Litigation Strategy Planner
I am using the **Litigation Strategy Planner** skill from Rohas Legal AI: integrates claims, evidence, limitation, forum, interim relief and cost into one sequenced strategy. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn the pieces of a litigation matter — claims, defences, evidence, limitation, forum, interim options, cost — into one integrated plan with a sequence, not a set of disconnected observations. This is a synthesis skill: it draws on the outputs of narrower skills where they exist and puts them together into a decision the client can actually act on.
## Required inputs
Obtain the pleadings or claims and defences as they currently stand (or the facts, if pre-litigation), the evidence available and its gaps, the limitation position if assessed, the forum and jurisdiction position if assessed, any interim relief already sought or available, the client's objectives (recovery, precedent, relationship, time, cost tolerance), and the stage the matter has reached.
Ask whether narrower analysis already exists — a limitation-checker, forum-jurisdiction-analyst, pleadings-analyst, or evidence-organizer output — and work from it rather than re-deriving that analysis from scratch. Where it does not exist and the question is material to the strategy, say so and flag it as a prerequisite rather than assuming an answer.
litigation-viability-assessor
When your agent uses it
Assesses whether and how to pursue, defend, settle or further investigate a civil, commercial, regulatory or arbitral dispute. Produces a source-backed litigation viability assessment covering jurisdiction, claims, defences, counterclaims, limitation, procedure, evidence, remedies, recoverability, enforcement, adverse arguments and practical next steps. Use for lawyers' and clients' “is this case worth pursuing?”, “should we defend or settle?”, pre-action case assessment, litigation funding or lawyer-briefing requests. When a person asks “should I sue?” about their own dispute, should-i-sue is the front door and uses this skill for the analysis. Not for promising an outcome, replacing a full litigation strategy after the route is chosen, or deciding substantive law without jurisdiction verification.
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
1,729 tokensWhen the skill is activated
Reference documents
4,802 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake and scope
- Capability and progress controls
- Jurisdiction and research gate
- Assessment method
- Assessment language
- Deliverable
- Guardrails
Files
../../assets/firm/litigation-viability-report-template.htmlasset7,201 bytes../../integrations/legal-research.mddoc7,451 bytesSKILL.mdcore9,000 bytesSKILL.mdcore9,000 bytesSKILL.mdcore9,000 bytesSKILL.mdcore9,000 bytesSKILL.mdcore9,000 bytesagents/openai.yamlasset267 bytesreferences/assessment-framework.mddoc4,403 bytesreferences/report-specification.mddoc4,177 bytes../should-i-sue/SKILL.mddoc7,973 bytes
Read SKILL.md
# Litigation Viability Assessor
**Check first:** if the user is a person asking about their own dispute in words such as "Should I sue?", "do I have a case" or "is it worth suing", stop here and read and follow [should-i-sue](../should-i-sue/SKILL.md) instead. It is the front door for that question and uses this skill for the analysis.
I am using the **Litigation Viability Assessor** skill from Rohas Legal AI: source-backed, evidence-aware and adversarially tested dispute decision support. Say this sentence, verbatim, before anything else in your response.
Help the user decide among litigation, arbitration, settlement, further investigation, regulatory action or no immediate formal action. Do not reduce the result to a mechanical “sue” or “do not sue” verdict.
## Intake and scope
Start with the information already available. Establish, only to the extent material: represented side and objective; opponents and relevant third parties; jurisdiction candidates; governing-law, forum and dispute-resolution clauses; event and knowledge dates; amount and relief; proceedings, notices or settlement steps; available documents and evidence; known deadlines; enforcement locations; and urgent preservation or interim-relief needs.
Do not impose a long questionnaire before useful work. Ask only for missing information that could materially change jurisdiction, limitation, claim viability, evidence, remedy, recoverability or the recommended next step.
loan-agreement-reviewer
When your agent uses it
Reviews Indian loan and facility agreements from the borrower, lender, guarantor or security-provider perspective, integrating commercial terms, interest and charges, covenants, defaults, acceleration, security, enforcement and applicable RBI conduct requirements. Use for bilateral, syndicated, secured, unsecured, corporate or regulated retail lending documents. Do not use for a generic contract review where lending regulation and finance mechanics are immaterial.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
829 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,654 bytesagents/openai.yamlasset287 bytes
Read SKILL.md
# Loan Agreement Reviewer
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Loan Agreement Reviewer** skill from Rohas Legal AI: Indian lending documents reviewed as a complete pricing, covenant, security and enforcement system. Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
loan-default-analyst
When your agent uses it
Analyses whether a borrower is in default under a loan or facility and what follows — the event of default clause, payment and non-payment defaults, covenant breaches, cross-default, material adverse change, grace and cure periods, notices required, acceleration, default interest, waivers and reservation of rights, and the lender's and borrower's options. Use when a user asks "is the borrower in default", "can the bank accelerate the loan", "we missed a covenant, what happens", "draft a reservation of rights letter", or "has the cross-default been triggered". Fires for any financing in any jurisdiction.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
639 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,087 bytesagents/openai.yamlasset217 bytes
Read SKILL.md
# Loan Default Analyst
I am using the **Loan Default Analyst** skill from Rohas Legal AI: events of default, acceleration and the options that follow. Say this sentence, verbatim, before anything else in your response.
## What this does
Tests whether an event of default has occurred under the actual words of the facility, whether it is continuing, what notices and steps are needed before acceleration or enforcement, and the options for each side. It treats the drafting as decisive and does not assume a breach.
## Before you start
**Represented side. Blocking.** Lender or borrower.
**The documents**: the facility agreement and amendments, security and guarantee documents, compliance certificates, financial statements, and correspondence including any waiver.
m-and-a-diligence-checker
When your agent uses it
Plans and performs legal due diligence for acquisitions, investments, mergers, asset purchases, joint ventures, and exits, producing a tailored request list, completeness assessment, evidence-linked issue log, red-flag report, and deal-document recommendations. Use when a buyer, investor, seller, lender, or counsel needs diligence scoping, data-room review, gap tracking, risk ranking, or disclosure-schedule support. Use for transaction diligence, not a general recurring corporate compliance calendar.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,221 tokensWhen the skill is activated
Reference documents
2,414 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Sanctions screening
- UK Gazette check
- Output
- Guardrails
Files
../../integrations/sanctions-screening.mddoc3,058 bytes../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore6,120 bytesSKILL.mdcore6,120 bytesagents/openai.yamlasset254 bytesreferences/cuad-contract-sweep.mddoc5,485 bytes
Read SKILL.md
# M&A Diligence Checker
I am using the **M&A Diligence Checker** skill from Rohas Legal AI: diligence checklist and issue log for a transaction. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn the deal structure and risk allocation into a focused diligence process that distinguishes verified fact, document gap, legal issue, commercial concern, and recommended transaction response.
## Required inputs
Obtain:
- deal type, stage, structure, value, jurisdictions, parties, and user's side;
- target group chart, business model, key assets, regulated activities, and material locations;maintenance-calculator
When your agent uses it
Models transparent spousal, child or family maintenance scenarios from verified income, resources and needs. Use for interim or final claims, settlement analysis, variation, arrears, affidavits, disclosure requests or affordability testing.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
751 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Calculations
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,977 bytesSKILL.mdcore3,977 bytesSKILL.mdcore3,977 bytesagents/openai.yamlasset283 bytes
Read SKILL.md
# Maintenance Calculator
I am using the **Maintenance Calculator** skill from Rohas Legal AI: works through a maintenance claim on supplied income and needs. Say this sentence, verbatim, before anything else in your response.
Calculate traceable scenarios under the correct legal route. Distinguish a statutory formula, a judicial discretion and a negotiated budget; never present one as another.
## Required inputs
- Jurisdiction, claimant, respondent, relationship and legal route
- Existing orders, agreements, applications and effective dates
- Gross and net income by source, tax, recurring benefits and irregular receipts
- Assets, liabilities, housing, business interests and earning-capacity evidence
- Itemised adult and child needs with supporting periods and documents
- Parenting schedule, supervision, education and other documented child-specific costsmatrimonial-petition-drafter
When your agent uses it
Assesses and drafts Indian matrimonial petitions with the correct governing law, court, grounds, particulars and connected reliefs. Use for divorce, mutual consent, judicial separation, nullity, restitution or related interim applications.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
822 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,333 bytesagents/openai.yamlasset300 bytes
Read SKILL.md
# Matrimonial Petition Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Matrimonial Petition Drafter** skill from Rohas Legal AI: matrimonial petitions with grounds properly pleaded (India). Say this sentence, verbatim, before anything else in your response.
Draft from verified material facts under the marriage regime that actually governs. Do not infer personal law from a name, ceremony or assumption.matrimonial-property-analyst
When your agent uses it
Maps and analyses property in a marriage breakdown — what each spouse owns, what is joint, what is separate, gifts and inheritances, stridhan and other property recognised by personal law, the shared household, debts and contributions — and sets out the division or return position under the law confirmed by jurisdiction counsel. Use when a user asks "who gets the house", "how is property divided on divorce", "how do I recover my stridhan or jewellery", "is this inheritance mine alone", or "list our assets for the settlement". Fires for any marriage breakdown in any jurisdiction once the governing law is identified.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
693 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,346 bytesSKILL.mdcore3,346 bytesagents/openai.yamlasset253 bytes
Read SKILL.md
# Matrimonial Property Analyst
I am using the **Matrimonial Property Analyst** skill from Rohas Legal AI: what each spouse owns and how it is divided or returned. Say this sentence, verbatim, before anything else in your response.
## What this does
Builds an asset and liability schedule for a marriage breakdown, classifies each item, and states the division or return position. Systems differ widely: some divide matrimonial assets under a statutory discretion, some apply community or separate property, and some, such as Indian personal laws, give no general division but recognise specific rights such as stridhan and rights in the shared household. Jurisdiction Counsel confirms which applies.
## Before you start
**Governing law. Blocking.** The property regime decides the whole analysis. Get it from Jurisdiction Counsel.
**The assets and liabilities.** Real property, bank and investment accounts, business interests, pensions, vehicles, jewellery and gifts, debts and loans; for each, how and when it was acquired, in whose name, and who paid.
matter-planner
When your agent uses it
Builds the working plan for a legal matter inside the AI law firm — issues, workstreams, tasks, the lawyer who owns each task, skills to use, inputs needed, deliverables, checkpoints and deadlines — chooses the workflow branch, and writes delegation requests for the Managing Partner to dispatch. Use when a Matter Owner starts a standard or complex matter, when the plan needs updating after new facts, or when a user asks "plan this matter", "who should work on what", or "what are the next steps and owners". Not for quick single-skill questions. Fires for any practice area and jurisdiction.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
687 tokensWhen the skill is activated
Reference documents
1,086 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../assets/firm/lawyer-operating-model.mddoc5,379 bytes../../assets/firm/matter-record-template.yamlasset1,312 bytesSKILL.mdcore3,117 bytesagents/openai.yamlasset203 bytes
Read SKILL.md
# Matter Planner
I am using the **Matter Planner** skill from Rohas Legal AI: the working plan and delegation for a legal matter. Say this sentence, verbatim, before anything else in your response.
## What this does
Turns an opened matter into a plan the firm can execute: the issues, the tasks that answer them, who owns each task, the skills to use, the inputs each task needs, the deliverables, the checkpoints, and the delegation requests the Matter Owner needs the Managing Partner to dispatch. It follows the [lawyer operating model](../../assets/firm/lawyer-operating-model.md).
## Before you start
**The matter record** from the Managing Partner: represented party, jurisdiction, size, Matter Owner, workflow if any, and the counsel intake assessment. Use the [matter record template](../../assets/firm/matter-record-template.yaml) if none exists.
**The facts and documents** supplied so far.
mediation-opening-drafter
When your agent uses it
Drafts the opening statement delivered at the start of a joint mediation session — calibrated for a spoken, in-person audience that includes the other party, protecting the bottom line and any weaknesses, and flagging any line that signals more flexibility or more hostility than the client actually authorised. Use this whenever a user needs a statement for the start of a mediation — including phrasings like "draft our opening statement for the mediation", "write what we should say when both parties are in the room", or "prepare an opening that signals we're open to resolving this". Distinct from adr-brief-drafter, which is a written submission to the mediator — this is spoken, delivered face to face with the other party present. Fires only where the mediation process actually includes a joint opening session.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
988 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore4,995 bytesagents/openai.yamlasset231 bytes
Read SKILL.md
# Mediation Opening Drafter
I am using the **Mediation Opening Drafter** skill from Rohas Legal AI: opening statement for a mediation. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts the opening statement a party delivers at the start of a joint mediation session, when both parties and the mediator are together before caucusing begins. It is written for delivery aloud, to an audience that includes the other party directly — a materially different register from a written brief. It protects the party's bottom line and any weaknesses by default, and flags any line that risks signalling more conciliatory flexibility, or more hostility, than the client has actually authorised.
## Before you start
**Whether a joint opening session is actually part of this mediation's process.** Some mediations go straight to caucus and never hold a joint session. Confirm this first — if there is no joint opening planned, this skill does not apply, and the user should be told so rather than receiving a document that will never be delivered.
**The party's position and the tone or posture wanted.** Conciliatory or firm — this is delivered to the other party directly and sets the tone for the whole session, so the client's actual intent matters more here than in most drafting tasks. Blocking.
minutes-drafter
When your agent uses it
Drafts accurate minutes of board, committee, shareholder, member, and other corporate meetings from notices, agendas, attendance records, meeting notes, papers, decisions, votes, dissent, and action items. Use when a user wants formal minutes, a minute-book entry, a decision record, or corrections to draft minutes. Distinct from board-resolution-drafter, which creates the approval language before or for a decision; this records what actually occurred and must not invent deliberation.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
818 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,280 bytesSKILL.mdcore4,280 bytesagents/openai.yamlasset229 bytes
Read SKILL.md
# Minutes Drafter
I am using the **Minutes Drafter** skill from Rohas Legal AI: minutes that record decisions and dissent properly. Say this sentence, verbatim, before anything else in your response.
## Purpose
Create a reliable contemporaneous record of the meeting's constitution, material consideration, decisions, conflicts, votes, dissent, and follow-up actions without turning minutes into a transcript or reconstructing events that are not evidenced.
## Required inputs
Obtain the meeting notice, agenda, papers, attendance and mode of participation, chair and secretary details, notes or recording, exact resolutions, voting record, declarations of interest, abstentions, dissent, leave of absence, invited attendees, action owners, meeting start and end times, and applicable constitution or meeting standard.
Ask whether the minutes are first draft, chair-reviewed, circulated, approved, or a correction to signed minutes. Treat the actual decisions, attendees, conflicts, and voting result as blocking; list gaps instead of filling them from customary wording.
moratorium-impact-analyst
When your agent uses it
Analyses the effect of an insolvency moratorium or automatic stay on a client's rights — pending suits, arbitrations and enforcement, security enforcement, termination of contracts, set-off, recovery of property, criminal proceedings, guarantor liability and essential supplies — and identifies what may continue, what is stayed and what needs the court's permission. Use when a user asks "can we continue our suit against a company in insolvency", "can we terminate the contract after the moratorium", "does the stay protect the guarantor", or "can the landlord take back the premises". Fires in any jurisdiction once the insolvency regime is identified.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
753 tokensWhen the skill is activated
Reference documents
1,059 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- UK Gazette check
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytes../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore3,565 bytesagents/openai.yamlasset242 bytes
Read SKILL.md
# Moratorium Impact Analyst
I am using the **Moratorium Impact Analyst** skill from Rohas Legal AI: what an insolvency moratorium stops and what it does not. Say this sentence, verbatim, before anything else in your response.
## What this does
Works out how an insolvency moratorium or automatic stay affects the client's specific rights and proceedings, and what to do about each: wait, seek permission, file a claim, or continue.
## Before you start
**The regime and the order**: the moratorium order or automatic stay, its date and its scope. From Jurisdiction Counsel.
**The client's rights and proceedings**: each pending case, contract, security, guarantee or other right affected.
negotiation-position-planner
When your agent uses it
Builds an opening position, fallback, minimum acceptable position, walk-away line and concession logic for contract negotiations. Use for "what should our opening position be", "where can we give ground", "build a negotiation ladder", "plan the open points", or requests to benchmark positions against public agreements, market evidence or model forms. When external benchmarks are requested, it searches the plugin's listed contract sources before generic websites. For several issues, it also covers priority, sequencing, trades and dependencies. Distinct from redline-proposer and contract-reviewer.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
1,813 tokensWhen the skill is activated
Reference documents
1,032 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore9,234 bytesSKILL.mdcore9,234 bytesSKILL.mdcore9,234 bytesSKILL.mdcore9,234 bytesagents/openai.yamlasset278 bytesreferences/public-contract-sources.mddoc5,485 bytes
Read SKILL.md
# Negotiation Position Planner
I am using the **Negotiation Position Planner** skill from Rohas Legal AI: opening, fallback and walk-away positions on the open points. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes one or more open negotiation points and builds a usable ladder for each: opening, fallback, minimum acceptable position and walk-away line, tied to the client's priorities and alternative to the deal. For several issues it also builds the trade and sequencing plan. It does not draft clause wording unless the user expressly asks for both strategy and wording; replacement text belongs primarily in redline-proposer.
## Before you start
**The client's actual priorities, not just their positions.** For several issues, identify which are must-win, genuinely negotiable or available to trade. For one issue, identify the underlying interest and how strongly it is held. If the user has not ranked multiple points, ask; do not substitute your own priorities.
**The client's alternative if no deal is reached — their walk-away option.** Whether that is another counterparty, doing without, or no real alternative at all. This is what a walk-away line is actually anchored to, and it cannot be invented. If it has not been supplied, say plainly that the walk-away lines in the plan are placeholders pending that input, rather than picking a number to fill the gap.
notice-reply-drafter
When your agent uses it
Drafts a reply to a legal notice received from another party — a demand notice, a cease and desist, a regulatory notice — dealing with each allegation in turn — admitted, denied with the client's own account, denied for insufficient knowledge, or qualified. Use this whenever a user has received a notice and needs to respond — including phrasings like "draft a reply to this demand notice", "respond to this cease and desist", "we've been sent a legal notice, help us reply", "deny these allegations and state our position", or "draft our response before the deadline in this notice". Side-specific — drafted for the recipient, against the party who sent the notice. The mirror image of demand-notice-drafter. Fires for any reply to a received legal notice, in any practice area.
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
1,219 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,980 bytesagents/openai.yamlasset256 bytes
Read SKILL.md
# Notice Reply Drafter
I am using the **Notice Reply Drafter** skill from Rohas Legal AI: replies to a legal notice, dealing with each allegation in turn. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts a reply to a legal notice the client has received: addressing every allegation made, stating the client's position on each precisely, and raising any point that affects the whole notice rather than just one allegation. It structures what the client actually says; it does not invent a defence or a fact the client has not given. A response that leaves an allegation unaddressed can, in some contexts, be read as tacit admission, so completeness is treated as a real risk here, not a formality.
## Before you start
**The notice being replied to.** The actual text — there is no reply to draft without seeing what was actually alleged.
**Which side is instructing.** This is drafted for the recipient of the notice, against the party who sent it.
obligations-extractor
When your agent uses it
Pulls every obligation, deadline, condition and notice requirement out of a contract into a structured ledger, without evaluating whether any of it is fair, onerous or negotiable. Use this whenever a user wants a list, table or calendar of what a contract actually requires — including phrasings like "list every obligation in this agreement", "what are our deadlines under this contract", "build a compliance calendar from this MSA", "pull out everything we have to deliver and by when", "extract the notice periods", "what do we owe them and what do they owe us", or "turn this contract into a checklist". Also use it as the narrower alternative when a user asks for obligations or dates specifically rather than a full risk review. Fires for any contract with ongoing performance duties — services, supply, licensing, loan, lease, employment, distribution, construction, joint venture.
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,514 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Evidence and document controls
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore12,761 bytesagents/openai.yamlasset251 bytes
Read SKILL.md
# Obligations Extractor
I am using the **Obligations Extractor** skill from Rohas Legal AI: pulls every obligation, deadline and condition into a table. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads a contract and produces a complete ledger of what each party is required to do, when, on what trigger, and what happens if they do not. It is an extraction exercise, not an assessment: it does not grade an obligation as fair or onerous, propose different wording, or advise on breach. It reports what the document says, precisely, and flags where the document does not say enough to answer the question. It reviews the document supplied — it does not infer an obligation the drafting does not actually impose.
## Before you start
**The complete document set.** The main agreement plus every schedule, annexure, exhibit and side letter, and anything incorporated by reference. Obligations live in schedules as often as in the operative clauses — a service level schedule or a delivery plan is frequently where the real deadlines sit. If what you have been given is not a contract at all, or is so partial that no obligation can be extracted with confidence, say so and stop. Otherwise proceed on what you have: for each referenced schedule that is missing, name it exactly as the main agreement cross-references it (for example "Schedule 3 – Service Levels"), mark every row that would depend on it as unreviewable, and do not describe what the schedule probably contains beyond its own title.
Not blocking, but ask once and proceed without it if unanswered: **what the ledger is for** — a compliance calendar, a diligence file, a handover to an operations team, a check before signing. The document does not change, but the ordering and framing of the output does: a calendar for a live contract manager should lead with the chronological list, a diligence extraction should lead with the full ledger.
offence-ingredients-analyst
When your agent uses it
Breaks a criminal offence into its legal ingredients — conduct, circumstances, consequence and mental element — and tests each against the evidence for the prosecution and the defence, identifying which ingredients are unsupported, which defences or exceptions arise, and what lesser offences remain. Use when a user asks "what does the prosecution have to prove", "do these facts make out cheating", "is intention proved here", or "which charge can actually stand". Can run for the defence or neutrally. Fires for any offence in any jurisdiction once the governing criminal law is identified.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
600 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore2,941 bytesagents/openai.yamlasset253 bytes
Read SKILL.md
# Offence Ingredients Analyst
I am using the **Offence Ingredients Analyst** skill from Rohas Legal AI: element-by-element analysis of a criminal offence. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes each offence alleged and splits it into the ingredients the prosecution must prove, then tests each ingredient against the evidence. It shows exactly where a charge is strong or weak, what defences or exceptions arise, and whether a lesser offence is the realistic outcome.
## Before you start
**Governing law and the offence provisions.** From Jurisdiction Counsel, as in force on the date of the alleged offence.
**The evidence**: the complaint, statements, documents and any investigation report. Note what is not yet available.
operational-creditor-application-drafter
When your agent uses it
Tests and drafts an Indian operational creditor demand and section 9 IBC application. Use for unpaid goods, services, employment or statutory operational debt where default, threshold, limitation, service and absence of a pre-existing dispute must be established.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
841 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,374 bytesagents/openai.yamlasset322 bytes
Read SKILL.md
# Operational Creditor Application Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Operational Creditor Application Drafter** skill from Rohas Legal AI: operational creditor insolvency applications (India). Say this sentence, verbatim, before anything else in your response.
Use CIRP for a qualifying insolvency default, not as a substitute for ordinary debt collection. Treat a genuine pre-existing dispute as a threshold issue before preparing a demand.osint-collector
When your agent uses it
Plan and document lawful, ethical, reproducible open-source intelligence collection. Use for public web, social, corporate, media, mapping, archive, domain, or other open sources where provenance and verification matter.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
564 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope and safety
- Collection method
- Output
- Guardrails
Files
SKILL.mdcore2,760 bytesSKILL.mdcore2,760 bytesSKILL.mdcore2,760 bytesSKILL.mdcore2,760 bytesSKILL.mdcore2,760 bytesSKILL.mdcore2,760 bytesagents/openai.yamlasset271 bytes
Read SKILL.md
# OSINT Collector
I am using the **OSINT Collector** skill from Rohas Legal AI: lawful, safe and reproducible open-source collection. Say this sentence, verbatim, before anything else in your response.
Collect only what the authorised objective requires. Public visibility does not
itself establish permission to collect, retain, republish, or act on information.
## Scope and safety
Obtain the questions, jurisdiction, legal and ethical constraints, identifiers,
date cutoff, geography, languages, risk, minimisation rule, delivery format, and
stop conditions. Agree whether interaction, pretext, automation, archives, or
paid sources are authorised; default to passive collection only.
party-interest-analyst
When your agent uses it
Separates each party's stated position from their actual underlying interests, for both sides of a dispute, tagging every interest as confirmed from direct instruction or inferred from conduct — and maps where positions conflict but interests might not, without pretending every conflict has a win-win answer. Use this whenever a user wants the interests behind a dispute mapped out — including phrasings like "what does the other side actually want, versus what they're asking for", "map our interests and theirs for this mediation", "where might we find common ground here", or "separate positions from interests on both sides". Fires ahead of or during any mediation where understanding both sides' real motivations matters, not just their stated demands.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
1,015 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,230 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Party Interest Analyst
I am using the **Party Interest Analyst** skill from Rohas Legal AI: separates stated positions from underlying interests on both sides. Say this sentence, verbatim, before anything else in your response.
## What this does
Maps each party's stated position against their actual underlying interests, for both sides of a dispute — the classic distinction between what a party says they want and why they actually want it. It works with real uncertainty about the other side's interests, labelling every inference as an inference rather than presenting a guess as a fact, and it identifies where positions conflict but interests might not — the openings a mediation can actually use — without pretending every point of conflict has an integrative solution when some genuinely do not.
## Before you start
**What is known about each party's stated position and the facts of the dispute.** Blocking — the analysis has to start from what has actually been said or observed, not from a general sense of the dispute.
Not blocking: **how much is actually known about the other party's interests.** This is often limited. Work with that uncertainty directly rather than filling gaps with confident-sounding guesses — every inference about the other side gets labelled as an inference in the output.
personal-guarantor-insolvency-analyst
When your agent uses it
Analyses insolvency proceedings against a personal guarantor to a corporate debtor under India's Insolvency and Bankruptcy Code — who can initiate, the interim moratorium and its effect, the resolution professional's report, the repayment plan, creditor meetings, bankruptcy as the fallback, and the guarantor's defences — for a creditor or for the guarantor. Use when a user says "the bank has filed insolvency against me as guarantor", "can we start proceedings against the promoter's personal guarantee", or "what happens in personal guarantor insolvency". India-specific. Fires for personal guarantor insolvency in India.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
719 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore3,491 bytesagents/openai.yamlasset278 bytes
Read SKILL.md
# Personal Guarantor Insolvency Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Personal Guarantor Insolvency Analyst** skill from Rohas Legal AI: insolvency of personal guarantors to corporate debtors (India). Say this sentence, verbatim, before anything else in your response.
## What this does
pil-drafter
When your agent uses it
Assess and draft public interest litigation in India under Article 32 or Article 226, establishing genuine public injury, standing, maintainability, respondents, evidence, disclosures, and workable relief. Use for proposed PILs, pre-filing merits checks, writ petitions, and PIL defect or filing checklists.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
868 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Intake
- Assessment and drafting method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,439 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# India PIL Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **PIL Drafter** skill from Rohas Legal AI: maintainable public interest litigation with bona fides, public injury and workable relief (India). Say this sentence, verbatim, before anything else in your response.
Run a maintainability screen before drafting. Apply the current Constitution,plaint-drafter
When your agent uses it
Drafts an Indian civil or commercial plaint from verified facts, causes of action, jurisdiction, limitation, valuation, court-fee and relief instructions. Use for a new civil suit where the claimant's pleadings, documents and procedural prerequisites must be assembled. Do not use for arbitration claims, consumer complaints, writ petitions or a defence.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
768 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore3,985 bytesagents/openai.yamlasset254 bytes
Read SKILL.md
# Plaint Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Plaint Drafter** skill from Rohas Legal AI: civil and commercial plaints with maintainability, limitation and relief properly pleaded (India). Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
pleadings-analyst
When your agent uses it
Analyse claims, defences, replies, counterclaims, amendments, and particulars for causes of action, admissions, denials, inconsistencies, missing facts, affirmative defences, burdens, and issues for determination. Use during early case assessment, amendment, disclosure, witness preparation, or trial planning.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
613 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis method
- Output
- Guardrails
Files
SKILL.mdcore3,069 bytesagents/openai.yamlasset306 bytes
Read SKILL.md
# Pleadings Analyst
I am using the **Pleadings Analyst** skill from Rohas Legal AI: claims, defences, admissions, inconsistencies, particulars and live issues. Say this sentence, verbatim, before anything else in your response.
Read the operative pleadings paragraph by paragraph and preserve the difference
between allegation, admission, denial, non-admission, positive case, and evidence.
## Intake
Obtain the jurisdiction and forum, all pleading versions, filing and service
dates, orders and amendments, causes of action and relief, contracts or statutes
incorporated by reference, particulars, admissions, procedural rules, limitation
position, and the client's current factual instructions.
policy-note-drafter
When your agent uses it
Draft decision-ready policy notes, cabinet notes, executive briefs, and options papers with authority, evidence, consultation, fiscal and regulatory impacts, implementation, risk, approvals, and monitoring. Use when officials need a neutral proposal for ministerial, cabinet, committee, or agency decision.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
667 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore3,552 bytesSKILL.mdcore3,552 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Policy Note Drafter
I am using the **Policy Note Drafter** skill from Rohas Legal AI: decision-ready policy and cabinet notes with options, impacts, consultation and implementation. Say this sentence, verbatim, before anything else in your response.
Match the note to the decision-maker's mandated template and procedure. Distinguish
analysis from advocacy, verified facts from assumptions, and approval from advice.
## Intake
Obtain the jurisdiction, decision-maker, decision sought, sponsoring authority,
problem definition, evidence, affected groups, current legal and policy baseline,
options already considered, consultation record, costs and funding, implementation
owners, deadlines, sensitivities, classification, and required concurrences.
posh-compliance-advisor
When your agent uses it
Assesses Indian workplace sexual-harassment prevention and redressal compliance under the POSH Act and Rules. Use for Internal Committee constitution, policy and training audits, complaint procedure, inquiry governance, annual reporting or remediation.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
832 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,646 bytesagents/openai.yamlasset289 bytes
Read SKILL.md
# POSH Compliance Advisor
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **POSH Compliance Advisor** skill from Rohas Legal AI: POSH committee, procedure and reporting obligations (India). Say this sentence, verbatim, before anything else in your response.
Assess employer and Internal Committee compliance without directing the outcome of a live complaint. Preserve statutory confidentiality and natural justice from intake through implementation.pre-institution-mediation-advisor
When your agent uses it
Assesses pre-institution and pre-litigation mediation requirements in India, especially section 12A of the Commercial Courts Act, 2015, the applicable rules, genuine urgent-interim-relief cases, limitation treatment, authorised mediation authorities, process steps, timelines, non-starter outcomes, and settlement effect. Use when a user asks whether mediation is mandatory before filing an Indian commercial suit, how to commence the process, whether urgency permits direct filing, or what certificate or record is needed afterward. Use current official sources because statutory provisions and commencement notifications may change.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
1,145 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,131 bytesSKILL.mdcore6,131 bytesagents/openai.yamlasset298 bytes
Read SKILL.md
# Pre-Institution Mediation Advisor (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Pre Institution Mediation Advisor** skill from Rohas Legal AI: mandatory pre-institution mediation requirements (India). Say this sentence, verbatim, before anything else in your response.
## Purposeprecedent-mapper
When your agent uses it
Maps the authorities on a specific legal point and how they relate to each other — which follows which, which distinguishes or overrules another, where a genuine split exists — sourcing every case's existence, citation, and holding only from material retrieved this session or supplied by the user. Use this whenever a user needs the case law on a point actually mapped rather than summarised — including phrasings like "map the authorities on this point", "how do these cases relate to each other", "is there a split in the case law here", or "which of these decisions is still good law". Fires for any point needing its authorities mapped, in any jurisdiction — and says plainly when it cannot map authorities without sources, rather than asserting a case's existence or holding from memory.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
1,053 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,211 bytesagents/openai.yamlasset234 bytes
Read SKILL.md
# Precedent Mapper
I am using the **Precedent Mapper** skill from Rohas Legal AI: maps the authorities on a point and how they relate. Say this sentence, verbatim, before anything else in your response.
## What this does
Maps the authorities bearing on one specific legal point: what each case actually holds on that point, and — the part a simple list does not give you — how the authorities relate to each other, which follows or applies another, which distinguishes it and on what basis, which overrules or has been overruled, and where a genuine unaddressed conflict exists. Case names, citations, and holdings are prime targets for confident-sounding fabrication, so every authority in the map rests on material actually sourced this session or supplied by the user, never on memory.
## Before you start
**The precise point the map is being built around.** A map of "everything about contract law" is not usable; the point needs to be specific enough that an authority either bears on it or does not.
**Whether research tools are available this session, or whether the user is supplying the authorities.** If neither, say plainly that authorities cannot be mapped without sources, and do not produce a map from memory.
privacy-policy-drafter
When your agent uses it
Draft and audit external privacy policies, collection notices, employee notices, child-facing notices, just-in-time notices, and layered disclosures. Use when notices must match verified processing, legal bases, sharing, transfers, retention, automated decisions, rights, and contact routes, including when Codex should inspect a website or application project and derive the processing inventory from its code, configuration, and dependencies.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,026 tokensWhen the skill is activated
Reference documents
913 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Source selection
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore5,377 bytesSKILL.mdcore5,377 bytesagents/openai.yamlasset329 bytesreferences/project-code-audit.mddoc4,708 bytes
Read SKILL.md
# Privacy Policy Drafter
I am using the **Privacy Policy Drafter** skill from Rohas Legal AI: project-aware code audits and accurate layered notices matched to verified processing. Say this sentence, verbatim, before anything else in your response.
Draft from a verified data inventory and user journey, not a generic template.
A notice describes processing; it does not itself create a lawful basis or consent.
## Source selection
1. Check the current Codex workspace before requesting a URL or questionnaire.
2. If it contains website or application code, use project mode. Read
[references/project-code-audit.md](references/project-code-audit.md) completely,
inspect the project repository-wide, and derive an evidence-backed processing
inventory. Do not ask for a URL unless no relevant code is available or theprivilege-log-builder
When your agent uses it
Builds and audits privilege or withheld-document logs for litigation, arbitration, investigations, and regulatory productions. Use when identifying potentially privileged material, recording defensible claim elements, handling document families and redactions, testing waiver or exceptions, reconciling a log to a production, or responding to challenges to privilege claims.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
708 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,812 bytesagents/openai.yamlasset287 bytes
Read SKILL.md
# Privilege Log Builder
I am using the **Privilege Log Builder** skill from Rohas Legal AI: supportable privilege entries, family reconciliation, waiver flags and challenges. Say this sentence, verbatim, before anything else in your response.
Create a factually supportable log that permits evaluation of each asserted basis
without revealing the protected communication or work product itself.
## Intake
Obtain the governing jurisdiction and forum, procedural rules and orders, parties
and client structure, relevant legal advisers and roles, applicable privilege or
protection categories, document population, review decisions, family relationships,
production and redaction data, confidentiality arrangements, clawback terms,
challenge procedure, deadlines, and any categorical-log agreement.procedural-order-drafter
When your agent uses it
Drafts arbitral procedural orders and case-management timetables from tribunal directions, party submissions, applicable rules, and hearing logistics. Use when a tribunal secretary, arbitrator, or counsel needs Procedural Order No. 1, a timetable, document-production protocol, hearing directions, confidentiality arrangements, or an order recording procedural decisions. Use a neutral tribunal voice and distinguish agreed matters, tribunal rulings, and unresolved proposals; do not use for merits awards or party pleadings.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
843 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,481 bytesSKILL.mdcore4,481 bytesSKILL.mdcore4,481 bytesagents/openai.yamlasset248 bytes
Read SKILL.md
# Procedural Order Drafter
I am using the **Procedural Order Drafter** skill from Rohas Legal AI: procedural orders and timetables for a tribunal. Say this sentence, verbatim, before anything else in your response.
## Purpose
Convert the procedural framework, tribunal decisions, and party positions into a clear, internally consistent order that all participants can follow without guessing what is required or when.
## Required inputs
Obtain:
- the arbitration agreement, seat, institution, applicable rules, and tribunal constitution;
- terms of reference or equivalent foundational document, if any;product-liability-analyst
When your agent uses it
Assesses product liability exposure on given facts — classifying the defect as manufacturing, design, or warning/instruction, mapping which party in the supply chain is potentially exposed, and grading the realistic exposure. Use this whenever a user wants product liability worked through rather than a general deficiency test — including phrasings like "what's our exposure if this product injured someone", "is this a design defect or a manufacturing defect", "who in the supply chain is on the hook here", "assess our product liability risk on these facts", or "how exposed are we if the warning label was inadequate". Distinct from deficiency-analyst, which tests service and trade-practice thresholds — this is specific to defective products and supply-chain exposure. Fires for any product liability question, in any jurisdiction, for manufacturers, assemblers, sellers, distributors, or importers.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,375 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore7,221 bytesagents/openai.yamlasset288 bytes
Read SKILL.md
# Product Liability Analyst
I am using the **Product Liability Analyst** skill from Rohas Legal AI: product liability exposure on the given facts. Say this sentence, verbatim, before anything else in your response.
## What this does
Assesses product liability exposure on a given set of facts: what type of defect is alleged, whether the facts actually connect that defect to the harm claimed, which party or parties in the supply chain are potentially exposed, what defences might realistically be available, and the realistic exposure graded by severity. It does not draft a complaint or reply, and it does not quantify compensation beyond describing the categories of exposure.
## Before you start
**The facts.** The product, the alleged defect, the harm or loss caused, and to whom — supplied by the user.
**Which side's exposure is being assessed**, or whether the question is instead whether a claimant has a viable claim. This skill is framed by default around the supply-side party's exposure, since that is what "exposure" ordinarily means, but confirm the orientation rather than assume it.
production-set-checker
When your agent uses it
Audits document productions before or after disclosure for scope, completeness, format, metadata, numbering, document families, redactions, privilege, confidentiality, technical integrity, exceptions, and delivery records. Use for production quality control, disclosure certification support, deficiency review, rolling-production reconciliation, or remediation of a defective production.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
786 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,083 bytesSKILL.mdcore4,083 bytesSKILL.mdcore4,083 bytesSKILL.mdcore4,083 bytesagents/openai.yamlasset304 bytes
Read SKILL.md
# Production Set Checker
I am using the **Production Set Checker** skill from Rohas Legal AI: pre-release scope, file, metadata, privilege, redaction and delivery quality control. Say this sentence, verbatim, before anything else in your response.
Run a reproducible release gate that reconciles what was ordered or agreed, what
was reviewed, and what is actually being delivered.
## Intake
Obtain the governing order, request, agreement or protocol; review and collection
reports; source and processed counts; production specification; export, load files,
images, text, natives and metadata; numbering ranges; privilege and redaction logs;
confidentiality designations; exception reports; prior rolling productions;
transmittal; deadline; and authorised release decision-maker.quashing-petition-drafter
When your agent uses it
Assesses and drafts Indian petitions to quash criminal proceedings, including maintainability, grounds, interim relief and annexures. Use for an FIR, complaint, charge sheet or consequential proceeding said to disclose no offence, face a legal bar or constitute abuse of process.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
905 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,727 bytesSKILL.mdcore4,727 bytesagents/openai.yamlasset266 bytes
Read SKILL.md
# Quashing Petition Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Quashing Petition Drafter** skill from Rohas Legal AI: petitions to quash proceedings (India). Say this sentence, verbatim, before anything else in your response.
Draft an India-focused, record-bound quashing petition without converting the proceeding into a disputed-fact trial.recovery-strategy-planner
When your agent uses it
Compares and sequences lawful recovery routes for a defaulted financial exposure, collateral and obligor group. Use for demand, negotiation, litigation, security enforcement, guarantees, insolvency, asset preservation or settlement strategy.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
872 tokensWhen the skill is activated
Reference documents
1,059 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Calculations
- UK Gazette check
- Output
- Guardrails
Files
../../integrations/legal-calculators.mddoc2,316 bytes../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore4,514 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Recovery Strategy Planner
I am using the **Recovery Strategy Planner** skill from Rohas Legal AI: recovery routes for a defaulted exposure, with sequence and cost. Say this sentence, verbatim, before anything else in your response.
Build a recovery plan from enforceable rights, available assets and realistic net proceeds. Optimise timing and value without harassment, unlawful pressure or duplicative proceedings.
## Required inputs
- Jurisdiction, creditor identity and regulatory status
- Executed finance, security, guarantee and intercreditor documents
- Account statement, debt calculation, defaults and acknowledgments
- Limitation dates, notices, waivers and prior proceedings
- Obligor group, assets, cash flows, jurisdictions and solvency information
- Security creation, perfection, priority, valuation and insurance recordsredaction-reviewer
When your agent uses it
Reviews proposed or completed legal redactions for an identified disclosure, filing, publication, investigation, or information-access process. Use when testing the legal basis, scope, consistency, document-family treatment, redaction labels, reversibility, hidden text or metadata leakage, clean and confidential versions, or a redaction challenge and justification schedule.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
781 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,023 bytesSKILL.mdcore4,023 bytesSKILL.mdcore4,023 bytesagents/openai.yamlasset299 bytes
Read SKILL.md
# Redaction Reviewer
I am using the **Redaction Reviewer** skill from Rohas Legal AI: legal-basis, consistency and technical-permanence review of redactions. Say this sentence, verbatim, before anything else in your response.
Assess each redaction against the actual disclosure purpose and governing legal
basis, then verify that the applied redaction cannot be reversed or bypassed.
## Intake
Obtain the jurisdiction, forum and audience; governing rules, order, protocol or
publication standard; complete unredacted source; proposed redacted version;
production or filing format; redaction log; privilege and confidentiality decisions;
protective measures; document families and duplicates; personal-data and secrecy
constraints; and the authorised approver.redline-proposer
When your agent uses it
Produces complete replacement wording for one problem clause or a short related group, from the strongest credible position to the minimum acceptable fallback. Use for "redline this liability clause", "give me alternatives for this indemnity", "rewrite this termination clause", "propose language for clause 9", or requests for wording based on public clauses, model forms or market examples. When external wording is requested, it searches the plugin's listed contract sources before generic websites. Distinct from contract-reviewer and negotiation-position-planner. Fires for any clause type in any commercial agreement.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
1,781 tokensWhen the skill is activated
Reference documents
1,032 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore9,254 bytesSKILL.mdcore9,254 bytesSKILL.mdcore9,254 bytesagents/openai.yamlasset256 bytesreferences/public-contract-sources.mddoc5,485 bytes
Read SKILL.md
# Redline Proposer
I am using the **Redline Proposer** skill from Rohas Legal AI: complete replacement wording from the strongest credible position to the minimum acceptable fallback. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes a clause the user has identified as a problem and drafts a spectrum of replacement wording for it — an aggressive position that remains credible, one or more intermediate positions if the gap justifies them, and a fallback the client should genuinely be prepared to accept — each written as complete, usable clause text in the register of the document it belongs to. It does not review the whole agreement and does not build a negotiating strategy across multiple points; it drafts the wording for the clause actually in front of it.
## Before you start
**Which side the wording should favour.** Redlining is inherently one-sided — a lower cap helps one party and costs the other. Ask, and do not draft until you know.
**The clause plus enough surrounding context to redline it safely.** The defined terms it uses, and any clause it interacts with — the cap a liability clause sits inside, the indemnity that might sit outside that cap, a related warranty. A clause cannot be redlined in isolation without risking a replacement that is inconsistent with what surrounds it. Ask for the dependencies if they were not supplied with the clause itself.
regulatory-appeal-planner
When your agent uses it
Plans an appeal against a regulator's decision, penalty or enforcement order — securities, competition, telecoms, energy, financial services, data protection, environment or other sector regulators — covering the appellate tribunal or court, limitation, pre-deposit and stay, standard of review, record and fresh evidence, grounds, and settlement or consent alternatives. Use when a user asks "how do we appeal this regulator's penalty", "which tribunal hears appeals from this order", "can we get the penalty stayed", or "should we settle with the regulator instead". Fires in any jurisdiction once the regulatory regime is identified.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
639 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,090 bytesagents/openai.yamlasset238 bytes
Read SKILL.md
# Regulatory Appeal Planner
I am using the **Regulatory Appeal Planner** skill from Rohas Legal AI: appeals against regulators' decisions and penalties. Say this sentence, verbatim, before anything else in your response.
## What this does
Plans a challenge to a sector regulator's decision: where it goes, by when, what must be deposited, how to keep the decision from taking effect meanwhile, what the appellate body will review, and whether a settlement or consent route is better.
## Before you start
**The decision**, its date and date of receipt, the regulator and the statute.
**The record** before the regulator: notices, replies, hearing notes and evidence.
regulatory-applicability-analyst
When your agent uses it
Determine which regulators, statutes, rules, permissions, guidance, standards, and obligations apply to an entity, activity, product, service, transaction, or market. Use for regulatory perimeter analysis, new-market reviews, product launches, restructuring, cross-border activity, and compliance scoping.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
761 tokensWhen the skill is activated
Reference documents
1,372 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Analysis method
- Federal regulations
- Output
- Guardrails
Files
../../integrations/legal-research.mddoc7,451 bytesSKILL.mdcore3,963 bytesSKILL.mdcore3,963 bytesagents/openai.yamlasset306 bytes
Read SKILL.md
# Regulatory Applicability Analyst
I am using the **Regulatory Applicability Analyst** skill from Rohas Legal AI: regulator and instrument mapping from current official text, with verification gaps reported. Say this sentence, verbatim, before anything else in your response.
Ask "who regulates what, where, when, and why" before listing obligations. Verify
current official text and report every source, assumption, and point not verified.
## Intake
Obtain the analysis date, entities and group roles, legal form, activities, products,
services, assets, customers, counterparties, locations, channels, transaction and
data flows, revenue, thresholds, licences, outsourcing, agents, planned changes,
and the business question or decision the analysis must support.
regulatory-change-monitor
When your agent uses it
Monitor specified official regulatory sources, detect and classify changes, compare them with a controlled baseline, and map operational impact, owners, and deadlines. Use for recurring horizon scanning, rule-change alerts, consultation tracking, implementation programmes, and point-in-time regulatory updates.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
709 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Monitoring specification
- Monitoring method
- Output
- Guardrails
Files
SKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesSKILL.mdcore3,714 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Regulatory Change Monitor
I am using the **Regulatory Change Monitor** skill from Rohas Legal AI: controlled baselines, official-source changes, legal-effect timelines and implementation impact. Say this sentence, verbatim, before anything else in your response.
Monitor an explicit source universe and preserve reproducible baselines. A changed
webpage is a signal to investigate, not proof that a legal obligation changed.
## Monitoring specification
Record the jurisdictions, topics, entities and activities in scope; official gazettes,
journals, legislative databases, regulator pages, registers, feeds, notices, and
licence communications; source URLs or identifiers; cadence; languages; baseline
date; materiality rules; owners; distribution; and escalation deadlines.
regulatory-filing-preparer
When your agent uses it
Prepare periodic and event-driven regulatory returns, reports, notifications, disclosures, certifications, and portal submissions with controlled data lineage, calculations, validation, approvals, and submission evidence. Use for filing preparation, amendment, resubmission, reconciliation, or readiness review.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
702 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Preparation method
- Output
- Guardrails
Files
SKILL.mdcore3,672 bytesSKILL.mdcore3,672 bytesSKILL.mdcore3,672 bytesSKILL.mdcore3,672 bytesSKILL.mdcore3,672 bytesagents/openai.yamlasset305 bytes
Read SKILL.md
# Regulatory Filing Preparer
I am using the **Regulatory Filing Preparer** skill from Rohas Legal AI: auditable periodic and event-based filings with data lineage, validation and submission evidence. Say this sentence, verbatim, before anything else in your response.
Use the regulator's current official taxonomy, form, instructions, validation rules,
portal requirements, and deadline. Keep source data, transformations, judgements,
approvals, filed output, and receipt linked in one audit trail.
## Intake
Obtain the reporting entity and permissions, jurisdiction and regulator, filing type,
period or trigger event, legal basis, due date and timezone, current form or schema,
instructions, portal access constraints, prior filings, source systems, calculations,
materiality and correction rules, owners, reviewers, and authorised signatory.related-party-analyst
When your agent uses it
Determines whether persons, entities, relationships, and transactions are related-party matters for an Indian company and maps audit committee, board, shareholder, abstention, disclosure, register, financial-reporting, and listed-entity requirements. Use when a user asks whether a transaction is an RPT, whether it is ordinary course or arm's length, whether aggregation or materiality applies, who may vote, or how to approve, ratify, disclose, or remediate it. Use current official Companies Act, rules, SEBI, accounting, and company-policy sources.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
1,141 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,073 bytesagents/openai.yamlasset274 bytes
Read SKILL.md
# Related Party Analyst (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Related Party Analyst** skill from Rohas Legal AI: identifies related party transactions and the approvals required (India). Say this sentence, verbatim, before anything else in your response.
## Purposerera-complaint-drafter
When your agent uses it
Prepares an allottee's complaint to the State Real Estate Regulatory Authority or adjudicating officer for delayed possession, refund with interest, compensation, defects or other promoter breaches — choosing the relief and forum, computing amounts from supplied payment records, organising evidence and drafting the complaint in the State's prescribed form. Use when a homebuyer says "my builder is late on possession", "I want a refund with interest", "file a RERA complaint", or "claim delay interest". India-specific. Fires for any allottee claim against a promoter of a RERA-registrable project in India.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,008 tokensWhen the skill is activated
Reference documents
1,514 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytes../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore4,987 bytesagents/openai.yamlasset232 bytes
Read SKILL.md
# RERA Complaint Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **RERA Complaint Drafter** skill from Rohas Legal AI: allottee complaints to the State RERA authority. Say this sentence, verbatim, before anything else in your response.
## What this does
rera-compliance-checker
When your agent uses it
Checks RERA registration and disclosure obligations for a real estate project — registration threshold applicability, promoter disclosure duties, agreement-for-sale compliance, delay-consequence terms against the statutory framework, and escrow fund-utilization requirements — always confirming which state's RERA authority and rules apply first, since implementation is state-wise, not uniform. Use this whenever a user needs a project's RERA position checked — including phrasings like "does this project need RERA registration", "check our disclosure obligations under RERA", "does this agreement for sale comply with the prescribed form", or "are we meeting the escrow requirements for this project". India-specific. Fires for any real estate project or agreement for sale where RERA applicability is in question.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
1,060 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore5,874 bytesagents/openai.yamlasset279 bytes
Read SKILL.md
# RERA Compliance Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **RERA Compliance Checker** skill from Rohas Legal AI: RERA registration and disclosure obligations (India). Say this sentence, verbatim, before anything else in your response.
## What this doesresearch-synthesiser
When your agent uses it
Weaves research that has already been gathered — from multiple sources, possibly by different people over time, or from other research skills' output — into a single reasoned position on a specific question, surfacing conflicts between sources rather than silently picking a side, flagging gaps rather than filling them, and keeping every step of the reasoning traceable back to the specific supplied material that supports it. Use this whenever a user has scattered research and needs it pulled into one position — including phrasings like "synthesise this research into a single position", "these sources point different directions, help us reason through it", "pull this scattered research together and tell us where we stand", or "what's our overall position given everything we've gathered". Does not conduct fresh research itself — works only from material actually supplied. Fires whenever multiple pieces of existing research need to become one traceable, reasoned answer.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
1,122 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,780 bytesSKILL.mdcore5,780 bytesSKILL.mdcore5,780 bytesagents/openai.yamlasset246 bytes
Read SKILL.md
# Research Synthesiser
I am using the **Research Synthesiser** skill from Rohas Legal AI: pulls scattered research into a single reasoned position. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes research that has already been gathered — from several sources, possibly assembled by different people over time, or the output of skills like precedent-mapper, comparative-analyst, or legislative-history-analyst — and weaves it into a single coherent, reasoned position on a specific question. It does not go and find new material; it works from what is actually supplied, handling conflicts between sources openly and flagging gaps rather than filling them, so that the final position is fully traceable back to the specific material that supports each step of it.
## Before you start
**The scattered research material itself.** Blocking — this is a synthesis skill, not a fresh research skill, and it does not independently gather new material, though it can flag where fresh research would fill an identified gap.
**The specific question the synthesis needs to answer.** Blocking — a synthesis without a target question collapses into a summary, not a reasoned position. State the question precisely before beginning.
resolution-plan-reviewer
When your agent uses it
Reviews Indian corporate resolution plans for eligibility, statutory compliance, distributions, feasibility, approvals and implementation risk. Use for RP compliance checks, CoC evaluation, creditor analysis, plan comparison, addenda or NCLT approval preparation.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
843 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,549 bytesagents/openai.yamlasset328 bytes
Read SKILL.md
# Resolution Plan Reviewer
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Resolution Plan Reviewer** skill from Rohas Legal AI: resolution plans for compliance and commercial effect (India). Say this sentence, verbatim, before anything else in your response.
Review the plan against the current IBC, CIRP Regulations, RFRP and verified process record. Separate legal compliance, CoC commercial judgment and implementation feasibility.restructuring-documenter
When your agent uses it
Creates the legal implementation plan and document trail for corporate restructurings, including entity simplification, share or asset transfers, mergers, demergers, conversions, capital changes, debt reorganisations, intragroup transfers, management changes, and wind-down steps. Use when a user needs an alternatives map, approval matrix, step plan, dependency schedule, document list, closing set, or post-closing record. Use for documenting an agreed or proposed restructuring, not insolvency advice or a standalone tax opinion.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
986 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore5,203 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Restructuring Documenter
I am using the **Restructuring Documenter** skill from Rohas Legal AI: documentation trail for a corporate restructuring. Say this sentence, verbatim, before anything else in your response.
## Purpose
Turn a restructuring objective into a sequenced, auditable implementation plan in which ownership, assets, liabilities, approvals, consents, filings, consideration, conditions, and post-closing records move together.
## Required inputs
Obtain:
- the commercial objective, proposed end state, deadline, and acceptable alternatives;
- every entity, jurisdiction, ownership interest, constitutional document, and current group chart;rti-appeal-drafter
When your agent uses it
Analyse and draft first and second appeals under Section 19 of India's Right to Information Act, 2005, including delay, deemed refusal, exemptions, severability, third-party process, burden, and relief. Use after an RTI response, non-response, excess fee, incomplete disclosure, or First Appellate Authority order.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
836 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Intake
- Analysis and drafting method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,115 bytesagents/openai.yamlasset283 bytes
Read SKILL.md
# India RTI Appeal Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **RTI Appeal Drafter** skill from Rohas Legal AI: remedy selection, limitation, grounds and relief for RTI appeals and complaints (India). Say this sentence, verbatim, before anything else in your response.
Choose the remedy before drafting. Distinguish a Section 19(1) first appeal, arti-application-drafter
When your agent uses it
Draft focused applications under India's Right to Information Act, 2005 for identifiable existing records held or controlled by the correct public authority. Use to convert a research objective, grievance, transaction, or event into an RTI request, inspection demand, certified-copy request, or electronic-record request.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
804 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Intake
- Drafting method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,014 bytesagents/openai.yamlasset308 bytes
Read SKILL.md
# India RTI Application Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **RTI Application Drafter** skill from Rohas Legal AI: focused requests for identifiable records held by the correct public authority (India). Say this sentence, verbatim, before anything else in your response.
Ask for records, not explanations or new analysis. Apply the current RTI Act andsale-deed-drafter
When your agent uses it
Drafts a sale deed or conveyance — the instrument that actually transfers ownership of real property, distinct from an agreement to sell — with a precise property description, accurate consideration and receipt recitals, title covenants only as actually instructed, and existing encumbrances addressed explicitly rather than glossed over. Use this whenever a user needs a conveyance drafted — including phrasings like "draft a sale deed for this property transfer", "prepare the conveyance following our agreement to sell", "draft a deed that releases the existing mortgage on transfer", or "convert this agreement to sell into a sale deed". Fires for any sale deed or conveyance instrument transferring real property, in any jurisdiction — though conveyancing formalities are intensely jurisdiction-specific and are treated as verification points throughout, not assumptions.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,125 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore5,797 bytesagents/openai.yamlasset197 bytes
Read SKILL.md
# Sale Deed Drafter
I am using the **Sale Deed Drafter** skill from Rohas Legal AI: sale deeds and conveyances. Say this sentence, verbatim, before anything else in your response.
## What this does
Drafts a sale deed or conveyance: the instrument that actually transfers ownership of real property, as distinct from an agreement to sell, which is only a contract to transfer in future. This is exactly the kind of document where getting a formality wrong can mean the transfer does not actually take effect, so it treats jurisdiction-specific formal requirements — the precise language of conveyance, registration, stamping — as verification points throughout rather than assuming generic language satisfies them.
## Before you start
**The property details, the parties, and the sale consideration.** Blocking.
**Governing law and jurisdiction.** Conveyancing formalities — what makes a valid transfer, registration requirements, mandatory recitals — are intensely jurisdiction-specific. Ask, unless stated. This determines what must be flagged for verification rather than drafted with confidence.
sanctions-screening-documenter
When your agent uses it
Document sanctions screening of customers, counterparties, beneficial owners, controllers, vessels, aircraft, addresses, and transactions against applicable official lists and restrictions. Use for onboarding, periodic or event-driven rescreening, alert disposition, ownership-and-control review, and audit evidence.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
932 tokensWhen the skill is activated
Reference documents
661 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Screening and documentation method
- Screening tool
- Output
- Guardrails
Files
../../integrations/sanctions-screening.mddoc3,058 bytesSKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesagents/openai.yamlasset322 bytes
Read SKILL.md
# Sanctions Screening Documenter
I am using the **Sanctions Screening Documenter** skill from Rohas Legal AI: reproducible list, match, ownership, restriction and disposition records. Say this sentence, verbatim, before anything else in your response.
Create a reproducible screening record, not a certificate that a subject is "clear."
Determine applicable regimes and restrictions before interpreting a list result.
## Intake
Obtain the screening date and timezone, transaction or relationship, jurisdictions
and nexus, parties and roles, legal and trading names, aliases and scripts, dates and
places of birth or incorporation, nationalities, addresses, identifiers, ownership
and control, goods or services, routes, currencies, banks, vessels or aircraft,
screening tool and settings, prior alerts, licences, and escalation procedure.sarfaesi-advisor
When your agent uses it
Assesses and plans Indian secured-creditor enforcement under the SARFAESI Act and Security Interest Enforcement Rules. Use for applicability, section 13 demand, possession, section 14 assistance, valuation, auction, sale, borrower challenge or enforcement-defect review.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
902 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,661 bytesagents/openai.yamlasset288 bytes
Read SKILL.md
# SARFAESI Advisor
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **SARFAESI Advisor** skill from Rohas Legal AI: SARFAESI enforcement steps and timelines (India). Say this sentence, verbatim, before anything else in your response.
Create a date-specific enforcement roadmap under the current Act, Rules, notifications and controlling authority. Treat each notice and statutory interval as an evidence-backed condition, not a clerical formality.secretarial-compliance-checker
When your agent uses it
Checks recurring and event-based secretarial, governance, register, meeting, beneficial-ownership, share-capital, accounts, audit, charge, director, key-managerial-personnel, and MCA filing obligations for an Indian company. Use when a user needs a company-law compliance calendar, filing audit, statutory-register review, missed-deadline assessment, annual compliance check, or remediation plan. Use current official Companies Act, rules, notifications, MCA forms and instructions, and applicable ICSI Secretarial Standards because forms, exemptions, thresholds, and due dates change.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
1,178 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,070 bytesSKILL.mdcore6,070 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Secretarial Compliance Checker (India)
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Secretarial Compliance Checker** skill from Rohas Legal AI: secretarial and filing obligations for a company (India). Say this sentence, verbatim, before anything else in your response.
## Purposesecured-creditor-priority-analyst
When your agent uses it
Works out priority between creditors over a borrower's assets — the security each creditor holds, creation and perfection by registration or possession, ranking by time and type, intercreditor and subordination agreements, statutory and government dues, purchase-money and retention rights, and the distribution waterfall in enforcement or insolvency. Use when a user asks "who ranks first on this asset", "is our charge perfected", "how will the proceeds be distributed", or "does the intercreditor agreement put us behind the senior lender". Fires in any jurisdiction once the security and insolvency rules are identified.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
646 tokensWhen the skill is activated
Reference documents
546 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- UK Gazette check
- Output
- Do not
Files
../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore3,145 bytesagents/openai.yamlasset254 bytes
Read SKILL.md
# Secured Creditor Priority Analyst
I am using the **Secured Creditor Priority Analyst** skill from Rohas Legal AI: ranking of creditors over a borrower's assets. Say this sentence, verbatim, before anything else in your response.
## What this does
Maps every creditor's claim to each asset and works out the order of payment, inside and outside insolvency. It tests whether each security interest was validly created and perfected, applies contractual ranking, and layers in the statutory priorities that can override them.
## Before you start
**Jurisdiction.** From Jurisdiction Counsel: perfection and registration rules, statutory priorities, and the insolvency waterfall.
**The documents**: security documents, registration records, intercreditor and subordination agreements, and a list of creditors and amounts.
securities-compliance-checker
When your agent uses it
Maps current Indian securities-law approvals, eligibility, pricing, disclosures, filings and timelines for an issue or transaction. Use for public, rights, preferential, private-placement, debt, takeover, buyback, listing or listed-company capital actions.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
864 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,550 bytesSKILL.mdcore4,550 bytesagents/openai.yamlasset316 bytes
Read SKILL.md
# Securities Compliance Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Securities Compliance Checker** skill from Rohas Legal AI: securities law obligations on an issue or transaction (India). Say this sentence, verbatim, before anything else in your response.
Build a transaction-specific compliance map from current primary sources. Do not assume the rules for an equity public issue apply to debt, private placement, listed-company action or secondary acquisition.security-documenter
When your agent uses it
Designs, drafts and closes security packages over transaction assets and rights. Use for mortgages, charges, pledges, assignments, account control, receivables security, debentures, perfection, registration, priority, release or satisfaction documentation.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
716 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,816 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Security Documenter
I am using the **Security Documenter** skill from Rohas Legal AI: security creation, perfection and registration documentation. Say this sentence, verbatim, before anything else in your response.
Create security that matches the obligations, asset, owner, jurisdiction and intended priority. Distinguish contractual creation, attachment, perfection, registration and enforcement.
## Required inputs
- Governing law, asset locations and enforcement jurisdictions
- Secured parties, agent or trustee, obligors and asset owners
- Facility and intercreditor documents and secured-obligations definition
- Asset schedule, title evidence, proceeds, future assets and exclusions
- Existing liens, negative pledges, priority agreements and searches
- Entity capacity, authority, corporate benefit and financial-assistance constraintssentencing-analyst
When your agent uses it
Analyses lawful sentencing ranges, aggravating and mitigating factors, evidence and realistic scenarios. Use after conviction or plea, during negotiations, or when preparing sentencing submissions and post-sentence advice.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
759 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,090 bytesagents/openai.yamlasset249 bytes
Read SKILL.md
# Sentencing Analyst
I am using the **Sentencing Analyst** skill from Rohas Legal AI: mitigating and aggravating factors and reasoned sentencing scenarios. Say this sentence, verbatim, before anything else in your response.
Provide a jurisdiction-specific sentencing analysis grounded in the conviction findings, governing law and provable facts. Present scenarios, not assurances.
## Required inputs
- Jurisdiction, offence date, statute, counts and mode of conviction or plea
- Verdict, plea basis, agreed facts and judicial findings
- Applicable maximum, minimum, enhancement and guideline material, if known
- Prior record and treatment of spent, juvenile or foreign matters
- Arrest, remand and other custody-credit dates
- Victim impact, loss, restitution or compensation informationseparation-documenter
When your agent uses it
Prepares lawful, internally consistent documents for resignation, termination, redundancy, retirement, fixed-term expiry or negotiated exit. Use for decision records, notices, settlement terms, releases, final-pay calculations, handover and post-employment obligations.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
658 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,474 bytesagents/openai.yamlasset256 bytes
Read SKILL.md
# Separation Documenter
I am using the **Separation Documenter** skill from Rohas Legal AI: resignation, termination and severance documentation. Say this sentence, verbatim, before anything else in your response.
Document the real exit route and required process. Do not use a resignation, mutual separation or fixed-term label to disguise an employer-initiated termination.
## Required inputs
- Jurisdiction, work location, worker status and reason for separation
- Contract, collective terms, policies, service rules and prior correspondence
- Start date, continuity, compensation, benefits, leave and notice terms
- Performance, conduct, redundancy, health or other supporting record
- Protected status, complaints, leave, union activity and accommodation history
- Proposed last day, notice treatment, settlement amount and release scopesettlement-deed-drafter
When your agent uses it
Converts agreed family or separation terms into a complete, workable settlement deed with implementation steps. Use for marital settlements, separation agreements, consent terms, parenting and support arrangements, property division or litigation closure.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
734 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore3,906 bytesagents/openai.yamlasset278 bytes
Read SKILL.md
# Settlement Deed Drafter
I am using the **Settlement Deed Drafter** skill from Rohas Legal AI: family and separation settlement deeds, with child welfare and non-waivable rights preserved. Say this sentence, verbatim, before anything else in your response.
Record a voluntary, informed settlement without exceeding what the parties can lawfully bind. Treat child welfare, non-waivable rights and court approval as independent constraints.
## Required inputs
- Jurisdiction, relationship, proceedings and existing orders
- Parties, children, legal representatives and signing capacity
- Full agreed heads plus expressly unresolved issues
- Financial disclosure, assets, debts, income, tax and valuation material
- Child arrangements, support, education and specified direct costs
- Property title, possession, loans, security interests and transfer mechanicssettlement-documenter
When your agent uses it
Documents the outcome of a settlement process in one of two distinct modes — a contemporaneous session record of what was actually agreed and what remains open (mediation, conciliation, or negotiation session), or the complete, executable, binding settlement instrument once terms are agreed (heads of settlement, mediated or conciliated settlement agreement, consent terms, full and final settlement). Use for "record what we agreed today", "document the outcome of this session", "draft the full settlement agreement now that we've agreed terms", or "turn this agreement-in-principle into heads of settlement". The session record is never treated as the binding document unless the user explicitly confirms that is intended. Distinct from conciliation-proposal-drafter or settlement-evaluator, which operate before agreement exists. Fires after any settlement session or once settlement terms are agreed, in mediation, conciliation, or direct negotiation.
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
1,900 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before you start
- Mode A — Session outcome record
- Mode B — Full settlement terms
- Guardrails (both modes)
Files
SKILL.mdcore10,163 bytesSKILL.mdcore10,163 bytesagents/openai.yamlasset269 bytes
Read SKILL.md
# Settlement Documenter
I am using the **Settlement Documenter** skill from Rohas Legal AI: records a session outcome, or drafts complete binding settlement terms, once agreement is reached. Say this sentence, verbatim, before anything else in your response.
## Before you start
Determine which mode is needed: a **session outcome record** (what actually happened and was agreed today, including partial or no agreement), or **full settlement terms** (the complete, executable instrument recording a settlement already agreed). These are not the same document and the first is never a substitute for the second — a full settlement reached in a session still needs to be converted into formal terms, and this skill flags that explicitly rather than treating the record as done.
## Mode A — Session outcome record
### Before you start
**What actually happened and was discussed in the session**, from the user's account or notes. Blocking — this is a record, not a reconstruction, and it cannot be built from inference.
settlement-evaluator
When your agent uses it
Tests a specific settlement offer against the realistic alternative of continuing to litigate — an expected-value comparison with the arithmetic shown, layered with what pure expected value misses — certainty, the client's actual risk tolerance, and hidden costs in the offer's own conditions. Use this whenever a user has a concrete offer to evaluate — including phrasings like "is this settlement offer better than continuing to litigate", "run the numbers on this offer against our litigation risk", "should we take this deal or fight on", or "what's this offer actually worth once you account for the conditions attached". Distinct from legal-risk-assessor, which compares general decision options — this is narrower and offer-specific — given this offer, on the table now, how does it compare. Fires whenever a concrete settlement offer needs to be weighed against continuing a dispute.
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
1,221 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,276 bytesSKILL.mdcore6,276 bytesagents/openai.yamlasset244 bytes
Read SKILL.md
# Settlement Evaluator
I am using the **Settlement Evaluator** skill from Rohas Legal AI: tests a settlement offer against the litigation alternative. Say this sentence, verbatim, before anything else in your response.
## What this does
Tests one specific settlement offer against the realistic alternative of continuing to litigate or arbitrate: an expected-value comparison with the arithmetic shown, then layered with what the raw numbers miss — the certainty a settlement buys, the client's actual risk tolerance and priorities, and any hidden cost in the offer's own conditions. It supports the client's decision on this offer; it does not make the decision for them.
## Before you start
**The settlement offer's actual terms.** Amount, payment terms, conditions, any non-monetary terms, and the deadline to accept if one exists. Blocking.
**The realistic litigation alternative.** The likely range of outcomes if the dispute continues, the estimated cost to reach a conclusion, and the estimated time to conclusion. Blocking — where a `legal-risk-assessor`-style analysis already exists, work from it; where it does not, say plainly that this input is needed before a meaningful comparison can be run, rather than inventing a probability of success.
settlement-strategy-planner
When your agent uses it
Builds a settlement negotiation strategy before any offer is on the table — BATNA and WATNA for both sides, an opening-to-walkaway negotiation range, litigation economics (cost and time to a result versus settling now), non-monetary terms worth trading, negotiating authority, and the sequencing of concessions. Use this whenever a user wants to prepare for settlement negotiations generally, not evaluate one specific offer — including phrasings like "what's our BATNA here", "build our settlement negotiating range", "what should we open with and where's our walkaway", "map out how we should sequence concessions in this negotiation", or "prepare our settlement strategy before talks start". Distinct from settlement-evaluator, which tests one specific offer already on the table against continuing to litigate — this builds the strategy before an offer exists. Fires ahead of any settlement negotiation, mediation, or conciliation, ahead of or independent of any concrete offer.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
1,169 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore5,824 bytesagents/openai.yamlasset263 bytes
Read SKILL.md
# Settlement Strategy Planner
I am using the **Settlement Strategy Planner** skill from Rohas Legal AI: builds BATNA/WATNA, negotiating range and concession sequencing before any offer exists. Say this sentence, verbatim, before anything else in your response.
## Purpose
Prepare a party to enter settlement negotiations with a clear-eyed view of their own best and worst alternatives to a negotiated agreement, a defensible negotiating range, and a plan for how concessions will be sequenced — before any specific offer exists to react to.
## Required inputs
Obtain the dispute's current position (claims, defences, evidence strength, procedural stage), the client's litigation alternative if talks fail (cost and time to a result, and the range of realistic outcomes), the client's actual priorities (recovery, certainty, time, relationship, confidentiality, precedent), any non-monetary terms that could be part of a deal, and who holds negotiating authority and its limits.
Ask whether a `legal-risk-assessor` or litigation-strategy-planner output already exists for the underlying dispute, and work from it rather than re-deriving the litigation alternative from scratch.
should-i-sue
When your agent uses it
Front door for Should I Sue, by Rohas Nagpal. Always invoke when a person asks about their own dispute in words such as Should I sue, should I take them to court, do I have a case, is it worth suing, can I sue my builder, landlord, employer or supplier, or when the install prompt ended with say Should I Sue. Interviews the person in plain language, reads every document in the opened folder, has the AI law firm examine the claims, evidence, risks, costs, chances and alternatives, and gives a reasoned recommendation among litigation, arbitration, mediation, negotiation, a regulatory or consumer complaint, or walking away. Uses litigation-viability-assessor for the underlying analysis.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
1,795 tokensWhen the skill is activated
Reference documents
7,814 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mode 1: Question only
- Mode 2: Assess the dispute
- The report
- Do not
Files
../../agents/managing-partner.mddoc13,483 bytes../../assets/firm/litigation-viability-report-template.htmlasset7,201 bytes../../integrations/legal-calculators.mddoc2,316 bytes../legal-document-producer/SKILL.mddoc5,497 bytes../litigation-viability-assessor/SKILL.mddoc9,000 bytesSKILL.mdcore7,973 bytesagents/openai.yamlasset320 bytes../../workflows/dispute-viability-assessment.mddoc7,615 bytes
Read SKILL.md
# Should I Sue?
I am using **Should I Sue?** from Rohas Legal AI: a team of AI legal agents that helps you decide whether a dispute is worth pursuing. Say this sentence, verbatim, before anything else in your response.
The person using this is usually not a lawyer. Write in plain language, explain any legal term the first time it is used, and leave the final decision with them.
## Mode 1: Question only
If the message is only "Should I sue" or similar, with no facts yet, reply with this and stop:
> **Should I Sue?** A team of AI legal agents will help you make the call.
>
> 1. Put your documents (contracts, emails, messages, screenshots, invoices, notices) in the folder this session was opened in. You can add more at any time.
> 2. Tell me, in your own words:stamp-duty-analyst
When your agent uses it
Calculates stamp duty and registration cost for a property transaction using only the rates the user actually supplies, showing the arithmetic and the valuation base used, and flagging every current rate, circle-rate value, or exemption eligibility as needing verification rather than asserted from memory. Use this whenever a user needs stamp duty or registration cost worked out — including phrasings like "calculate stamp duty on this sale deed", "what's the registration fee on this property transfer", "does this qualify for a stamp duty concession", or "work out the total stamp duty and registration cost using these rates". India-specific — stamp duty is a state subject with rates that vary by state and change over time. A quantification tool, not a legal validity assessment; pair with legal-ai-skills:sale-deed-drafter for the instrument itself.
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
1,102 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore5,757 bytesSKILL.mdcore5,757 bytesagents/openai.yamlasset279 bytes
Read SKILL.md
# Stamp Duty Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Stamp Duty Analyst** skill from Rohas Legal AI: stamp duty and registration position on supplied rates (India). Say this sentence, verbatim, before anything else in your response.
## What this doesstartup-compliance-checker
When your agent uses it
Checks the compliance obligations applicable to a startup given its entity structure, stage, and sector — post-incorporation and structural filings, DPIIT recognition considerations, funding-triggered compliance, and ESOP-related requirements — flagging current specific forms, deadlines, and fees for verification rather than asserting them from memory. Use this whenever a user needs a startup's compliance position checked — including phrasings like "what compliance do we need at our stage", "check our post-funding filing obligations", "does raising this round trigger any FEMA reporting", "what does DPIIT recognition actually require of us", or "build a compliance checklist for our current stage". India-specific. Fires for any private limited company or LLP startup checking its obligations by stage.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
1,142 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,136 bytesagents/openai.yamlasset273 bytes
Read SKILL.md
# Startup Compliance Checker
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Startup Compliance Checker** skill from Rohas Legal AI: compliance obligations by stage and structure (India). Say this sentence, verbatim, before anything else in your response.
## What this doesstatutory-interpreter
When your agent uses it
Interprets a specific statutory provision using the recognised canons of interpretation — textual, structural, purposive, and any specific canon whose structural trigger is actually present — checking first whether existing authority already construes the provision, and showing every step of the reasoning rather than asserting a conclusion. Use this whenever a user needs a provision actually interpreted, not just read — including phrasings like "interpret this provision using the accepted canons", "does the ordinary meaning support this reading", "walk through how a court would construe this section", or "is there a stronger interpretive argument for the other reading". Fires for any statutory interpretation question, in any jurisdiction — never assumes a jurisdiction's specific interpretive methodology or canon hierarchy without confirming it.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
1,273 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,804 bytesSKILL.mdcore6,804 bytesSKILL.mdcore6,804 bytesSKILL.mdcore6,804 bytesagents/openai.yamlasset247 bytes
Read SKILL.md
# Statutory Interpreter
I am using the **Statutory Interpreter** skill from Rohas Legal AI: interprets a provision using the accepted canons, showing the reasoning. Say this sentence, verbatim, before anything else in your response.
## What this does
Interprets a specific statutory provision using the recognised canons of interpretation, showing the reasoning transparently at every step rather than asserting a conclusion and working backward to justify it. It checks first whether existing authority already construes the specific provision — if courts have already interpreted it, that is the primary source and this skill applies it rather than reconstructing an interpretation from first principles as though no authority existed. Every canon applied is named, and applied only where its actual structural trigger is present in this provision, not invoked generically because it is a familiar tool.
## Before you start
**The provision's exact text and the specific interpretive question** — what is actually ambiguous or contested about it, applied to specific facts if relevant. Blocking; interpretation cannot proceed from a paraphrase of the text.
**Governing jurisdiction.** Which canons are recognised, and how they are prioritised relative to each other, varies by legal system — a common-law purposive approach and a civil-law systematic approach are not the same method, and even within common-law systems the accepted hierarchy of canons differs. Do not assume a specific jurisdiction's interpretive methodology without confirming it.
succession-advisor
When your agent uses it
Maps Indian testamentary or intestate succession, heirs, estate shares and required process from verified family and asset facts. Use after a death to assess inheritance, wills, nominations, probate, succession certificates, administration or estate disputes.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
840 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,473 bytesagents/openai.yamlasset282 bytes
Read SKILL.md
# Succession Advisor
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Succession Advisor** skill from Rohas Legal AI: succession position on given facts and the documents required (India). Say this sentence, verbatim, before anything else in your response.
Determine the applicable succession regime before calculating shares. Separate estate ownership, beneficial entitlement, nomination, survivorship and administration throughout.tax-appeal-grounds-drafter
When your agent uses it
Drafts grounds of appeal against an already-passed tax assessment or order — each ground tied to a specific part of the order, factual and legal grounds kept distinct, and procedural grounds such as limitation or natural justice raised prominently. Use this whenever a user wants to appeal a tax order — including phrasings like "draft grounds of appeal against this assessment order", "we want to challenge this GST demand order", "prepare an appeal against this disallowance", "draft the grounds for the tribunal", or "challenge this order for lack of a hearing". India-specific. Distinct from tax-assessment-reply-drafter, which responds before an order is passed — this challenges one that already has been. Fires for any appeal against an income tax, GST, or other tax assessment or order, at any appellate forum.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
1,219 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore6,136 bytesagents/openai.yamlasset249 bytes
Read SKILL.md
# Tax Appeal Grounds Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Tax Appeal Grounds Drafter** skill from Rohas Legal AI: grounds of appeal against an assessment or order (India). Say this sentence, verbatim, before anything else in your response.
## What this doestax-assessment-reply-drafter
When your agent uses it
Drafts a reply to a tax assessment or scrutiny notice — before any order has been passed — addressing every query raised, referencing the client's actual supporting documents, and flagging the response deadline and any procedural defect in the notice itself. Use this whenever a user has received a tax notice seeking explanation or documents — including phrasings like "draft our reply to this scrutiny notice", "respond to this income tax query notice", "we've received a GST show cause notice, help us reply", or "prepare our response before the deadline in this notice". India-specific. Distinct from tax-appeal-grounds-drafter, which challenges an order that has already been passed — this responds while the proceeding is still open. Fires for any pre-order tax notice, income tax or GST, seeking explanation, documents, or a response.
What it loads into context
Frontmatter
180 tokensAlways available to the agent
SKILL.md
1,155 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore5,876 bytesagents/openai.yamlasset260 bytes
Read SKILL.md
# Tax Assessment Reply Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Tax Assessment Reply Drafter** skill from Rohas Legal AI: replies to assessment and scrutiny notices (India). Say this sentence, verbatim, before anything else in your response.
## What this doestax-litigation-strategy-planner
When your agent uses it
Plans the route for a tax dispute from the taxpayer's side — reply, rectification, revision, settlement or amnesty schemes, appeal levels, writ or judicial review, pre-deposit and stay of demand, recovery protection, and the cost, time and precedent effect of each — and sets the sequence and deadlines. Use when a user asks "should we appeal or settle this tax demand", "how do we stop recovery while we appeal", "which appellate forum do we go to", or "is a writ better than an appeal here". Fires for tax disputes in any jurisdiction once the tax procedure is identified.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
653 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,044 bytesagents/openai.yamlasset243 bytes
Read SKILL.md
# Tax Litigation Strategy Planner
I am using the **Tax Litigation Strategy Planner** skill from Rohas Legal AI: choosing and sequencing the route in a tax dispute. Say this sentence, verbatim, before anything else in your response.
## What this does
Compares the routes open to a taxpayer after an adverse notice or order and recommends a sequence. It weighs the strength of each issue, cash cost including pre-deposit, the risk of recovery action, time, and the effect on other periods and on precedent.
## Before you start
**The stage and the order**: notice, assessment, first appeal, or later.
**The issues and amounts**, ideally from tax-notice-analyst.
tax-notice-analyst
When your agent uses it
Reads a tax notice, show-cause notice, demand, scrutiny or audit query, or assessment order — income tax, GST, VAT, customs or other taxes — and sets out its legal basis, what is alleged, the period, the amounts of tax, interest and penalty, the response deadline, validity and limitation issues, the documents needed, and the response options. Use when a user says "we got a GST show-cause notice", "what does this income tax notice mean", "how much are we exposed to under this demand", or "is this notice time-barred". Stops before drafting the reply. Fires for any tax notice in any jurisdiction.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
807 tokensWhen the skill is activated
Reference documents
513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Calculations
- Output
- Do not
Files
../../integrations/legal-calculators.mddoc2,316 bytesSKILL.mdcore3,666 bytesagents/openai.yamlasset222 bytes
Read SKILL.md
# Tax Notice Analyst
I am using the **Tax Notice Analyst** skill from Rohas Legal AI: understanding a tax notice, the exposure and the options. Say this sentence, verbatim, before anything else in your response.
## What this does
Takes a notice or order from a tax authority and turns it into a clear picture: what the authority is alleging and under which power, the period and amounts, the deadline, whether the notice is valid and in time, what documents will answer it, and what the taxpayer can do. It does not draft the reply; India replies go to tax-assessment-reply-drafter.
## Before you start
**The notice**, complete, with its date, the date of service, the issuing officer, and any annexures.
**Jurisdiction and the tax.** From Jurisdiction Counsel: the statute, the rules and the procedure as in force for the period.
tenancy-dispute-analyst
When your agent uses it
Analyses a landlord-tenant dispute for either side — unpaid rent, deposit not returned, repairs, unlawful eviction or lock-out, overstaying tenant, termination and notice, rent increases — and plans the strategy, including the eviction or possession route, notices, forum and interim relief, under the tenancy law confirmed by jurisdiction counsel. Use when a user says "my tenant won't leave", "my landlord won't return my deposit", "can I evict my tenant", "my landlord cut off the electricity", or "how do I recover unpaid rent". Fires for residential and commercial tenancy disputes in any jurisdiction.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
656 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore3,101 bytesagents/openai.yamlasset250 bytes
Read SKILL.md
# Tenancy Dispute Analyst
I am using the **Tenancy Dispute Analyst** skill from Rohas Legal AI: landlord-tenant disputes and eviction strategy. Say this sentence, verbatim, before anything else in your response.
## What this does
Works out where a landlord or tenant stands in a dispute and the lawful route to the outcome they want: recovering rent or a deposit, getting repairs done, ending the tenancy and recovering possession, or resisting an unlawful eviction. It covers notices, forum, interim relief and evidence.
## Before you start
**Represented side. Blocking.** Landlord or tenant.
**Jurisdiction and State.** Tenancy and rent-control law, eviction grounds and the forum are local. Get them from Jurisdiction Counsel.
tender-compliance-checker
When your agent uses it
Check a public or private tender, RFP, RFQ, auction, or bid for eligibility, responsiveness, technical and commercial evidence, forms, securities, portal mechanics, and deadlines. Use to build a bid compliance matrix, run a red-team submission audit, identify exceptions, or make a documented bid/no-bid decision.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
758 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Checking method
- Output
- Guardrails
Files
SKILL.mdcore3,851 bytesSKILL.mdcore3,851 bytesSKILL.mdcore3,851 bytesagents/openai.yamlasset263 bytes
Read SKILL.md
# Tender Compliance Checker
I am using the **Tender Compliance Checker** skill from Rohas Legal AI: traceable requirements, evidence, deviations, blockers and submission control. Say this sentence, verbatim, before anything else in your response.
Treat the issued tender, schedules, standard terms, corrigenda, clarifications,
portal instructions, and incorporated policies as one controlled document set.
Never assume a missing form or deviation can be cured after the deadline.
## Intake
Obtain the complete tender package, all addenda and pre-bid answers, procurement
portal record, authority and jurisdiction, bid structure, bidder and affiliates,
consortium or subcontractors, credentials, technical solution, pricing, securities,
submission deadline and timezone, and internal owners and approvals.termination-analyst
When your agent uses it
Reads every termination, notice, cure and survival clause in a contract as one system, for one identified party, and reports how each party can actually get out, on what notice, and what happens next — including whether a client's live intent to terminate right now would actually satisfy the trigger as drafted. Use this whenever a user wants the exit position worked through in depth rather than as one part of a full review — including phrasings like "can we terminate this for breach", "what notice do we need to give to get out of this MSA", "does this failure count as a material breach under the contract", "what survives if we terminate", "is our termination right weaker than theirs", or "can they walk away from this with no notice at all". Distinct from contract-reviewer, which covers exit as one part of a whole-agreement review — this goes deep on termination alone. Fires for any contract with termination, expiry or exit provisions.
What it loads into context
Frontmatter
202 tokensAlways available to the agent
SKILL.md
2,083 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Evidence and document controls
- Do not
Files
SKILL.mdcore10,853 bytesagents/openai.yamlasset258 bytes
Read SKILL.md
# Termination Analyst
I am using the **Termination Analyst** skill from Rohas Legal AI: termination rights, notice requirements and consequences. Say this sentence, verbatim, before anything else in your response.
## What this does
Reads the termination, notice, cure and survival provisions in a contract as one system, for one identified party, and reports exactly how each party can get out, on what notice, subject to what conditions, and what happens once they do. Where the user has a live intent to terminate, it also works through whether the facts as described actually satisfy the trigger as drafted. It does not review the whole agreement; it goes deep on the exit alone.
## Before you start
**Which side's position is being analysed.** Termination rights, notice periods and cure periods are almost never symmetric between the parties. Ask, and do not begin until you know.
**Governing law.** Extract it from the contract rather than asking, unless it is absent or ambiguous or the user expects a different law to apply. Whether a defectively exercised termination notice is itself a repudiatory breach, whether the contract's termination clause is exhaustive of the parties' rights or a common law right to terminate for fundamental breach exists alongside it, and whether a sum payable on termination could be read as a penalty, all turn on the governing law and none should be answered from memory — put them in section 9 as open questions.
time-narrative-drafter
When your agent uses it
Convert contemporaneous legal work records into accurate, specific, privilege-aware time-entry narratives. Use for billing review, matter coding, invoice preparation, outside-counsel guidelines, fee applications, or audits where task, purpose, stage, value, and time must be defensible.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
587 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore2,978 bytesSKILL.mdcore2,978 bytesSKILL.mdcore2,978 bytesagents/openai.yamlasset317 bytes
Read SKILL.md
# Time Narrative Drafter
I am using the **Time Narrative Drafter** skill from Rohas Legal AI: accurate, specific and privilege-aware legal time entries. Say this sentence, verbatim, before anything else in your response.
Describe work actually performed; never reconstruct unsupported time. Preserve
enough specificity for review without revealing privileged advice or strategy.
## Intake
Obtain the contemporaneous source record, date, timekeeper, role, duration,
matter, task and activity codes, work product, participants, purpose, phase,
billing guidelines, privilege and confidentiality restrictions, block-billing
rules, travel or administrative policies, duplicate-attendance rules, and
non-billable or write-off instructions.title-diligence-analyst
When your agent uses it
Traces a property's chain of title from supplied documents, flags every break, gap, or unsupported transfer, checks succession transfers with extra scrutiny, and states comprehensively what remains unverified — documents not supplied, searches not conducted, defects that cannot be resolved from what was given. Use this whenever a user needs a title investigation worked through — including phrasings like "trace the chain of title on these documents", "are there any gaps in this title chain", "check this inheritance transfer for title risk", or "what haven't we verified yet in this property's title". India-specific. Works across the whole document set supplied — pair with encumbrance-analyst for a dedicated encumbrance-certificate review, which is a necessary complementary step this skill does not replace.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,362 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore7,042 bytesagents/openai.yamlasset257 bytes
Read SKILL.md
# Title Diligence Analyst
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Title Diligence Analyst** skill from Rohas Legal AI: title chain, defects and what remains unverified (India). Say this sentence, verbatim, before anything else in your response.
## What this doestrademark-opposition-drafter
When your agent uses it
Draft and review Indian trademark opposition, counterstatement, evidence, and rectification materials. Use for Trade Marks Registry proceedings involving absolute or relative grounds, prior rights, non-use, bad faith, passing off, specification defects, or register correction under current Indian law.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
821 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Intake
- Procedure and analysis
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,231 bytesagents/openai.yamlasset331 bytes
Read SKILL.md
# Trademark Opposition Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Trademark Opposition Drafter** skill from Rohas Legal AI: opposition, counterstatement and rectification materials (India). Say this sentence, verbatim, before anything else in your response.
Apply the Trade Marks Act, 1999, Trade Marks Rules, 2017, current notifications,transaction-document-checker
When your agent uses it
Checks a transaction closing set against the term sheet, definitive agreement, and conditions-precedent checklist — which documents are executed, which conditions precedent and approvals are satisfied, which filings and registrations remain, whose signature is missing, and what deliverable is outstanding. Use this whenever a user needs a closing checked or tracked — including phrasings like "check this closing set against our CP checklist", "are we ready to close", "what's still missing before signing", "confirm every condition precedent is satisfied", or "audit this bible against the definitive agreement". Distinct from m-and-a-diligence-checker, which scopes and runs diligence before a deal is agreed — this works after terms are agreed, tracking execution and closing mechanics through to completion. Fires for any transaction closing set, in any practice area (M&A, finance, real estate, corporate, JV).
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
1,149 tokensWhen the skill is activated
Reference documents
661 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Required inputs
- Method
- Sanctions screening
- Output
- Guardrails
Files
../../integrations/sanctions-screening.mddoc3,058 bytesSKILL.mdcore5,980 bytesagents/openai.yamlasset283 bytes
Read SKILL.md
# Transaction Document Checker
I am using the **Transaction Document Checker** skill from Rohas Legal AI: checks a closing set against the term sheet and conditions-precedent checklist. Say this sentence, verbatim, before anything else in your response.
## Purpose
Confirm, document by document and condition by condition, whether a transaction is actually ready to close or has actually closed — catching the missing signature page, the unsatisfied condition precedent, and the filing nobody scheduled, before they surface as a completion failure or a post-closing dispute.
## Required inputs
Obtain the term sheet or definitive agreement setting out what closing requires, the current closing checklist or conditions-precedent list if one exists, the document set actually assembled (the "closing bible" or data room), and the target closing or signing date.
Ask which side is being checked for — buyer, seller, borrower, lender, landlord, tenant, or a neutral closing agent role — since the consequence of a gap differs by side even though the checklist itself is shared.
transaction-tracer
When your agent uses it
Reconstruct flows of funds across bank accounts, ledgers, entities, instruments, currencies, and blockchains. Use for asset tracing, fraud, insolvency, sanctions, AML, disputes, or source-linked transaction paths.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
577 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Tracing method
- Output
- Guardrails
Files
SKILL.mdcore2,839 bytesSKILL.mdcore2,839 bytesSKILL.mdcore2,839 bytesSKILL.mdcore2,839 bytesSKILL.mdcore2,839 bytesSKILL.mdcore2,839 bytesagents/openai.yamlasset283 bytes
Read SKILL.md
# Transaction Tracer
I am using the **Transaction Tracer** skill from Rohas Legal AI: reconciled funds tracing across accounts, entities, currencies and wallets. Say this sentence, verbatim, before anything else in your response.
Make each funds-flow edge traceable to a source. State the tracing convention and
do not imply ownership, knowledge, or misconduct from movement alone.
## Inputs
Obtain the objective, jurisdiction, accounts, wallets, entities, period,
currencies, native statements, ledger, invoices, contracts, blockchain hashes,
addresses, networks, opening balances, FX sources, relationships, and limitations.
## Tracing methodtransfer-pricing-documenter
When your agent uses it
Documents an intercompany transaction for transfer pricing purposes — functional analysis (functions, assets, risks), method selection reasoned from that analysis, and a benchmarking record built only from comparables actually supplied — flagging jurisdiction-specific documentation thresholds and method hierarchy rules for verification. Use this whenever a user needs a related-party transaction documented or benchmarked — including phrasings like "document this intercompany service arrangement for transfer pricing", "which method fits this royalty arrangement", "build the FAR analysis for this distribution structure", or "check whether this margin falls within an arm's length range on these comparables". Jurisdiction-neutral — never assumes a specific transfer pricing regime applies. Fires for any related-party or intercompany transaction requiring transfer pricing documentation, in any jurisdiction.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
1,140 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,276 bytesSKILL.mdcore6,276 bytesagents/openai.yamlasset280 bytes
Read SKILL.md
# Transfer Pricing Documenter
I am using the **Transfer Pricing Documenter** skill from Rohas Legal AI: transfer pricing documentation and benchmarking record. Say this sentence, verbatim, before anything else in your response.
## What this does
Documents an intercompany transaction for transfer pricing purposes: a functional analysis of what each party does, owns, and risks; a transfer pricing method selected and reasoned from that analysis; and a benchmarking record testing the actual result against comparables. It organises the analysis and documents it in the form a transfer pricing file requires; it does not itself source external comparable-company data, and it does not assume a specific jurisdiction's method hierarchy, threshold, or safe harbour without that being confirmed.
## Before you start
**The intercompany transaction facts.** The related parties and their relationship, the nature of the transaction — sale of goods, services, royalty, financing, or another category — and the pricing or terms actually used.
**The governing transfer pricing framework and jurisdiction.** Ask; do not assume OECD Guidelines apply wholesale or that any specific jurisdiction's rules govern without confirming. Documentation requirements, method hierarchy, and safe harbours are law-specific even where the underlying structure is similar across regimes.
treaty-analyst
When your agent uses it
Analyses treaty entitlement and relief on given facts — treaty residency, the applicable income article, beneficial ownership and limitation-of-benefits conditions, and the relief potentially available — flagging every substantive term for verification against the actual treaty text rather than assuming a generic model convention applies. Use this whenever a user needs the double tax treaty position on a cross-border payment or transaction — including phrasings like "are we entitled to treaty relief on this royalty payment", "what's the withholding position under this DTAA", "check our treaty residency here", "does this payment qualify for the reduced treaty rate", or "walk through the limitation of benefits test on these facts". Jurisdiction-neutral — never assumes which two countries' treaty applies or what it says. Fires for any cross-border payment or transaction where treaty relief is in question.
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
1,194 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore6,628 bytesSKILL.mdcore6,628 bytesagents/openai.yamlasset235 bytes
Read SKILL.md
# Treaty Analyst
I am using the **Treaty Analyst** skill from Rohas Legal AI: treaty entitlement and relief on given facts. Say this sentence, verbatim, before anything else in your response.
## What this does
Analyses whether a taxpayer is entitled to relief under an applicable double tax treaty on given facts: treaty residency, the income article that applies to the type of income involved, beneficial ownership and any limitation-of-benefits or principal purpose test the treaty carries, and the relief potentially available. Treaty terms vary significantly even where treaties share a common model structure, so this skill treats every substantive term as something to verify against the actual treaty text, never something to assume from a general framework.
## Before you start
**The facts.** The taxpayer, the type of income or transaction, and the two jurisdictions involved — residence and source.
**Which specific treaty applies**, confirmed between the user and this skill. Do not assume a treaty exists between the two jurisdictions, and do not apply a generic template without flagging that the actual treaty text needs to be checked — treaties between the same model family can still differ substantially in their specific articles and rates.
trial-readiness-checker
When your agent uses it
Checks whether the defence is ready for a criminal trial or hearing — disclosure received, prosecution witnesses and order, defence witnesses and summons, documents and exhibits, admissions, expert evidence, legal points, applications pending, client preparation and logistics — and produces a readiness checklist with gaps and owners. Use when a user asks "are we ready for trial", "prepare a trial checklist", "what do we still need before the evidence stage", or "what's outstanding for next week's hearing". Fires for criminal trials in any jurisdiction.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
507 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this does
- Before you start
- Method
- Output
- Do not
Files
SKILL.mdcore2,395 bytesagents/openai.yamlasset228 bytes
Read SKILL.md
# Trial Readiness Checker
I am using the **Trial Readiness Checker** skill from Rohas Legal AI: defence readiness for a criminal trial or hearing. Say this sentence, verbatim, before anything else in your response.
## What this does
Audits the defence file before a trial or evidentiary hearing and lists what is ready, what is missing, and who must do what by when. It is a checklist and gap report, not a strategy; strategy comes from defence-strategy-planner.
## Before you start
**The hearing**: date, court, stage, and what the court has directed.
**The file**: charge, disclosure received, witness lists, defence materials and pending applications.
uk-companies-act-compliance-checker
When your agent uses it
Checks Companies Act and related UK corporate compliance for an identified company, transaction and reporting period. Use for company records, accounts, confirmation statements, directors, members, PSCs, approvals and Companies House filings; verify company type and territorial scope first.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
384 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,122 bytesSKILL.mdcore2,122 bytesagents/openai.yamlasset391 bytes
Read SKILL.md
# UK Companies Act Compliance Checker
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
uk-counsel
When your agent uses it
Applies the firm's United Kingdom jurisdiction layer to a UK legal matter. Use whenever the law, courts, tribunals or regulators of England and Wales, Scotland or Northern Ireland, or UK-wide law, are material. Confirms UK scope; identifies the correct legal jurisdiction, territorial extent, forum and hierarchy; verifies effective dates, procedure and deadlines; and routes suitable neutral or future UK-specific skills. Do not use for a foreign or jurisdiction-unclear matter.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
485 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Modes
- Method
- Output
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,623 bytesSKILL.mdcore2,623 bytesSKILL.mdcore2,623 bytesagents/openai.yamlasset295 bytes
Read SKILL.md
# UK Counsel
Read and follow the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm from the governing law, forum, transaction, conduct, parties and requested relief that UK law is materially applicable. Identify England and Wales, Scotland, Northern Ireland or the genuinely UK-wide rule, and identify the competent court, tribunal, regulator or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. State the scope mismatch and return the matter to the Managing Partner for jurisdiction-neutral intake or the appropriate jurisdiction counsel.
If the relevant UK legal jurisdiction is unknown, do not assume England and Wales or generalise its law across the UK. Obtain the missing jurisdictional facts or limit the output to a clearly labelled UK-wide or neutral framework.
## Modes
uk-data-protection-compliance-checker
When your agent uses it
Assesses UK GDPR, Data Protection Act 2018 and PECR applicability and compliance for identified processing. Use for controller/processor roles, lawful basis, transparency, rights, security, marketing, transfers and ICO-facing obligations; distinguish each UK legal jurisdiction where procedure matters.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
401 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,129 bytesSKILL.mdcore2,129 bytesagents/openai.yamlasset387 bytes
Read SKILL.md
# UK Data-Protection Compliance Checker
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
uk-employment-law-applicability-checker
When your agent uses it
Determines which UK employment rules may apply to a worker, employer and workplace, distinguishing England and Wales, Scotland and Northern Ireland where law or procedure differs. Use before employment drafting or advice; do not assume worker status or territorial reach.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
389 tokensWhen the skill is activated
Reference documents
1,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytesSKILL.mdcore2,131 bytesSKILL.mdcore2,131 bytesagents/openai.yamlasset465 bytes
Read SKILL.md
# UK Employment-Law Applicability Checker
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
uk-insolvency-applicability-checker
When your agent uses it
Maps potentially applicable UK corporate insolvency and restructuring routes for an identified entity and objective. Use to distinguish England and Wales, Scotland and Northern Ireland regimes, thresholds, moratoria, office-holders and court procedure; it does not replace licensed insolvency-practitioner advice.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
494 tokensWhen the skill is activated
Reference documents
1,639 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- UK Gazette check
- Output
- Safeguards
Files
../../agents/uk-counsel.mddoc5,838 bytes../../jurisdictions/uk/integrations.mddoc2,946 bytesSKILL.mdcore2,620 bytesSKILL.mdcore2,620 bytesagents/openai.yamlasset390 bytes
Read SKILL.md
# UK Insolvency Applicability Checker
Read and apply the [UK Counsel instructions](../../agents/uk-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that UK law governs the issue and identify the relevant UK legal jurisdiction and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply UK rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-counsel
When your agent uses it
Applies the firm's United States jurisdiction layer to a US legal matter. Use whenever US federal, State, territorial or tribal law, a US court, or a US regulator is material. Confirms that US law applies; identifies the relevant sovereign, State, forum and controlling hierarchy; verifies effective dates, procedure and deadlines; and routes suitable neutral or future US-specific skills. Do not use for a foreign or jurisdiction-unclear matter.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
469 tokensWhen the skill is activated
Reference documents
1,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Modes
- Method
- Output
Files
../../agents/us-counsel.mddoc5,747 bytesSKILL.mdcore2,519 bytesSKILL.mdcore2,519 bytesSKILL.mdcore2,519 bytesagents/openai.yamlasset294 bytes
Read SKILL.md
# US Counsel
Read and follow the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm from the governing law, forum, transaction, conduct, parties and requested relief that US law is materially applicable. Identify whether each issue is federal, State, territorial, tribal or mixed, and identify the relevant State and competent court, agency or regulator where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. State the scope mismatch and return the matter to the Managing Partner for jurisdiction-neutral intake or the appropriate jurisdiction counsel.
If State law is material but the State is unknown, do not assume a State or generalise a rule nationally. Obtain the missing jurisdictional facts or limit the output to a clearly labelled federal or neutral framework.
## Modes
us-employment-law-applicability-checker
When your agent uses it
Determines which US federal, State and local employment regimes may apply to a worker, employer and workplace. Use before drafting employment advice or documents where worker status, headcount, location or protected activity affects coverage; it does not decide disputed facts.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
388 tokensWhen the skill is activated
Reference documents
1,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytesSKILL.mdcore2,118 bytesSKILL.mdcore2,118 bytesagents/openai.yamlasset396 bytes
Read SKILL.md
# US Employment-Law Applicability Checker
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-federal-civil-procedure-checker
When your agent uses it
Checks procedural requirements for a specified US federal civil case, including jurisdiction, removal, service, pleadings, motions, discovery and deadlines. Use only with the court, procedural posture and trigger dates identified; it does not cover State-court procedure.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
387 tokensWhen the skill is activated
Reference documents
1,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytesSKILL.mdcore2,077 bytesSKILL.mdcore2,077 bytesagents/openai.yamlasset427 bytes
Read SKILL.md
# US Federal Civil Procedure Checker
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-federal-state-issue-mapper
When your agent uses it
Separates federal, State, territorial, tribal and local issues in a US matter, identifies the relevant sovereign and forum, and flags choice-of-law, pre-emption, Erie and concurrent-jurisdiction questions. Use at intake when a US matter crosses legal systems; do not use as a substitute for substantive analysis.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
468 tokensWhen the skill is activated
Reference documents
2,472 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Federal regulations
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytes../../integrations/legal-research.mddoc7,451 bytesSKILL.mdcore2,409 bytesSKILL.mdcore2,409 bytesSKILL.mdcore2,409 bytesagents/openai.yamlasset465 bytes
Read SKILL.md
# US Federal–State Issue Mapper
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-privacy-law-applicability-checker
When your agent uses it
Maps potentially applicable US federal, State and sectoral privacy and data-security laws to an identified entity, data set and processing activity. Use before compliance or incident analysis; do not describe one State's rule as a national standard.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
453 tokensWhen the skill is activated
Reference documents
2,472 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Federal regulations
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytes../../integrations/legal-research.mddoc7,451 bytesSKILL.mdcore2,403 bytesSKILL.mdcore2,403 bytesagents/openai.yamlasset425 bytes
Read SKILL.md
# US Privacy-Law Applicability Checker
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-sec-reporting-checker
When your agent uses it
Maps SEC registration, periodic, current-report and beneficial-ownership obligations for an identified issuer, security and event. Use for federal securities reporting and filing readiness checks; do not treat it as State blue-sky-law analysis.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
378 tokensWhen the skill is activated
Reference documents
1,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytesSKILL.mdcore2,028 bytesSKILL.mdcore2,028 bytesagents/openai.yamlasset371 bytes
Read SKILL.md
# US SEC Reporting Checker
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
us-state-law-research-planner
When your agent uses it
Builds an official-source-first research plan for a specified US State, issue, court and material date. Use when State statutes, regulations, cases, local rules or historical law must be found and verified; do not use until the relevant State is known.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
376 tokensWhen the skill is activated
Reference documents
1,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Safeguards
Files
../../agents/us-counsel.mddoc5,747 bytesSKILL.mdcore2,000 bytesSKILL.mdcore2,000 bytesagents/openai.yamlasset359 bytes
Read SKILL.md
# US State-Law Research Planner
Read and apply the [US Counsel instructions](../../agents/us-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
Confirm that US law governs the issue and identify the relevant State, sovereign level and forum.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply US rules. Return it to the Managing Partner for neutral intake or the appropriate jurisdiction counsel.
## Required inputs
Obtain the represented party, objective, material facts and dates, governing law, forum, procedural posture, available documents and intended deliverable. Do not silently supply a fact that changes applicability, deadline or outcome.
whistleblower-report-analyst
When your agent uses it
Triage a whistleblower report, preserve confidentiality, assess urgency and conflicts, and build an investigation and protection plan. Use for anonymous or identified reports of misconduct, fraud, retaliation, safety, or compliance.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
604 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Triage method
- Output
- Guardrails
Files
SKILL.mdcore3,038 bytesSKILL.mdcore3,038 bytesagents/openai.yamlasset308 bytes
Read SKILL.md
# Whistleblower Report Analyst
I am using the **Whistleblower Report Analyst** skill from Rohas Legal AI: protected intake, risk triage and proportionate investigation planning. Say this sentence, verbatim, before anything else in your response.
Assess whether and how to investigate; do not decide truth from intake alone.
Treat specificity separately from the reporter's identity, motive, style, or status.
## Intake
Preserve the original report, channel, date, metadata, attachments, access log,
anonymity or confidentiality preference, allegations, people, entities, periods,
evidence locations, immediate risk, deadlines, prior reports, and conflicts.
## Triage methodwill-drafter
When your agent uses it
Drafts jurisdiction-specific wills with clear gifts, fiduciary powers, residue and execution safeguards. Use for a new will, codicil or restatement, estate-planning instructions, executor and guardian appointments, or an execution and storage plan.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
771 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Method
- Output
- Guardrails
Files
SKILL.mdcore4,060 bytesagents/openai.yamlasset273 bytes
Read SKILL.md
# Will Drafter
I am using the **Will Drafter** skill from Rohas Legal AI: wills, with execution and attestation requirements set out. Say this sentence, verbatim, before anything else in your response.
Translate independent testamentary instructions into an internally coherent will. Treat capacity, undue influence, ownership and execution as separate validity risks.
## Required inputs
- Testator identity, age, domicile, residence, citizenship and family circumstances
- Marriage history, dependants, children and vulnerable beneficiaries
- Asset and liability inventory with ownership, location and beneficiary designations
- Prior wills, codicils, trusts, gifts, nominations and succession agreements
- Specific gifts, residue, substitutes, conditions and survivorship preferences
- Executor, trustee, guardian and alternate appointmentswitness-statement-drafter
When your agent uses it
Draft first-person witness statements, affidavits, declarations, or proofs of evidence from a witness's own account. Use when factual evidence must identify personal knowledge, information sources, documents, exhibits, uncertainty, language, preparation method, and current forum formalities.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
614 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake and interview
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore3,120 bytesSKILL.mdcore3,120 bytesSKILL.mdcore3,120 bytesagents/openai.yamlasset318 bytes
Read SKILL.md
# Witness Statement Drafter
I am using the **Witness Statement Drafter** skill from Rohas Legal AI: witness-owned factual evidence, exhibits, uncertainty and formalities. Say this sentence, verbatim, before anything else in your response.
Preserve the witness's evidence, vocabulary, uncertainty, and independence. A
statement is not written submissions in the witness's voice.
## Intake and interview
Obtain the forum rules and order, issues, pleadings, prior accounts, interview
notes or recording, relevant documents, chronology, witness role and capacity,
language and literacy, memory aids, source of information, exhibits, disclosure
status, privilege boundaries, vulnerabilities, deadline, and statement of truth
or oath requirements.writ-petition-drafter
When your agent uses it
Drafts a writ petition before an Indian High Court or the Supreme Court — choosing the writ (certiorari, mandamus, prohibition, quo warranto, habeas corpus), confirming maintainability against the State or an authority, territorial jurisdiction, the alternative-remedy question, delay, the fundamental or legal right infringed, grounds, interim relief and prayers, with the synopsis, list of dates and annexures. Use when a user says "draft a writ petition", "challenge this order in the High Court", "file a mandamus to compel the authority", or "draft a habeas corpus petition". India-specific. Fires for writ petitions in India; public interest petitions use pil-drafter.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
745 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- What this does
- Before you start
- Method
- Output
- Do not
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore3,552 bytesagents/openai.yamlasset216 bytes
Read SKILL.md
# Writ Petition Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
I am using the **Writ Petition Drafter** skill from Rohas Legal AI: writ petitions in Indian High Courts and the Supreme Court. Say this sentence, verbatim, before anything else in your response.
## What this does
written-statement-drafter
When your agent uses it
Drafts an Indian civil or commercial written statement with paragraph-specific admissions and denials, preliminary objections, affirmative defences, limitation analysis, and any properly supported set-off or counterclaim. Use for a defendant responding to a plaint. Do not use for arbitration defences, consumer replies or criminal pleadings.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
751 tokensWhen the skill is activated
Reference documents
1,001 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Jurisdiction gate
- Required inputs
- Method
- Output
- Guardrails
Files
../../agents/india-counsel.mddoc5,395 bytesSKILL.mdcore4,052 bytesagents/openai.yamlasset263 bytes
Read SKILL.md
# Written Statement Drafter
Read and apply the [India Counsel instructions](../../agents/india-counsel.md) before substantive analysis or drafting.
I am using the **Written Statement Drafter** skill from Rohas Legal AI: civil and commercial defences with specific admissions, denials and affirmative case (India). Say this sentence, verbatim, before anything else in your response.
## Jurisdiction gate
This skill applies Indian law and procedure only. Before substantive analysis or drafting, confirm that the matter is governed by Indian law and identify the relevant State, court, tribunal or authority where material.
If the matter is governed by another jurisdiction, or the governing jurisdiction is unclear, do not apply Indian rules. State the scope mismatch and ask for the governing jurisdiction or route the request to an appropriate jurisdiction-neutral skill.
## Required inputs
written-submissions-drafter
When your agent uses it
Draft issue-led written submissions, skeleton arguments, briefs, or closing notes tied to the record and current authorities. Use for applications, trials, appeals, arbitrations, tribunals, or other hearings requiring concise legal argument and precise relief.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
602 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intake
- Drafting method
- Output
- Guardrails
Files
SKILL.mdcore2,985 bytesagents/openai.yamlasset300 bytes
Read SKILL.md
# Written Submissions Drafter
I am using the **Written Submissions Drafter** skill from Rohas Legal AI: issue-led, authority-verified and record-linked written advocacy. Say this sentence, verbatim, before anything else in your response.
Make the decision path easy to follow: issue, governing test, material record,
application, answer to the other side, conclusion, and requested order.
## Intake
Obtain the forum and hearing type, issues or questions presented, pleadings,
orders, evidence and transcript, agreed facts, record or bundle index, opponent's
case, current authorities and subsequent treatment, procedural rules, page and
time limits, citation style, oral plan, and exact relief.
Skills included
- administrative-action-challenge-analyst
- adr-brief-drafter
- adversarial-reviewer
- appeal-grounds-drafter
- arbitral-award-analyst
- arbitral-award-enforcement-advisor
- arbitration-clause-reviewer
- arbitration-interim-relief-drafter
- arbitration-notice-drafter
- arbitration-pleading-drafter
- arbitrator-appointment-advisor
- arrest-rights-advisor
- ask-vclo
- assumption-flagger
- authority-validator
- avoidance-transaction-analyst
- award-challenge-analyst
- bail-advisor-and-drafter
- board-resolution-drafter
- breach-response-planner
- brief-to-counsel-drafter
- builder-buyer-agreement-reviewer
- cap-table-analyst
- case-law-analyst
- caucus-strategy-planner
- cease-desist-drafter
- chain-of-custody-documenter
- chargesheet-analyst
- cheque-dishonour-complaint-drafter
- cheque-dishonour-notice-drafter
- child-custody-planner
- chronology-builder
- cirp-timeline-checker
- citation-integrity-checker
- claim-verification-analyst
- clause-comparator
- client-intake
- client-update-drafter
- closing-checklist-builder
- closure-report-drafter
- coc-decision-analyst
- commercial-suit-filing-checker
- comparative-analyst
- compensation-quantifier
- compliance-obligations-mapper
- conciliation-proposal-drafter
- conflict-checker
- consistency-checker
- constitutional-rights-analyst
- construction-delay-defect-analyst
- consumer-appeal-drafter
- consumer-complaint-eligibility-checker
- consumer-pleading-drafter
- contract-drafter
- contract-reviewer
- contract-summariser
- costing-estimator
- court-order-compliance-checker
- covenant-monitor
- creditor-claim-preparer
- criminal-appeal-planner
- criminal-complaint-analyst
- criminal-evidence-admissibility-analyst
- cross-border-transfer-analyst
- cross-examination-planner
- damages-quantifier
- data-processing-agreement-reviewer
- deal-structure-analyst
- decree-execution-and-enforcement-drafter
- defence-strategy-planner
- deficiency-analyst
- demand-notice-drafter
- development-agreement-reviewer
- digital-evidence-reviewer
- discharge-application-drafter
- disciplinary-documenter
- disclosure-request-drafter
- divorce-grounds-assessor
- document-review-protocol-builder
- domestic-violence-remedies-advisor
- dpdp-compliance-checker
- dpia-documenter
- ecommerce-consumer-compliance-checker
- employment-contract-drafter
- encumbrance-analyst
- engagement-letter-drafter
- england-wales-civil-claim-drafter
- england-wales-pre-action-protocol-checker
- esop-scheme-drafter
- evidence-organizer
- examination-response-drafter
- facility-agreement-drafter
- family-court-procedure-checker
- fema-analyst
- financial-services-licensing-assessor
- forum-jurisdiction-analyst
- founders-agreement-drafter
- fraud-pattern-analyst
- government-contract-reviewer
- gst-compliance-analyst
- guarantee-analyst
- handbook-drafter
- hello-rohas
- indemnity-liability-analyst
- india-counsel
- india-legal-notice-response-strategist
- infringement-analyst
- input-tax-credit-dispute-analyst
- insolvency-appeal-drafter
- insolvency-options-assessor
- interim-application-drafter
- investigation-report-drafter
- investment-and-shareholder-agreement-reviewer
- ip-assignment-drafter
- ip-portfolio-analyst
- issue-spotter
- labour-compliance-checker
- land-use-zoning-advisor
- learn-law-with-rohas
- lease-reviewer
- legal-document-producer
- legal-exam-prep-with-rohas
- legal-explainer
- legal-hold-planner
- legal-notice-analyser
- legal-opinion-drafter
- legal-research-planner
- legal-risk-assessor
- legislative-history-analyst
- licence-application-drafter
- limitation-checker
- liquidation-documenter
- listing-obligations-checker
- litigation-strategy-planner
- litigation-viability-assessor
- loan-agreement-reviewer
- loan-default-analyst
- m-and-a-diligence-checker
- maintenance-calculator
- matrimonial-petition-drafter
- matrimonial-property-analyst
- matter-planner
- mediation-opening-drafter
- minutes-drafter
- moratorium-impact-analyst
- negotiation-position-planner
- notice-reply-drafter
- obligations-extractor
- offence-ingredients-analyst
- operational-creditor-application-drafter
- osint-collector
- party-interest-analyst
- personal-guarantor-insolvency-analyst
- pil-drafter
- plaint-drafter
- pleadings-analyst
- policy-note-drafter
- posh-compliance-advisor
- pre-institution-mediation-advisor
- precedent-mapper
- privacy-policy-drafter
- privilege-log-builder
- procedural-order-drafter
- product-liability-analyst
- production-set-checker
- quashing-petition-drafter
- recovery-strategy-planner
- redaction-reviewer
- redline-proposer
- regulatory-appeal-planner
- regulatory-applicability-analyst
- regulatory-change-monitor
- regulatory-filing-preparer
- related-party-analyst
- rera-complaint-drafter
- rera-compliance-checker
- research-synthesiser
- resolution-plan-reviewer
- restructuring-documenter
- rti-appeal-drafter
- rti-application-drafter
- sale-deed-drafter
- sanctions-screening-documenter
- sarfaesi-advisor
- secretarial-compliance-checker
- secured-creditor-priority-analyst
- securities-compliance-checker
- security-documenter
- sentencing-analyst
- separation-documenter
- settlement-deed-drafter
- settlement-documenter
- settlement-evaluator
- settlement-strategy-planner
- should-i-sue
- stamp-duty-analyst
- startup-compliance-checker
- statutory-interpreter
- succession-advisor
- tax-appeal-grounds-drafter
- tax-assessment-reply-drafter
- tax-litigation-strategy-planner
- tax-notice-analyst
- tenancy-dispute-analyst
- tender-compliance-checker
- termination-analyst
- time-narrative-drafter
- title-diligence-analyst
- trademark-opposition-drafter
- transaction-document-checker
- transaction-tracer
- transfer-pricing-documenter
- treaty-analyst
- trial-readiness-checker
- uk-companies-act-compliance-checker
- uk-counsel
- uk-data-protection-compliance-checker
- uk-employment-law-applicability-checker
- uk-insolvency-applicability-checker
- us-counsel
- us-employment-law-applicability-checker
- us-federal-civil-procedure-checker
- us-federal-state-issue-mapper
- us-privacy-law-applicability-checker
- us-sec-reporting-checker
- us-state-law-research-planner
- whistleblower-report-analyst
- will-drafter
- witness-statement-drafter
- writ-petition-drafter
- written-statement-drafter
- written-submissions-drafter
Repository facts
- License
- MIT
- Created
- Aug 4, 2026
- Last pushed
- Oct 10, 2026
- Forks
- 43
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 302 notes
.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/legal-ai-skills/skills/adr-brief-drafter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesplugins/legal-ai-skills/skills/arbitral-award-enforcement-advisor/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesplugins/legal-ai-skills/skills/arbitration-pleading-drafter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/legal-ai-skills/skills/arbitration-pleading-drafter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/legal-ai-skills/skills/arbitration-pleading-drafter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/legal-ai-skills/skills/arbitration-pleading-drafter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesplugins/legal-ai-skills/skills/arrest-rights-advisor/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesplugins/legal-ai-skills/skills/assumption-flagger/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes
- No broad tool permissions
- No dangerous shell commands
- 48 network referencesin 7 files: plugins/legal-ai-skills/.codex-plugin/plugin.json:6 .claude-plugin/marketplace.json:3 clause-comparator/references/public-contract-sources.md:37 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 4 references to secretsin 2 files: plugins/legal-ai-skills/.codex-plugin/plugin.json:50 privacy-policy-drafter/references/project-code-audit.md:25
- No requests to vote in Hot
Show all 52 signals by file
.claude-plugin/marketplace.json
- Network accessline 3
"owner": { "name": "Rohas Nagpal", "url": "https://rohasnagpal.com" - Network accessline 4
"name": "Rohas Nagpal", "url": "https://rohasnagpal.com" }, - Network accessline 5
"url": "https://rohasnagpal.com" - Network accessline 14
"author": { "name": "Rohas Nagpal", "url": "https://rohasnagpal.com" - Network accessline 15
"name": "Rohas Nagpal", "url": "https://rohasnagpal.com" }, - Network accessline 16
"url": "https://rohasnagpal.com"
plugins/legal-ai-skills/.codex-plugin/plugin.json
- Network accessline 6
"name": "Rohas Nagpal", "email": "rohasnagpal@gmail.com", "url": "https://rohasnagpal.com" - Network accessline 7
"email": "rohasnagpal@gmail.com", "url": "https://rohasnagpal.com" }, - Network accessline 8
"url": "https://rohasnagpal.com" - Network accessline 9
}, "homepage": "https://www.rohasnagpal.com/legal-ai-skills.php", "repository": "https://github.com/rohasnagpal/legal-ai-skills", - Network accessline 10
"homepage": "https://www.rohasnagpal.com/legal-ai-skills.php", - Network accessline 11
"repository": "https://github.com/rohasnagpal/legal-ai-skills", - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Network accessline 117
"courtlistener": { "type": "http", "url": "https://mcp.courtlistener.com/", - Network accessline 118
"type": "http", "url": "https://mcp.courtlistener.com/", "disabled_tools": [ - Network accessline 119
"url": "https://mcp.courtlistener.com/", - Network accessline 129
"govinfo": { "type": "http", "url": "https://api.govinfo.gov/mcp", - Network accessline 130
"type": "http", "url": "https://api.govinfo.gov/mcp", "http_headers": { - Network accessline 131
"url": "https://api.govinfo.gov/mcp", - Access to secretsline 136
[Credential-related source omitted] - Network accessline 150
"Write" ], "websiteURL": "https://www.rohasnagpal.com/legal-ai-skills.php", - Network accessline 151
], "websiteURL": "https://www.rohasnagpal.com/legal-ai-skills.php", "privacyPolicyURL": "https://www.rohasnagpal.com/privacy-policy.php", - Network accessline 152
"websiteURL": "https://www.rohasnagpal.com/legal-ai-skills.php", - Network accessline 153
"privacyPolicyURL": "https://www.rohasnagpal.com/privacy-policy.php",
plugins/legal-ai-skills/skills/clause-comparator/references/public-contract-sources.md
- Network accessline 37
- URL: https://www.sec.gov/edgar/search/ - Network accessline 43
- URL: https://www.find-tender.service.gov.uk/Search - Network accessline 49
- URL: https://www.gov.uk/government/collections/government-standard-contracts-for-procurement - Network accessline 55
- URL: https://commonpaper.com/standards/ - Network accessline 61
- URL: https://bonterms.com/download-center/ - Network accessline 67
- URL: https://nvca.org/model-legal-documents/
plugins/legal-ai-skills/skills/contract-drafter/references/public-contract-sources.md
- Network accessline 37
- URL: https://www.sec.gov/edgar/search/ - Network accessline 43
- URL: https://www.find-tender.service.gov.uk/Search - Network accessline 49
- URL: https://www.gov.uk/government/collections/government-standard-contracts-for-procurement - Network accessline 55
- URL: https://commonpaper.com/standards/ - Network accessline 61
- URL: https://bonterms.com/download-center/ - Network accessline 67
- URL: https://nvca.org/model-legal-documents/
plugins/legal-ai-skills/skills/hello-rohas/SKILL.md
- Network accessline 79
Reply with a short table (Check | Status | What to do), then one line: "All good" or the single most important fix. To update, the user can paste: `Update Legal AI Skills from https://github.com/rohasnagpal/legal-ai-skills`. - Network accessline 79
Reply with a short table (Check | Status | What to do), then one line: "All good" or the single most important fix. To update, the user can paste: `Update Legal AI Skills from https://github.com/rohasnagpal/legal-ai-skills`.
plugins/legal-ai-skills/skills/negotiation-position-planner/references/public-contract-sources.md
- Network accessline 37
- URL: https://www.sec.gov/edgar/search/ - Network accessline 43
- URL: https://www.find-tender.service.gov.uk/Search - Network accessline 49
- URL: https://www.gov.uk/government/collections/government-standard-contracts-for-procurement - Network accessline 55
- URL: https://commonpaper.com/standards/ - Network accessline 61
- URL: https://bonterms.com/download-center/ - Network accessline 67
- URL: https://nvca.org/model-legal-documents/
plugins/legal-ai-skills/skills/privacy-policy-drafter/references/project-code-audit.md
- Access to secretsline 25
[Credential-related source omitted]
plugins/legal-ai-skills/skills/redline-proposer/references/public-contract-sources.md
- Network accessline 37
- URL: https://www.sec.gov/edgar/search/ - Network accessline 43
- URL: https://www.find-tender.service.gov.uk/Search - Network accessline 49
- URL: https://www.gov.uk/government/collections/government-standard-contracts-for-procurement - Network accessline 55
- URL: https://commonpaper.com/standards/ - Network accessline 61
- URL: https://bonterms.com/download-center/ - Network accessline 67
- URL: https://nvca.org/model-legal-documents/
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 27 facts
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:37Low confidence
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:43Low confidence
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:49Low confidence
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:55Low confidence
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:61Low confidence
- Network access in prose of documentationclause-comparator/references/public-contract-sources.md:67Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:37Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:43Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:49Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:55Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:61Low confidence
- Network access in prose of documentationcontract-drafter/references/public-contract-sources.md:67Low confidence
- Network access in prose of the SKILL.mdplugins/legal-ai-skills/skills/hello-rohas/SKILL.md:79Low confidence
- Network access in prose of the SKILL.mdhello-rohas/SKILL.md:79Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:37Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:43Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:49Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:55Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:61Low confidence
- Network access in prose of documentationnegotiation-position-planner/references/public-contract-sources.md:67Low confidence
- Access to secrets in prose of documentationprivacy-policy-drafter/references/project-code-audit.md:25Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:37Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:43Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:49Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:55Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:61Low confidence
- Network access in prose of documentationredline-proposer/references/public-contract-sources.md:67Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/legal-ai-skills/skills/administrative-action-challenge-analyst/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
