Individual skill
deal-workbench-ma-json
Prepare strict JSON legal-analysis outputs from an M&A deal workbench. Use when a task asks counsel to review buyer-side or seller-side draft M&A terms, compare them against a playbook or M&A committee policy, quantify economics, closing, consent, employee, regulatory, indemnity, escrow, transition, or committee risks, and return only JSON conforming to a provided answer template.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_020/self/self_attempt_03/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 121
- Repository last updated
- Oct 29, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- legal Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Read excerpt
# Deal Workbench M&A JSON
## Workflow
1. Read the user prompt and the provided answer template before querying data. Extract the deal ID, client side, transaction type, requested work product, required units, enum values, stable issue/redline IDs, ordering rules, and whether the comparison source is a playbook or committee policy.
2. Use only the base URL, token, and endpoints authorized by the task environment. Start with `GET /api/deals/<deal_id>`, then follow the requested records through the deal links or documented routes.
3. Fetch all record families that could affect requested fields: `/terms`, `/benchmarks`, `/risk-estimates`, `/consents`, `/employees`, `/material-contracts`, `/regulatory`, `/diligence-findings`, `/cap-table`, `/documents`, and `/notes`. Fetch `/api/playbooks/<playbook_id>/rules` for playbook comparisons and `/api/policies/<policy_id>/thresholds` for committee/policy comparisons.
[Credential-related source omitted]
5. Work only on the exact `deal_id`. Do not borrow facts from similarly named projects, related examples, or other deals.
6. Build the JSON directly from the answer template. Preserve field names, nesting, types, enums, and requested ordering exactly. Return no prose outside the JSON.
## Source Handling
- Treat `deals` as the authoritative source for client names, counterparty, target, signing/meeting dates, currency, headline value, upfront cash, stock value, milestone value, playbook ID, policy ID, status, and transaction type.