Individual skill
ma-deal-workbench-json
Prepare M&A deal-workbench legal and business analysis packages as strict JSON. Use when a task asks counsel to review buyer or seller M&A deal terms, playbooks, policies, consents, regulatory status, cap tables, employees, material contracts, risk estimates, benchmarks, notes, or diligence findings and return a structured issue register, deviation matrix, closing package, committee escalation, or transition review conforming to a provided JSON template.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_020/self/self_attempt_01/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
- productivity Derived category
- productivity-notes 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
# M&A Deal Workbench JSON
## Core Workflow
1. Read the user prompt, every file under the task's `input/payloads/`, and any environment access file supplied with the task before querying data or drafting an answer.
2. Use only the workbench base URL, query token, and endpoints authorized by the environment access file. Prefer the exact API routes named in the prompt, then use listed collection endpoints or read-only SQL only for cross-table checks and reconciliation.
3. Identify the deal ID, client side, transaction type, applicable playbook or policy, requested output package, units, rounding rules, allowed enums, required field names, ordering rules, and stable IDs from the prompt and payload templates.
4. Gather the complete evidence set needed for the requested package: deal record, current draft terms, playbook rules, policy thresholds, benchmarks, risk estimates, consents, employees, material contracts, regulatory records, diligence findings, cap table, documents, and notes as applicable.
5. Build an evidence map before writing JSON. Track stable source IDs for draft terms, consents, contracts, employees, holders, findings, benchmarks, estimates, notes, and policy or playbook rules. Use empty source arrays only when the issue is a genuinely missing required draft term.
6. Compare the current draft against the client's playbook or policy from the client's perspective. Treat missing affirmative protections as issues when the playbook, policy, or deal facts require them.
7. Include only the issue universe requested by the prompt and template. Exclude stale records, similarly named deals, in-policy distractors, and non-requested categories unless the template specifically asks to list excluded items.
8. Populate the exact JSON shape requested by the payload template. Use template keys, enums, stable issue IDs, redline IDs, final-position IDs, and ordering instructions exactly. Return valid JSON only, with no prose outside the object.
## Comparison Rules