Individual skill

ma-deal-workbench

Use this skill for M&A deal workbench tasks that ask counsel to prepare structured JSON issue registers, closing or economics packages, committee escalation memos, transition reviews, SPA or APA deviation matrices, or playbook/policy comparisons from deal APIs. Trigger whenever the prompt mentions a deal ID, buyer-side or seller-side counsel, APA, SPA, M&A Committee, consents, HSR, cap tables, material contracts, risk estimates, benchmarks, or an answer_template JSON.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/cc/fewshot_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 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.

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 Structured JSON

Use this skill when the user asks for a legal deal-workbench analysis and final output must be strict JSON. The recurring task is to gather workbench records for one deal, compare current draft terms against the applicable playbook or policy, compute derived economics, and emit exactly the schema in the provided answer template.

## Operating Rules

- Stay on the deal ID named in the prompt. Do not use records from similarly named projects or unrelated deals.
- Read `input/payloads/answer_template.json` before drafting the answer. Treat it as the output contract: field names, nesting, enums, ordering instructions, rounding, and nullability come from the template.
- Use current workbench records as source of truth. Notes, benchmarks, risk estimates, diligence findings, consents, and material contracts can explain or quantify an issue, but source term IDs should come from current draft terms unless the template asks for other IDs.
- Treat missing draft language as an issue when the applicable playbook, policy, prompt, or template requires an affirmative provision.
- Return only valid JSON. Do not include markdown, citations outside JSON, or explanatory prose.

## Collect Sources
Back to top