Individual skill
ma-deal-workbench-analysis
Produce structured M&A counsel deliverables (seller issue registers, buyer SPA closing/economics packages, committee escalation memos, carveout transition reviews, buyer deviation matrices) from a deal workbench. Use when a task casts you as buyer or seller counsel reviewing an M&A deal draft against a playbook or committee policy and requires a JSON answer conforming to a provided answer template.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_020/reflect-3/reflect-3_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
- Yes
- 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
- engineering 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
SKILL.mdcore · 11,076 bytesreference/classification_and_quantification.mddoc · 9,481 bytesreference/workbench_data_model.mddoc · 6,810 bytes
Read excerpt
# M&A Deal Workbench Analysis
You are acting as buyer- or seller-side counsel for an M&A transaction. A deal workbench holds the deal record, the current draft terms, the controlling framework (a counsel playbook or an M&A Committee policy), and supporting diligence data. Your job is to compare the draft against the framework, quantify the economics, classify every deviation, and return one JSON object that conforms exactly to the task's `answer_template.json`.
This skill is the **entry method**. It is transferable across deal types (asset purchase, stock purchase, carveout, public-company merger) and across client sides. It does not contain deal-specific values, endpoint specifics, or any step that calls a judge — at test time you only gather data, analyze, and return the JSON.
## When to use
Use this skill when the task:
- names you as counsel for a deal (buyer or seller) with a deal ID like `PRJ_<NAME>`;
- points you at a deal workbench and (optionally) a read-only SQL endpoint;
- gives you an `answer_template.json` whose top-level shape is one of: an issue register, an economics/closing package, an escalation memo, a transition review, or a position/deviation matrix;
- asks you to compare draft terms to a playbook or policy and return "only JSON".