Individual skill
ma-deal-workbench
Work with the M&A deal workbench API to produce structured deal-analysis deliverables for M&A transactions. Use when the task requires gathering deal records, draft terms, playbook rules, policy thresholds, and supporting data (consents, employees, regulatory, risk estimates, benchmarks, material contracts, diligence findings) from the workbench and producing a structured JSON deliverable that compares draft positions against playbook or policy requirements. Triggers on tasks involving SPA/APA issue registers, closing packages, committee escalation memos, transition reviews, deviation matrices, or any M&A deal-review output that references the workbench API.
experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_020/fewshot/deepagents/fewshot_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
- data 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 · 3,881 bytesSKILL.mdcore · 3,881 bytesreferences/api_endpoints.mddoc · 3,412 bytesreferences/comparison_methodology.mddoc · 6,274 bytesreferences/output_conventions.mddoc · 3,576 bytes
Read excerpt
# M&A Deal Workbench
Use the running M&A deal workbench to gather deal records, compare draft terms against playbook rules or policy thresholds, and produce structured JSON deliverables.
## Core Workflow
1. **Read the answer template** — The task provides an `answer_template.json` under `input/payloads/`. Parse it first. Every enum, field shape, and required output structure is defined there.
2. **Fetch the deal record** — `GET /api/deals/<deal_id>` gives headline purchase price, parties, structure, and signing date.
3. **Fetch the draft terms** — `GET /api/deals/<deal_id>/terms` gives every current draft term with `term_id`, `clause_ref`, `category`, and values.
4. **Fetch the governing rules** — `GET /api/playbooks/<playbook_id>/rules` for playbook positions or `GET /api/policies/<policy_id>/thresholds` for policy cutoffs.
5. **Fetch supporting records** — As the task requires: consents, employees, regulatory, risk estimates, benchmarks, material contracts, diligence findings, cap table, documents, notes.
6. **Compare draft against rules** — See [comparison_methodology.md](references/comparison_methodology.md) for classification.
7. **Compute numeric values** — See [output_conventions.md](references/output_conventions.md) for currency, percent, month, and delta rules.
8. **Produce JSON** — Return only the JSON object conforming to the answer template. No markdown fences, no prose outside the JSON.