Individual skill
ma-deal-workbench-json
Solve M&A deal workbench tasks that require strict JSON outputs from deal API records, playbook or policy comparisons, source IDs, and legal/economic calculations.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/naive/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
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
Use this skill when a prompt asks you to prepare an M&A issue register, deviation matrix, committee escalation package, closing package, transition review, or similar structured JSON output from a running deal workbench.
## Core Workflow
1. Read the user prompt and `input/payloads/answer_template.json` before querying data.
2. Extract the deal ID, client side, transaction type, requested package, applicable playbook or policy ID if named, required units, rounding rules, enum values, sorting rules, and required output shape.
3. Gather records from the workbench for only the requested deal. Start with the deal record, then fetch the endpoints the prompt names or implies: terms, playbook or policy rules, risk estimates, employees, consents, material contracts, regulatory, benchmarks, notes, diligence findings, cap table, documents, and deal-specific metadata.
4. If the prompt permits read-only SQL, use `POST /api/query` with token `deal-workbench-readonly` only for cross-table checks or to locate records that are not obvious from the REST endpoints. Do not use SQL to infer evaluator internals.
5. Build an evidence table keyed by stable source IDs: draft term IDs, consent IDs, material contract IDs, employee IDs, risk estimate IDs, benchmark IDs, document IDs, and regulatory IDs.
6. Compare current draft positions against the client playbook or committee policy. Treat absent required protections as issues when the playbook, policy, or surrounding deal facts show the provision is needed.
7. Construct the answer from the template, using exact field names and enum strings. Return valid JSON only, with no explanatory prose.
