Individual skill
ma-workbench-json
Use this skill for M&A deal workbench tasks that require a strict JSON answer from a running TASK_ENV_BASE_URL, answer_template.json, deal IDs, draft terms, playbooks, policy thresholds, consents, employees, material contracts, benchmarks, risk estimates, diligence findings, documents, or notes. Use it for counsel-style issue registers, closing/economics packages, committee escalation packages, carveout transition reviews, and SPA deviation matrices, even when the user only says to review a project or produce a deal package.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/cc/fewshot_attempt_02/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
- 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
SKILL.mdcore · 4,677 bytesSKILL.mdcore · 4,677 bytesSKILL.mdcore · 4,677 bytesSKILL.mdcore · 4,677 bytesreferences/analysis_patterns.mddoc · 8,839 bytesscripts/check_json_shape.pyruns · 4,623 bytesscripts/fetch_workbench.pyruns · 4,664 bytes
Read excerpt
# M&A Workbench JSON
Produce a schema-conforming JSON answer from the M&A workbench. The hard part is not prose drafting; it is collecting the right deal-scoped records, comparing draft terms to the applicable playbook or policy, doing the arithmetic consistently, and preserving the requested output shape.
## Required Workflow
1. Read the user prompt and every file under `input/payloads/`, especially `answer_template.json`.
2. Extract the exact deal ID, client side, required package type, output ordering rules, numeric precision rules, and any named playbook or policy.
3. Resolve `<TASK_ENV_BASE_URL>` from the prompt, `TASK_ENV_BASE_URL`, `WORKBENCH_BASE_URL`, or a local `environment_access.md`.
4. Fetch the workbench data for the exact deal ID. Do not use similarly named projects or records from other deals.
5. Read `references/analysis_patterns.md` before classifying issues or calculating totals.
6. Draft the answer directly against the template shape. Treat template metadata sections as instructions unless they are actual required answer fields.
7. Validate the JSON structure and arithmetic before final response. Return only valid JSON, with no explanatory prose.
