Menu

Individual skill

deal-workbench-ma-json

0upvotes

Solve M&A deal workbench tasks that require a strict JSON answer from a live task environment. Use when the prompt asks counsel to review a deal, APA/SPA terms, closing readiness, committee escalations, transition issues, consents, regulatory status, employee matters, or playbook/policy deviations using TASK_ENV_BASE_URL and an answer_template.json.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/opencode/fewshot_attempt_01/SKILL.md

Read pinned source

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.

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

# Deal Workbench M&A JSON Solver

Use this skill to produce strict JSON answers for legal deal-workbench tasks. The task normally provides a prompt, an `input/payloads/answer_template.json`, and a `<TASK_ENV_BASE_URL>` placeholder for a running M&A workbench.

## Core Workflow

1. Read the user prompt and the answer template before calling the workbench.
2. Identify the deal ID, client side, transaction type, required playbook or policy, requested scope, units, rounding rules, ordering rules, and enum values.
3. Replace `<TASK_ENV_BASE_URL>` with the environment base URL from the task. If the prompt does not give it directly, use the staged environment access file for the base URL.
4. Fetch the complete deal record and all relevant endpoint families. Use `scripts/fetch_workbench.py` when useful.
5. Build a source map keyed by stable IDs: terms, playbook rules, policy thresholds, risk estimates, consents, employees, material contracts, regulatory records, diligence findings, benchmarks, documents, notes, and cap table entries.
6. Compare current draft terms against the applicable buyer, seller, or committee position. Treat missing affirmative protections as issues when the playbook, policy, or surrounding deal facts show they are needed.
7. Populate the answer template exactly. Preserve top-level keys, nested structures, enum spelling, stable IDs, ordering requirements, numeric units, and `null` where a field is not applicable or not supported.
8. Validate that the final response is valid JSON only. Use `scripts/check_answer.py` for a quick structural check against the template.
Back to top