Menu

Individual skill

ma-deal-workbench-json

0upvotes

Use for M&A deal workbench tasks that ask counsel to review APA, SPA, merger, transition, closing, economics, policy, or committee issues and return strict JSON from an answer template. Covers fetching deal APIs, comparing draft terms against buyer or seller playbooks and committee policies, identifying missing required provisions, calculating dollar and percentage metrics, classifying risks and closing blockers, and emitting schema-conformant JSON with stable source IDs.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/deepagents/fewshot_attempt_03/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

# M&A Deal Workbench JSON

## Core Workflow

1. Read the prompt and answer template before fetching records. Extract the `deal_id`, client side or committee role, required playbook or policy if named, required endpoints, units, enum values, output ordering, and any explicit inclusion or exclusion rule.
2. Gather workbench data for the exact `deal_id`. Use the API routes in the prompt first, then fetch adjacent available routes for the same deal when the requested JSON needs them: terms, playbook rules, policy thresholds, benchmarks, risk estimates, cap table, consents, employees, material contracts, regulatory, diligence findings, documents, and notes.
3. Compare only current applicable draft terms against the controlling buyer/seller playbook or committee policy. Treat draft silence as an issue only when the playbook, policy, deal facts, regulatory facts, document record, or notes show an affirmative provision is required.
4. Fill every required field from the template using stable IDs from the workbench. Use an empty `source_term_ids` array for missing terms. Do not invent IDs; create synthetic IDs only when the template or prompt clearly allows them for regulatory or aggregate items.
5. Return only valid JSON. No commentary, markdown, or citations outside the object.

Use [references/workbench-workflow.md](references/workbench-workflow.md) when the task involves legal issue classification, monetary calculations, closing blocker selection, policy escalation, or aggregate metrics.

## Data Collection
Back to top