Individual skill
ma-deal-workbench-review
Analyze M&A deal-workbench records and produce strict JSON issue registers, deviation matrices, closing packages, committee escalations, or transition reviews for APA, SPA, merger, and carveout deal tasks. Use when a prompt asks Codex to compare draft transaction terms against buyer/seller playbooks or committee policies, quantify purchase-price-based positions, classify consents/regulatory/employee/material-contract blockers, allocate consideration, or summarize deal risk using a provided answer template.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_020/reflect-3/reflect-3_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
- 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 Review
## Core Workflow
1. Read the user prompt and answer template before querying data. Treat the template as the controlling schema for keys, enums, units, ordering, stable issue IDs, and whether to include metadata fields.
2. Gather every deal record relevant to the prompt: deal summary, draft terms, playbook rules or policy thresholds, risk estimates, employees, consents, material contracts, regulatory facts, diligence findings, cap table, benchmarks, documents, and notes.
3. Use stable IDs exactly as supplied by records or the template. Use empty arrays for missing draft terms when the template asks for source term IDs.
4. Compare only current draft terms unless the task explicitly asks for stale or historical terms. Exclude stale, in-policy, non-committee, or non-task distractors.
5. Treat a missing draft term as an issue when the playbook, policy, prompt, or surrounding deal facts require an affirmative provision.
6. Return only valid JSON matching the answer template. Do not include narrative outside the JSON.
## Comparisons
- For buyer-side positions, classify seller drafts below buyer fallback as `draft_below_playbook`; classify absent required protections as `missing_required_term`; classify accepted fallback terms as `in_policy`.