Menu

Individual skill

ma-deal-workbench

0upvotes

Analyze M&A deal workbench records for buyer-side or seller-side APA, SPA, merger agreement, transition, closing readiness, committee escalation, and deviation-matrix tasks. Use when a prompt provides a TASK_ENV_BASE_URL or deal APIs with draft terms, playbooks or policies, consents, regulatory facts, employees, cap tables, material contracts, diligence findings, risk estimates, benchmarks, documents, or notes and requires exact schema-conformant JSON.

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

# M&A Deal Workbench

## Core Rule

Produce the requested JSON from the current task's deal workbench records and answer template only. Do not reuse values from prior examples, train records, similarly named deals, or memory. Return no prose outside the JSON.

Read `references/reasoning-rules.md` before analyzing any substantive deal task. Use `scripts/workbench_snapshot.py` when a quick API snapshot would reduce missed records.

## One-Pass Workflow

1. Read the prompt and `input/payloads/answer_template.json` first. Capture the deal ID, client side, agreement type, playbook or policy ID, output sections, required units, enum values, sorting instructions, and whether in-policy items should be included or excluded.
2. Resolve `<TASK_ENV_BASE_URL>` from the task environment or prompt. Fetch every endpoint listed in the prompt, then fetch common supporting endpoints when relevant: deal record, terms, playbook or policy rules, risk estimates, employees, consents, regulatory, benchmarks, notes, cap table, material contracts, diligence findings, and documents.
3. Build a source map keyed by stable workbench IDs. Separate current draft terms from stale terms, superseded notes, non-committee distractors, notice-only consents, and records for other deals.
4. Compare current draft terms and draft silence against the side-specific playbook or committee policy. Treat absent protective terms as issues when the prompt, playbook, or surrounding deal facts require an affirmative provision.
Back to top