Menu

Individual skill

ma-deal-workbench-review

0upvotes

Produces a structured JSON deliverable for an M&A deal-review task driven by the running deal workbench — asset/stock purchase agreement issue registers, SPA closing & economics packages, carveout transition reviews, M&A committee escalations, and SPA deviation matrices. Use when a task casts you as buyer-side or seller-side counsel, points you at a deal workbench reachable over the network, asks you to compare draft terms against a playbook or committee policy, classify issues by status/risk, quantify dollar exposure from the purchase price, and return only JSON conforming to a shipped answer_template.json. Reads base URL and read-only SQL token from environment_access.md and never imports another deal's schema, IDs, or values.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_020/fewshot/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 Review

Produce a structured JSON deliverable for an M&A deal-review task by querying the running deal workbench, comparing the current draft against the applicable playbook or committee policy, and emitting JSON that conforms to the task's own `answer_template.json`.

## Read these first, in order
1. **The task prompt** — gives the `deal_id`, `client_side` (buyer/seller), deliverable type and required coverage, the playbook/policy id to compare against, and the unit/precision rules.
2. **`input/payloads/answer_template.json`** — the authoritative schema for THIS task: required fields, allowed enums, stable ID lists, ordering rules, and units. Templates differ across tasks; do not carry another task's schema forward.
3. **`environment_access.md`** — use it **only** to reach the running environment over the network (base URL, read-only SQL token, allowed-endpoint list). It is not a source of deal data or answer values.

## Workflow
1. **Extract task parameters** from the prompt (deal_id, client_side, deliverable, playbook/policy id, precision rules).
2. **Reach the workbench** — read `environment_access.md`; substitute its base URL for every `<TASK_ENV_BASE_URL>` in the prompt. See `references/workbench_access.md`.
3. **Pull records by exact deal_id** — deal record, draft terms, playbook rules (and/or policy thresholds), risk estimates, employees, consents, material contracts, regulatory, benchmarks, diligence findings, cap table, documents, notes. Pull what the deliverable needs. Do **not** assume records from a similarly named project apply.
4. **Classify each relevant term** against the playbook/policy — `issue_status`, `risk_rating`, `recommended_action` (and `redline_action` where the template has redlines). Derive allowed enum values from THIS task's template. See `references/analysis_method.md`.
Back to top