Menu

Individual skill

ma-deal-workbench-analysis

0upvotes

Produce a structured JSON analysis (issue register, deviation matrix, committee memo, or closing package) for an M&A deal on the deal workbench API. Use when a task names a deal_id (e.g. PRJ_XXX), states a client side (buyer/seller), and points at a per-task answer_template.json describing the required JSON shape. Covers gathering the deal record, draft terms, playbook/policy rules, consents, material contracts, employees, regulatory, benchmarks, risk estimates, diligence findings, and notes; comparing the draft against the applicable playbook or committee policy; quantifying dollar/percent/month values; and returning only conforming JSON.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_020/reflect-3/reflect-3_attempt_02/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 Analysis

## What this skill does

Deal-workbench tasks give you a **deal_id**, a **client side** (buyer or seller), and a **per-task answer template** (`input/payloads/answer_template.json`). Your job is to query the running M&A workbench for that one deal, analyze the draft deal terms against the applicable **playbook** or **committee policy**, quantify every dollar/percent/month value, and return **one JSON object** that conforms exactly to the template. Return only JSON — no narrative.

## Entry checklist (do these in order)

1. **Read the task prompt and the answer template together.** The template defines every required field, every allowed enum, and every stable ID list. Treat it as a strict schema — do not add fields, do not invent enum values, do not rename keys. The template's prose fields (e.g. `"string"`, `"stable holder name from cap table"`) are rubrics telling you what kind of value to put there.
2. **Confirm the exact `deal_id`** from the prompt and use **only that deal**. The workbench contains many deals with similar names (e.g. "Project Juniper" vs "Project Junia", "Project Meridian" vs "Project Meridian North"). Similarly-named projects do **not** apply. Never mix data across deal_ids even when fields look identical.
3. **Confirm the client side and which reference the prompt tells you to compare against**: a **playbook** (`PB_SELLER_A` or `PB_BUYER_A`) or a **committee policy** (`POL_MA_2025_A` / `POL_MA_2025_B`). The comparison basis determines every "in policy / out of policy / missing / exceeds / below" classification.
4. **Gather all deal resources** before classifying anything (route map below). An issue is only "missing required term" if the surrounding deal data shows the term is needed; absent terms are not automatically issues.
5. **Quantify before classifying.** Compute the dollar/percent/month numbers first, then derive status, risk, and recommendation from the numbers + playbook/policy thresholds.
Back to top