Menu

Individual skill

mna-workbench-json

0upvotes

Prepare strict JSON outputs for M&A deal-workbench tasks. Use when a user asks for seller or buyer APA/SPA issue registers, deviation matrices, closing/economics packages, committee escalation memos, transition reviews, or any structured M&A analysis that must compare deal-workbench records against playbooks, policies, benchmarks, risk estimates, consents, employees, cap tables, regulatory records, diligence findings, notes, or draft terms.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_020/fewshot/opencode/fewshot_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 Workbench JSON

Use this skill to answer deal-workbench tasks that require a JSON-only legal or business output. The core job is to collect current deal evidence, compare draft terms against the applicable playbook or policy, calculate normalized amounts, and fill the provided answer template exactly.

Before deriving issues, read [references/mna_issue_mapping.md](references/mna_issue_mapping.md). Use [scripts/fetch_workbench.py](scripts/fetch_workbench.py) when an HTTP workbench is available and you want a complete evidence snapshot.

## Workflow

1. Read the user prompt and the provided `input/payloads/answer_template.json` before fetching data.
2. Extract the deal ID, client side, deal type, output units, enum values, required fields, ordering rules, and any named playbook or policy IDs from the prompt and template.
3. Resolve the task workbench base URL from the prompt or task environment instructions. Stay inside the allowed workbench endpoints.
4. Fetch enough evidence to support every requested template section: deal record, current terms, playbook rules or policy thresholds, risk estimates, benchmarks, consents, material contracts, regulatory status, employees, cap table, diligence findings, documents, and notes as applicable.
5. Build an evidence table before drafting JSON. For every issue, record the source term IDs, source record IDs, governing rule or threshold, calculation basis, and any risk estimate used.
6. Compare only current applicable draft terms against the client-side rule set. Exclude stale, unrelated, in-policy, or distractor records when the prompt asks for escalations or deviations only.