What do I need to use Decision Forensics?

The thread; The cast (optional); What prompted the forensics (optional).

Is Decision Forensics free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Decision Forensics

Q: How do I know the Decision Forensics output is good?

The skill verifies itself against its own quality checks: Every attribution carries a quote or near-paraphrase with original wording nearby; Assumptions are labeled `[reconstructed]` — never presented as things people said; The confidence grade matches the evidence type (explicit / unobjected / inferred); Papered-over questions are listed separately from resolved ones.

🔵 Stable🕐 updated 2026-07-14 🔷 SkillSpec L3 pm-method

Reconstruct the decision actually made in a messy Slack, email, or meeting thread into a proper decision record — commitments named, silent assumptions surfaced, non-decisions called out. Use when asked what did we actually decide, turn this thread into a decision record, who committed to what, or reconstruct this discussion. Produces a decision record with quoted evidence, a commitments table, reconstructed assumptions, dismissed options, and a confidence note on the reconstruction itself.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The thread — Slack export, email chain, or meeting notes/transcript (paste; timestamps and names preserved if possible)

▸The cast (optional) — (optional) — who's who: roles and decision authority; else infer from context and label

▸What prompted the forensics (optional) — (optional) — a dispute, an audit, onboarding someone — shapes emphasis, never conclusions

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every attribution carries a quote or near-paraphrase with original wording nearby

✓Assumptions are labeled `[reconstructed]` — never presented as things people said

✓The confidence grade matches the evidence type (explicit / unobjected / inferred)

✓Papered-over questions are listed separately from resolved ones

✓If no decision was reached, the record says so plainly

⚠️ What it refuses to do

Do not attribute positions beyond what the text supports — quote it or drop it

Do not resolve ambiguity by inventing agreement — surfacing the ambiguity IS the deliverable

Do not clean a non-decision into a decision; "no decision was reached" is a valid, common, and useful finding

Do not editorialize about who was right — forensics reconstructs; it doesn't adjudicate

Do not omit the confidence note — a reconstruction that hides its own uncertainty is fabrication with footnotes

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="decision-forensics"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Decision Forensics is one of 743 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog