decision-forensics
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.
npx skills add mohitagw15856/pm-claude-skills --skill decision-forensics --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Decision Forensics Skill Most decisions are never stated — they precipitate out of a thread and everyone leaves with a different memory of them. This skill is the forensic pass: what was actually decided (if anything), who committed to what, and which disagreements got papered over rather than resolved. (To *write* a fresh decision going forward, use `architecture-decision-record`; this skill reconstructs one from the wreckage.) ## What This Skill Produces - **The decision, stated cleanly** — one sentence, even though nobody ever said it in one sentence — or the finding "no decision was reached" - **The commitments table** — who agreed to do what, with the quote that binds them - **Reconstructed assumptions** — what everyone silently took as true, labeled as reconstructed - **Dismissed options and papered-over questions** — what was set aside, and what was never actually resolved - **A confidence note** — how solid this reconstruction is and where it's guessing ## Required Inputs Ask for these if not provided: - **The thread** — Slack export, email chain, or meeting notes/transcript (paste; timestamps and names preserved if possible) - **The cast** (optional) — who's who: roles a
- What This Skill Produces
- Required Inputs
- Framework: The Forensic Protocol
- Output Format
- The Decision
- Commitments
- Assumptions (all [reconstructed])
- Options Dismissed
- Papered Over
- Quality Checks
- Anti-Patterns
What does the decision-forensics skill do?
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.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill decision-forensics --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.