Agent skill

fact-check-pass

Run a claim-by-claim fact-check pass on a draft article, script, or report before publication. Use when asked to fact-check a piece, verify claims before publishing, or do editorial verification. Produces a claim inventory (every checkable assertion pulled out), a verification status and source for each (confirmed / needs sourcing / unverifiable / wrong), the fixes, and a flag on the high-risk claims (numbers, quotes, names, legal/defamatory statements) that must not go out unverified.

mohitagw158561,255★ · 1 repos on radarProfile →
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill fact-check-pass --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/fact-check-pass/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,255
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Fact-Check Pass Skill Everything in a published piece is a claim someone can be wrong about — a date, a number, a quote, an implication. This skill does what a good fact-checker does: it pulls every checkable assertion out of the prose, verifies each against a source, and stops the high-risk ones (stats, quotes, anything defamatory) from going out on a "probably right." ## Working from a brief Given the draft, **produce the claim inventory and status** — check what you can against the provided/known sources, and for anything you can't verify, mark it clearly rather than guessing. Never assert a fact is confirmed without a basis. ## Required Inputs Ask for (if not provided, else infer and label): - **The draft** (article, script, report) - **Available sources** — the reporter's notes, documents, links, transcripts - **Risk level / venue** — where it publishes and how litigious/high-stakes the subject is ## Output Format ### Claim inventory Every checkable assertion extracted: | # | Claim (as written) | Type | Status | Source / basis | Fix | |---|---|---|---|---|---| - **Type:** number/stat · quote · name/title · date · causal/implied · characterization. - **Status:** ✅ confirmed ·

What's inside
Steps it walks through
  1. Working from a brief
  2. Required Inputs
  3. Output Format
  4. Claim inventory
  5. High-risk flags
  6. Fixes
  7. Sign-off
  8. Quality Checks
  9. Anti-Patterns
More from pm-claude-skills
All skills →
About this skill
What does the fact-check-pass skill do?

Run a claim-by-claim fact-check pass on a draft article, script, or report before publication. Use when asked to fact-check a piece, verify claims before publishing, or do editorial verification. Produces a claim inventory (every checkable assertion pulled out), a verification status and source for each (confirmed / needs sourcing / unverifiable / wrong), the fixes, and a flag on the high-risk claims (numbers, quotes, names, legal/defamatory statements) that must not go out unverified.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill fact-check-pass --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.

Keep going