Agent skill · Content & Marketing

fact-check

Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the speaker. Use before a pitch, press release, reactive comment, DM, or other journalist-facing draft is trusted or sent.

Elvis Sun613★ · +7/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add elvisun/newsjack --skill fact-check --agent claude-code

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

Facts
Files in the skill folder: 1
SKILL.md size: 22 KB
Bundled scripts: none
Path: skills/fact-check/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 620 · +7 this week
Language: Go
Read our review of the source →

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

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

You pull every factual claim out of the draft, verify each claim independently, attach concrete citations, and warn when certainty is low. You run each claim through newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and place the burden of proof on the speaker. Use before a pitch, press release, reactive comment, DM, or other journalist-facing draft is trusted or sent.

How it works

  • Identify all factual claims in the draft and format them as check-worthy items (claims with verifiable evidence).
  • For each claim, perform verification using the prescribed methods in order: triage, lateral reading, source-tier climbing, provenance pillars, triangulation, then calibrated rating.
  • For each claim, determine a status (Verified, Disputed, Unverifiable, Missing source) and attach a concrete citation URL when Verified or Disputed. If evidence is insufficient, mark as Unverifiable or Missing source.
  • End with a Warning section detailing unresolved, disputed, missing-source, or stale risks and what a human must review.

When to use it

Use when you need to verify facts, check sources, cite claims, assess whether a draft is safe to send, or another newsroom skill needs a pre-send factual accuracy gate.

What it can touch

The skill uses the declared tool: "claude-code" to perform verification steps and manage citations.

Caveats

All statements must reference concrete citations; opinions or speculative content should not pass as verified. If a claim cannot be backed by concrete evidence, mark it as a failure rather than passing it.

Output format

Return Markdown in the following structure: a short verdict, a numbered per-claim list, then a warning. The structure mirrors the stated output requirements in the skill.

From the SKILL.md

# Fact Check You are the factual accuracy gate inside newsjack.sh. Your job is narrow: pull every factual claim out of the draft, check each one on its own, attach real citations, and make any unresolved risk impossible to miss. You are not a copywriter, editor, media-list builder, or pitch strategist. Do not rewrite the draft. Do not improve the angle. Do not wave a claim through from memory. If a claim cannot be backed by concrete evidence, mark it a failure rather than letting it pass. ## Operating Doctrine A few principles run through everything below: - **The burden of proof is on the speaker.** An unsupported claim does not default to true. It is "probably fine" only after you have evidence. - Cite real source links. "Reports say" and "industry data" are not citations. - Treat weak or missing sourcing as a headline result, not a footnote. - Check each claim on its own. A paragraph that reads as trustworthy does not make every sentence in it true. - Never treat your own memory as evidence. Use the sources you are given and the search tools available to you. - Keep uncertainty visible. If evidence is old, indirect, or ambiguous, say so. - End every response with a `## Warning`

What's inside
Steps it walks through
  1. Operating Doctrine
  2. What You Need To Start
  3. How To Separate The Work (Ideal Setup)
  4. The Verification Methods — how to check a claim well
  5. 1. Checkworthiness triage — ClaimBuster / ClaimReview
  6. 2. Lateral reading — SHEG (Wineburg & McGrew) / SIFT "Investigate the source"
  7. 3. Source-tier climbing — primary > secondary > tertiary
  8. 4. Provenance pillars — First Draft (Claire Wardle)
  9. 5. Triangulation — Bellingcat / the two-independent-sources rule
  10. 6. Calibrated rating — PolitiFact decision procedure / Full Fact review
  11. Which Claims To Pull Out
  12. The Four Status Labels
  13. How Old Is Too Old
  14. Quality Bar
More from newsjack
All skills →
About this skill
What does the fact-check skill do?

Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the speaker. Use before a pitch, press release, reactive comment, DM, or other journalist-facing draft is trusted or sent.

How do I install it?

Run `npx skills add elvisun/newsjack --skill fact-check --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 elvisun/newsjack, a repository with 620 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