verify-claims
Skill0 starsChanged 7 days agoMITView on GitHub
Fact-checks a draft, answer, report or AI-generated text before it is used or published. Use when the user asks to check, verify or fact-check something; before finalizing anything with facts, numbers, quotes or citations; or for high-stakes content (legal, medical, financial, public). Splits text into atomic claims, checks each independently against sources, and reports what holds up.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- carriegale2710/resume-tailortheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 7, 2026
- Thakurvaibhav/platform-agent-harnesstheir own version, first seen Nov 6, 2026
- happier-dev/happiertheir own version, first seen Nov 3, 2026
- jasoncaston/two-body-verifytheir own version, first seen Nov 1, 2026
- zirui-song/claude-skillstheir own version, first seen Nov 1, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- happier-dev/happier★ 2.2ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- ShaishavMaisuria/research-paper-lifecycle-skills★ 59same name
- AlessandroCaforio/Academic-Writing★ 17same name
- zirui-song/claude-skills★ 17same name
- bhagyamudgal/skills★ 2same name
- Thakurvaibhav/platform-agent-harness★ 2same name
- busycaesar/Harness★ 1same name
- carriegale2710/resume-tailor★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- drop-in/AGENTS.mdAGENTS.md
- llms.txtllms.txt
- clarify-firstSkill
- coverage-checkSkill
- fresh-eyes-reviewSkill
- fresh-start-handoffSkill
- grounded-answerSkill
- honest-critiqueSkill
- learning-tutorSkill
- prompt-improverSkill
- task-specSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Plan a check for each: Write a verification question per claim ("Was X founded in 2019?").
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify claims
Asking a model "are you sure?" is not verification; it makes models flip correct answers. Check claims one by one, independently, against evidence outside the draft.
Steps
- Split into atomic claims. List every checkable statement in the text, one fact per line, numbered (names, dates, numbers, quotes, causal claims, citations).
- Plan a check for each. Write a verification question per claim ("Was X founded in 2019?").
- Answer the questions independently. Answer each verification question without relying on the draft's wording. Use the provided sources, files, a search tool, or code (for arithmetic). Open every cited link or file; check that it exists and says what the draft claims.
Report a verdict table:
# Claim Verdict (✅ supported / ❌ contradicted / ❓ unverified) Evidence - Fix the draft. Propose corrected wording for ❌ items and either remove ❓ items or mark them as unverified.
Scale the effort to the stakes
- Low (brainstorms, drafts): check the claims that look most specific (numbers, names, dates).
- Medium (work documents): check every number and every citation.
- High (legal, medical, financial, published): check every claim, read laterally (confirm with independent sources), recompute every number, and never accept the same model's agreement as proof.
Evidence
- Chain-of-Verification: plan questions, answer them independently, revise: Dhuliawala et al., 2023 — https://arxiv.org/abs/2309.11495
- Atomic-fact checking for long text: FActScore, 2023 — https://arxiv.org/abs/2305.14251
- "Are you sure?" made models flip answers 46% of the time (2023 study): FlipFlop — https://arxiv.org/abs/2311.08596
- Even real citations often don't support the claim: Walters & Wilder, 2023 — https://www.nature.com/articles/s41598-023-41032-5
- More in the guide: https://github.com/ji-hun-git/how-to-use-ai/blob/main/docs/08-verification-and-evals.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

