citation-verifier
Skill197 starsChanged yesterdayApache-2.0View on GitHub
Verify that research claims are supported by traceable sources, while preserving scope, freshness, limitations, and contradictions.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- TidalPaladin/skillstheir own version, first seen Nov 8, 2026
- papersflow-ai/papersflow-skillstheir own version, first seen Nov 8, 2026
- jkitchin/knowhowtheir own version, first seen Nov 1, 2026
- Nero1688/claude-academic-skillstheir own version, first seen Oct 20, 2026
- Boom5426/Nature-Paper-Skillstheir own version, first seen Oct 9, 2026
- AlpaZZ/office-agent-skillstheir own version, first seen Oct 7, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- Boom5426/Nature-Paper-Skills★ 661same name
- jkitchin/knowhow★ 45same name
- Chanw-research/claude-code-paper-writing★ 42same name
- Nero1688/claude-academic-skills★ 13same name
- KhaledSaeed18/dotclaude★ 5same name
- papersflow-ai/papersflow-skills★ 4same name
- AlpaZZ/office-agent-skills★ 1same name
- TidalPaladin/skills★ 1same name
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 repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- 3d-production-workflowSkill
- code-health-auditSkill
- code-reviewSkill
- docxSkill
- email-workflowSkill
- ghxSkill
- github-issue-solveSkill
- github-pr-fixSkill
- github-reviewSkill
- holon-runtime-opsSkill
- interlinked-markdown-wikiSkill
- learning-coachSkill
- opsSkill
- pdfSkill
- pptxSkill
- research-artifactSkill
- video-productionSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill after sources have been collected and before a research brief is delivered.
- Very specific: line 23
If an input is missing, report the missing field and mark affected claims unverified.
- Distinctive: line 30
Check entailment: does the cited passage support the exact proposition, or only a weaker/narrower statement?
- Distinctive: line 33
Check scope: compare geography, population, version, methodology, definitions, and date.
- Distinctive: line 35
Check freshness: distinguish publication date, last update, and access date.
- Distinctive: line 37
Check source quality separately from entailment: identify primary, secondary, official, self-reported, anonymous, or untraceable material …
- Distinctive: line 40
Search for counter-evidence when the claim is material, disputed, surprising, or supported by only one weak source.
- Distinctive: line 62
Keep the distinction explicit:
- Distinctive: line 73
Never invent a URL, DOI, title, date, quotation, page number, or source identity.
- Distinctive: line 75
Never cite a source you did not inspect when the task requires claim-level verification.
- Distinctive: line 77
Never remove a contradictory source merely because it is inconvenient.
- Distinctive: line 78
Do not use citation count, search rank, repository stars, or model agreement as a substitute for entailment and scope checks.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Citation Verifier Skill
Purpose
Use this skill after sources have been collected and before a research brief is delivered. It checks the relationship between a claim and its cited evidence; it does not decide whether a conclusion is desirable and it does not turn search results into evidence.
Required inputs
- A claim list with stable IDs, wording, and the importance of each claim.
- A source ledger with stable IDs, title, publisher or author, locator, publication/update date when available, access date, scope, and limitations.
- The relevant excerpt, table, section, or reproducible locator for each claim/source pair. A homepage or search snippet is not a sufficient locator.
If an input is missing, report the missing field and mark affected claims
unverified; do not fill it with a guessed citation.
Verification procedure
- Normalize each claim so that it has one testable proposition, a defined population or object, a time window, and any important qualifier.
- Check entailment: does the cited passage support the exact proposition, or only a weaker/narrower statement? Record a short paraphrase, not an invented quotation.
- Check scope: compare geography, population, version, methodology, definitions, and date. A source can be credible and still be out of scope.
- Check freshness: distinguish publication date, last update, and access date. Flag time-sensitive claims whose evidence may have changed.
- Check source quality separately from entailment: identify primary, secondary, official, self-reported, anonymous, or untraceable material and record the reason it matters.
- Search for counter-evidence when the claim is material, disputed, surprising, or supported by only one weak source. Preserve conflicts rather than collapsing them into an average.
- Assign one terminal status:
supported,partially-supported,contradicted,unverified, orblocked. Include the reason, source IDs, and the next check if unresolved.
Output contract
Return a claim/evidence matrix with at least these columns:
| claim_id | claim | source_ids | locator | scope/date check | source quality | counter-evidence | status | reason |
Also return:
verified_at: the date/time of the verification pass;coverage: material claims checked versus total material claims;conflicts: a list of unresolved or context-dependent conflicts;unverified: claims that must not appear as established facts;next_checks: the smallest useful follow-up actions.
Keep the distinction explicit:
- supported means the cited material entails the claim within its scope;
- partially-supported means only a qualified or narrower claim is entailed;
- contradicted means credible evidence materially conflicts with the claim;
- unverified means evidence is missing, inaccessible, or does not entail it;
- blocked means the check cannot proceed because access or required input is unavailable.
Safety rules
- Never invent a URL, DOI, title, date, quotation, page number, or source identity.
- Never cite a source you did not inspect when the task requires claim-level verification. Label operator-provided excerpts as excerpts.
- Never remove a contradictory source merely because it is inconvenient.
- Do not use citation count, search rank, repository stars, or model agreement as a substitute for entailment and scope checks.
- For high-risk topics, report verification limits and require qualified human review before the result is used as advice.
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.

