verify-citations
Helps your agent check if citations and references in a document are real. It's useful for ensuring accuracy in reports and articles.
What it does
Checks if citations in a document point to real sources and if the information is correct. It verifies if numbers match and if claims are supported.
When to use it
- ✓Before submitting a report or article.
- ✓When reviewing AI-generated text.
- ✓To check data accuracy in important documents.
Example of what to ask your AI
“Verify the citations in this report.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You send the document (or paste text). The tool checks each citation and number, comparing them with original sources or the web, and tells you what's correct and what needs attention.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill verify-citationsOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/verify-citations/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Citation Verification
Verify that citations in a document actually resolve and support the claims they're attached to. Uses the Stipple API (free anonymous tier, no signup) for citation resolution, arithmetic recomputation, and unsupported-claim detection.
When to use
- Before submitting or publishing a research report, tender response, or whitepaper
- Reviewing an LLM-generated document (LLM citations are plausibly-formatted and frequently wrong)
- Due diligence on third-party reports
- Academic reference checking
Instructions
Get the document. Ask the user for a URL to the report, or a local file path (PDF, DOCX, Markdown). If the user pastes text directly, skip to step 3 with
textinput.Run verification. POST the document to Stipple's citation verification endpoint:
curl -X POST https://www.stipple.sh/v1/verify-references \ -F "file=@report.pdf" \ -H "Authorization: Bearer $STIPPLE_API_KEY"The anonymous free tier works without the Authorization header. Deep mode (
?deep=true) costs more credits but cross-checks citations against live web sources.Interpret the response. The result includes:
verification_coverage— percentage of claims verified (e.g. "78%")citations[]— per-citation status: resolved and matching, resolved but mismatched, or unresolvable, with the issue explainedarithmetic[]— recomputed figures vs stated figures (flags decimal shifts, wrong sums)unsupported_claims[]— claims with no citation at all
Report honestly. Present results as verification coverage, not a truth verdict:
- "21/27 citations resolve and match"
- "[x] FY24+FY25 revenue stated $4.2m, actual $3.7m"
- "[!] 'industry-leading accuracy' — no source in document"
- Unverified ≠ false. The goal is telling the user which claims are backed and which aren't.
Offer remediation. For failed citations, suggest: fixing the decimal shift, finding the correct source, or removing the unsupported claim.
Output format
Verification coverage: 78%
Citations: 21/27 resolve and match
[+] "ABS unemployment 4.1% April 2026" — matches abs.gov.au
[-] "AI adoption grew 340% in 2025" — source states 34%, decimal shifted
Arithmetic: 12/13 recompute correctly
[x] FY24 + FY25 revenue — stated $4.2m, actual $3.7m
Unsupported claims: 2
[!] "industry-leading accuracy" — no source in document
Limitations and Safety
- Uploading a report or manuscript sends its contents to a hosted third party; deep mode also retrieves external sources. Obtain approval before transmission, remove confidential or personal material, and verify current retention and deletion terms.
- Resolution and textual support do not establish that a source is authoritative or that a claim is true. Inspect consequential citations in the primary source and preserve page, edition, date, and access context.
- Treat unresolved or unsupported claims as review items, not proof of fabrication, and keep a human reviewer responsible for publication or academic decisions.
Notes
- Works on PDF, DOCX, MD, TXT. For pasted text, POST JSON:
{"text": "..."} - Deep verification (
deep=true) is slower and costs more credits but resolves citations against live sources - Pairs well with
verify-document(is the source doc itself authentic?) run first - Anonymous free tier: shared weekly allowance. Get a free key at https://www.stipple.sh for your own metering
FAQ
What happens if a citation isn't found?
The tool will report that the citation couldn't be verified or that the found source doesn't match the claim.
Does it guarantee the information is true?
No, it only checks if the citation exists and if the information matches the source. The final truthfulness depends on the original source.
Can I send any file type?
It works with PDF, DOCX, and Markdown files, or you can paste the text directly.
Details
Original description by the author
Verify citations and references in a document, report, or article against real sources. Use when the user asks to fact-check, verify references, check citations, or validate evidence in research reports, tender responses, whitepapers, or academic writing.
Popularity
- GitHub stars
- 48k
- Ranking position
- #4494
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
deep-research
Lets your agent research topics in depth, gathering information from multiple sources. It cites sources and indicates confidence levels. Ideal for deep dives or investigations.
affaan-m/ECC
research-ops
Lets your agent find current facts and information. It uses public research and the context you provide to give evidence-based answers.
affaan-m/ECC
scientific-thinking-literature-review
Helps your agent conduct systematic reviews of scientific literature. It's useful for compiling and understanding research on a topic.
affaan-m/ECC