sickn33/agentic-awesome-skills/verify-citations

Claude Code and agent skill by sickn33/agentic-awesome-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

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.

Install

npx vskill@latest install sickn33/agentic-awesome-skills/verify-citations

SKILL.md

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

  1. 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 text input.
  1. Run verification. POST the document to Stipple's citation verification endpoint:

``bash 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.

  1. 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 explained
  • arithmetic[] — recomputed figures vs stated figures (flags decimal shifts, wrong sums)
  • unsupported_claims[] — claims with no citation at all
  1. 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.
  1. 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

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
47,054
Repository forks
6,853
7-day trend score
54

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sickn33/agentic-awesome-skills/verify-citations/badge)](https://verified-skill.com/skills/sickn33/agentic-awesome-skills/verify-citations)

Something wrong with this skill or its page? Tell us.