agentleFS
weininghuiweininghui/skills/fact-checker/SKILL.md

fact-checker

Skill1 starsChanged 13 days agoMITView on GitHub

Verify claims with web search, assign confidence scores, and generate structured fact-check reports.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use qa-expert, prompt-master and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • belokonmSkill

    qa-expert

    Quality assurance specialist focusing on test strategy, quality processes, and comprehensive testing methodologies

    Also in 3 projects that use this

  • ttmouseSkill

    prompt-master

    提示词主控 - 智能选择合适的领域skill并生成提示词,支持自动领域分类和调度

    Also in 3 projects that use this

  • NVIDIASkill

    deep-research

    Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.

    Also in 4 projects that use this

  • AnthropicSkill

    xlsx

    Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

    Also in 3 projects that use this

  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 4

    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
  1. Distinctive:

    No API keys needed

    line 15
  2. Distinctive:

    Ambiguous claims: If a claim can be interpreted multiple ways, check the most charitable interpretation first, then note caveats.

    line 61
  3. Distinctive:

    Never fabricate sources or URLs — only cite actually found results.

    line 68
  4. Distinctive:

    Don't present search snippets as verified facts.

    line 69

“Common” is measured: kept by at least 6 in 10 of the 19 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Fact Checker

Automated fact-checking with confidence scoring and source attribution.

Use when verifying claims, checking article accuracy, or fact-checking content before publishing.

Requirements

  • web_search tool access
  • No API keys needed

Instructions

  1. Extract claims from the provided text. List each claim separately. Skip opinions and subjective statements — only fact-check factual assertions.
  2. Search for evidence using web_search for each claim. Search for the core factual assertion, not the full sentence. Run 2-3 searches with different phrasings if initial results are inconclusive.
  3. Evaluate sources with this hierarchy:
    • 🥇 Official sources (government, organizations cited in the claim)
    • 🥈 Peer-reviewed research, established wire services (AP, Reuters)
    • 🥉 Major news outlets with editorial standards
    • ⚠️ Blogs, social media, opinion pieces (note as weak evidence)
  4. Assign verdict to each claim:
    VerdictConfidenceCriteria
    ✅ Verified90-100%Multiple reliable sources confirm
    ⚠️ Partially True50-89%True with caveats or missing context
    ❌ False0-29%Contradicted by reliable sources
    🔍 UnverifiableN/AInsufficient sources to determine
  5. Output format:
    ## 🔍 Fact Check Report
    **Source:** [article/text title]
    **Date checked:** YYYY-MM-DD
    
    ### Claim 1: "[exact claim text]"
    **Verdict:** ✅ Verified (95%)
    **Evidence:** [2-3 sentence summary]
    **Sources:**
    - [Source name](URL) — [key finding]
    - [Source name](URL) — [key finding]
    
    ### Summary
    | # | Claim | Verdict |
    |---|-------|---------|
    | 1 | [short claim] | ✅ Verified |
    | 2 | [short claim] | ❌ False |
    **Overall accuracy: X/Y claims verified**

Edge Cases & Troubleshooting

  • Date-sensitive claims: Note when the info was last verified. Facts about statistics, rankings, or prices change frequently.
  • Ambiguous claims: If a claim can be interpreted multiple ways, check the most charitable interpretation first, then note caveats.
  • No sources found: Mark as 🔍 Unverifiable — absence of evidence is not evidence of absence.
  • Conflicting sources: Report the conflict explicitly. Note which sources are more authoritative and why.
  • Satire/parody: Flag if the original source appears to be satirical.

Security Considerations

  • Never fabricate sources or URLs — only cite actually found results.
  • Don't present search snippets as verified facts; always cross-reference.
  • Disclose limitations transparently in the report.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.