Skip to content
TrustedSkillsbeta
Back to all skills

Fact Check

Checked
jwynia·vlatest·other

Verifies claims by cross-referencing sources, ensuring accuracy and combating misinformation for reliable information.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add jwynia/agent-skills --skill fact-check --full-depth -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

jwynia

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned jwynia/agent-skills at e02ec7e226.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
e02ec7e226
Manifest
skills/general/research/verification/fact-check/SKILL.md
Scanned
1 file, 290 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill systematically verifies claims within generated content to combat hallucinations and ensure accuracy. It operates by performing a separate verification pass, distinct from the initial generation process, focusing solely on checking each claim against external sources. The goal is to identify unsupported assertions and provide reliable information by avoiding self-verification or reliance on internal memory.

When to use it

  • When generating content that requires high accuracy and factual correctness (e.g., reports, articles).
  • To mitigate the risk of hallucinations and confabulations in AI-generated text.
  • After initial content generation, before delivery or publication, as a final quality check.

Key capabilities

  • Claim Extraction: Identifies verifiable statements including factual assertions, statistics, attributions, definitions, historical claims, causal claims, and comparative claims.
  • Separate Verification Pass: Performs verification independently of the content generation process.
  • External Source Checking: Relies on external sources for validation rather than internal memory or training data.
  • Claim Categorization: Classifies extracted claims to determine appropriate verification methods.
  • Diagnostic States: Identifies and addresses common errors in verification processes (e.g., self-verification, memory-based verification).

Example prompts

  • "Please fact-check the following text: [insert generated content here]"
  • "Verify all claims within this document and provide source citations."
  • "Run a separate verification pass on the generated report before delivery."

Tips & gotchas

  • The skill requires a complete generation phase before running the verification pass. Asking it to "check your facts" during content creation will be ineffective.
  • Ensure all verifiable claims are systematically extracted; selectively verifying only some claims can leave errors undetected.
  • Explicit source citations are crucial for reliable verification – if a claim cannot be verified with an external source, it should be marked as unverified.