Skip to content
TrustedSkillsbeta
Back to all skills

Fact Checker

Checked
nicepkg·vlatest·other·MIT

Verifies claims by cross-referencing sources, ensuring accuracy and combating misinformation in your content.

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 nicepkg/ai-workflow --skill fact-checker --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

nicepkg

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 nicepkg/ai-workflow at d167b41af7.

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

Commit
d167b41af7
Manifest
workflows/content-creator-workflow/.claude/skills/fact-checker/SKILL.md
Scanned
2 files, 451 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

The nicepkg-fact-checker skill is part of the nicepkg/ai-workflow collection, designed to help AI agents verify information and ensure data accuracy within automated workflows. It enables agents to cross-reference claims against trusted sources or internal knowledge bases before executing actions based on that data.

When to use it

  • Pre-decision verification: Validate critical data points (e.g., stock prices, medical advice) before an agent triggers a transaction or alert.
  • Hallucination prevention: Reduce the risk of agents generating false information when answering complex user queries.
  • Workflow integrity: Ensure that automated pipelines relying on external APIs or web searches do not propagate errors downstream.
  • Compliance checks: Confirm that generated content adheres to specific factual standards required by industry regulations.

Key capabilities

  • Integrates with the nicepkg/ai-workflow ecosystem to provide structured fact-checking logic.
  • Supports verification of dynamic data sources commonly accessed by AI agents.
  • Provides a standardized method for agents to flag unverified claims within their output.

Example prompts

  • "Before scheduling the meeting, use the fact-checker to verify the availability of all listed attendees."
  • "Cross-reference the product specifications in this email with our internal database using the fact-checker."
  • "Run a fact-check on the news headline provided to determine its credibility before sharing it."

Tips & gotchas

Ensure your AI agent has access to the necessary data sources or APIs required for verification, as the skill relies on external context. Limit usage to scenarios where factual accuracy is critical, as constant verification may increase latency in real-time workflows.