AI Claim Checker
AI Claim Checker is an agent skill (a SKILL.md file) from iflytek/skillhub. Evaluate factual claims in AI-generated text and teach a lightweight verification habit. It works with Claude Code and Codex and has 5,294 GitHub stars across a repository of 4 listed skills.
github.com/iflytek/skillhub/builtin-skills/skills/ai-claim-checker (opens in a new tab)
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Testing & QA
- Active
Add this skill
Claude
Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):
git clone --depth 1 https://github.com/iflytek/skillhub.git
cp -r skillhub/builtin-skills/skills/ai-claim-checker ~/.claude/skills/ai-claim-checker # personal, or .claude/skills in a projectIn the Claude apps, zip the ai-claim-checker folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/iflytek/skillhub.git
cp -r skillhub/builtin-skills/skills/ai-claim-checker .agents/skills/ai-claim-checker # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/iflytek/skillhub.git
cp -r skillhub/builtin-skills/skills/ai-claim-checker .cursor/skills/ai-claim-checker # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Evaluate factual claims in AI-generated text and teach a lightweight verification habit. Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy. Help the user treat fluent AI output as claims to evaluate, not as automatically true or false. Produce a direct assessment when requested; offer the learner-facing exercise without making it a mandatory gate.
When it triggers
- Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy.
More skills in iflytek/skillhub
4 skills are listed from this repository.
Similar skills
More testing & qa skills
Bug Bounty
elementalsouls/Claude-BugHunter
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind…
Active · last commit Oct 25, 2026
Testing & QAPythonMarginaleffects
brycewang-stanford/Auto-Empirical-Research-Skills
Manual for the marginaleffects R and Python package, and guide to the book "Model to Meaning".
Active · last commit Oct 20, 2026
Testing & QAStataMirrord Chaos
metalbear-co/mirrord
Help users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the mirrord chaos CLI.
Active · last commit Oct 25, 2026
OfficialTesting & QARustAPI Fuzzing Bug Bounty
zebbern/claude-code-guide
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing"…
Maintained · last commit Oct 24, 2026
Testing & QAPythonReplica Test
Jakeschincariol/replica-skill
Clicks through every flow of an app clone and tests it for bugs: a test plan generated from the recon flows with happy paths and edge cases, Playwright end-to-end tests where possible, a browser…
Too new to judge · created Oct 3, 2026
Testing & QAPythonObserval Ops
Observal/Observal
Inspects Observal traces, sessions, rankings, feedback, telemetry health, logs, and Agent insight reports.
Active · last commit Oct 25, 2026
Testing & QAPython
How do I install the AI Claim Checker skill?
Copy the ai-claim-checker folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.
Is the AI Claim Checker skill free?
Yes. The repository is open source under the Apache-2.0 license.
Is AI Claim Checker maintained?
The repository's most recent commit was on Oct 26, 2026. Its latest release is cli-v0.2.0. appsgit only lists skills from repositories with a commit in the last six months.