Reads a draft article, post, newsletter, report or script and lists every claim that needs a source before it is published, sorted by risk, with what kind of source would settle each one. It marks which claims the draft itself already supports, which are plain opinion, and which are risky (numbers, studies, quotes, dates, "first/only/best", cause and effect, claims about people or companies). It does not rule claims true or false from memory.
npx mdskills install proskillpacks/fact-claim-checkerRelated
Paste a draft before you publish it. You get a list of the claims that need a source, ranked by risk, with the kind of source that would settle each one, and safer wording for the high-risk ones you cannot back up. It does not tell you what is true. It tells you what to check.
Any assistant that reads the open SKILL.md format works.
fact-claim-checker folder into .agents/skills/ in your project (or ~/.agents/skills/ for everywhere). Create the folder if it is not there. Or use your tool's own skills folder (for example .claude/skills/ for Claude Code).No install: open prompt.md, copy it, paste it into ChatGPT or any chatbot, and add your draft where marked.
Needs: nothing. It works from the text you paste.
Works with any AI assistant that reads SKILL.md (Claude, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot and others). We run our release tests on Claude Sonnet and Opus. Use your assistant's strongest model: in our tests, a small, fast model added facts that were not in the source data.
A public launch post from a small software company, with prices, dates, a user count and a discount, mixed with opinion.
After (skill output, excerpt): Claims found: 17. High risk: 6. Medium: 7. Low: 4. "more than 60 people have signed up used Plausible successfully": a number, and "successfully" is undefined. A typo changes the meaning ("signed up used"). "up to 10k pageviews - $6 / mo" versus later "a small ( Safer wording: "More than 60 people have signed up for the beta, and [N] of them have [SOURCE: your definition of 'successfully']."
1 real-data run on a public launch post (Claude Sonnet). We read every flagged claim against the source text: all 17 were real claims, and the two conflicts it raised were real. Not yet run on other models.
Made by Pro Skill Packs. Free under the MIT licence.
More skills: https://proskillpacks.github.io/
Install via CLI
npx mdskills install proskillpacks/fact-claim-checkerFact Claim Checker is a free, open-source AI agent skill. Reads a draft article, post, newsletter, report or script and lists every claim that needs a source before it is published, sorted by risk, with what kind of source would settle each one. It marks which claims the draft itself already supports, which are plain opinion, and which are risky (numbers, studies, quotes, dates, "first/only/best", cause and effect, claims about people or companies). It does not rule claims true or false from memory.
Install Fact Claim Checker with a single command:
npx mdskills install proskillpacks/fact-claim-checkerThis downloads the skill files into your project and your AI agent picks them up automatically.
Fact Claim Checker works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Codex, Gemini Cli, Amp, Roo Code, Goose, Opencode, Trae, Qodo, Command Code, Chatgpt. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.