Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Fact-Claim Checker

    1

    Reads a draft article, post, newsletter, report or script and lists every claim that needs a source before it is published, sorted by....

    Free

    1 useSecurity scanned
    Fact-Claim Checker

    Fact-Claim Checker

    Example session with this skill installed

    Fact-check my draft before I publish it.

    • Read your context and instructions
    • Compiled the fact-claim checker

    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 (<10k) tier": pick one.
    Safer wording: "More than 60 people have signed up for the beta, and [N] of them have [SOURCE: your definition of 'successfully']."

    Connects securely to your tools. The creator never sees your data.

    About this 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. Use when the user says "fact check my draft", "what claims need a source", "check this before I publish", "find unsupported claims", or pastes a draft and wants it reviewed before it goes out.

    Free and open source (MIT). Source and README: https://github.com/proskillpacks/skills/tree/main/skills/writing/fact-claim-checker All our free skills: https://github.com/proskillpacks/skills . More from Pro Skill Packs: https://proskillpacks.github.io

    Every skill in the folder ships with prompt.md, a paste-in version for chatbots that cannot load skills.

    Does not verify truth from memory. Requires text or URL input. Skips plain opinion or personal experience. Does not provide professional advice for regulated topics.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill scans your draft for high-risk statements—such as statistics, superlatives, and causal claims—and flags them for verification. It helps prevent misinformation and saves time by identifying exactly which sentences require external citations before publication.

    This skill is compatible with any AI agent that supports custom instructions or system prompts, including ChatGPT, Claude, and Gemini. If your platform doesn't support direct skill imports, you can use the included 'prompt.md' version to manually configure your chatbot.

    No, this skill is designed to act as a neutral auditor. Rather than relying on potentially outdated internal memory to verify truth, it identifies what *needs* a source and suggests the specific type of evidence required to validate the claim.

    The package includes the core skill configuration, a 'prompt.md' file for manual use in any chatbot, and access to the open-source repository. Since it is MIT-licensed, you receive the full source code and the right to modify it for your specific needs.

    Setting up is as simple as copying the provided instructions into your AI agent's system settings. Once active, you can simply paste your draft and ask the agent to "check this before I publish" to receive a structured risk report.

    New in Writing & Content