agentleFS
winchxyzwinchxyz/idea-to-build/.claude/skills/factcheck/SKILL.md

factcheck

Skill9 starsChanged 5 months agoMITView on GitHub

Apply the idea-to-build verification protocol (Tier 1/2/3, Skeptical-by-Default) to a specific claim. Use when the user types "/factcheck" followed by a claim, or asks to verify, fact-check, or pressure-test a specific statement.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read core/CLAUDE.md (the Factual Rigor / Tier 1/2/3 protocol and the Skeptical-by-Default stance).

    line 8
  2. Distinctive:

    If the claim is false or shaky, say so directly and name exactly what would confirm or refute it.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/factcheck — verify a claim (Skeptical-by-Default)

  1. Read core/CLAUDE.md (the Factual Rigor / Tier 1/2/3 protocol and the Skeptical-by-Default stance).
  2. The claim to verify is whatever the user provided after /factcheck (as a slash command, that's $ARGUMENTS). If it's empty, ask which claim to check. Then classify it:
    • Tier 1 — logic, math on given numbers, fundamental concepts → assert directly.
    • Tier 2 — tool details, "best practices", memory-based claims below ~90% confidence → mark ⚠️ and verify when possible.
    • Tier 3 — market sizes, prices, competitor data, current platform policies, recent news, anything that could have changed in the last 6–18 months → search before stating.
  3. For Tier 3, search first, then cite the source (title + year, URL if available).
  4. Label the verdict: ✅ verified / ⚠️ hypothesis / 🔍 needs verification. If no reliable source exists, say so plainly — never fabricate.
  5. If the claim is false or shaky, say so directly and name exactly what would confirm or refute it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.