agentleFS
parker-brown-familyparker-brown-family/agent-skills/scientific-method/SKILL.md

scientific-method

Skill1 starsChanged 8 days agoNo licenceView on GitHub

Put a claim, a theory or a whole argument to the test, and hand back which steps the record confirms, which it contradicts, which an ordinary explanation already covers, which rest on a weak move, and which are reasonable conjecture still worth pursuing. Pulls every claim out word for word, writes the competing hypotheses before weighing anything, writes traps that would embarrass the grading, gathers the record apart from the argument, grades each claim's reasoning and its record in two passes that never see each other, weighs the hypotheses only on evidence that tells them apart, checks every striking coincidence against how often chance would produce it, and tests the grader before trusting it. Use on a podcast, video, article, thread or pitch that makes contested claims ('put this to the test', 'fact-check this episode', 'is this conspiracy theory any good', 'stress-test this theory', 'what would refute this', 'competing hypotheses', 'is this a coincidence'), and on our own conjectures: a bug's root cause, a product bet, a surprising result ('are we sure', 'what else could explain this', 'scientific method', '/scientific-method'). Never decides anyone's guilt, honesty or motives.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

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.