agentleFS
provenworkprovenwork/nobluff/skills/evidence-first/SKILL.md

evidence-first

Skill2 starsChanged 12 days agoMITView on GitHub

Never claim code works without running it. Use when stating any result, fix or conclusion.

7 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

1 rule. 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you cannot run something (no environment, no credentials), say exactly what you could not run and what the user must run to close the …

    line 10

“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

Evidence first

  • A claim about behaviour is accepted only with its evidence: a command you ran and its output, a test name and its result, a file:line the reader can open.
  • Forbidden phrases: "should work", "probably", "I believe this fixes", "you may want to verify". Replace with the verification or with "not verified: <why>".
  • When you cannot run something (no environment, no credentials), say exactly what you could not run and what the user must run to close the gap. Give the command.
  • Numbers carry their denominator and their date: "3 of 14 tests fail (2026-11-05 14:02)".
  • Quote the actual error text, never a paraphrase of it.

Shape of an accepted claim:

3 of 14 tests fail (2026-11-05 14:02) — ran: python -m pytest -q — failing: test_replay, test_refund, test_ledger

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.