agentleFS
cyb3rcricketcyb3rcricket/cricket-mode/.agents/skills/prove-it/SKILL.md

prove-it

Skill0 starsChanged 51 days agoMITView on GitHub

Use when someone claims a change works and you need to exercise the real behavior, then finish with PASS, FAIL, or PARTIAL and the evidence — not a code-reading summary.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use root-cause, grill and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 3 projects that use this

  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 4 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 8

    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:

    Do not rely only on reading the code or saying it looks correct.

    line 10
  2. Distinctive:

    Test the real behavior.

    line 12
  3. Distinctive:

    Use the actual application or executable path when practical.

    line 16
  4. Distinctive:

    Run relevant existing tests first when they help.

    line 17
  5. Distinctive:

    Prefer the same path a real user would take.

    line 19
  6. Distinctive:

    Keep the verification focused on the work that changed.

    line 21
  7. Distinctive:

    If something fails, say exactly what failed.

    line 22
  8. Distinctive:

    Do not quietly work around failures just to produce a passing result.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 26 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

Prove It

Prove that the thing you just built or changed actually works.

Do not rely only on reading the code or saying it looks correct.

Test the real behavior.

Verify

  • Use the actual application or executable path when practical.
  • Run relevant existing tests first when they help.
  • Exercise the specific feature or change that was just made.
  • Prefer the same path a real user would take.
  • Capture clear evidence such as output, test results, screenshots, responses, or application state.
  • Keep the verification focused on the work that changed.
  • If something fails, say exactly what failed.
  • Do not quietly work around failures just to produce a passing result.

Core Rule

Don't tell me it works. Prove it.

Finish with a concise result:

PASS — the requested behavior was verified and the evidence.

FAIL — the behavior failed and the evidence.

PARTIAL — some behavior was verified, but clearly state what remains unverified.

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.