agentleFS
Sign inStart free
prasadmogulothuprasadmogulothu/agent-skills/test-and-fix/SKILL.md

test-and-fix

Skill0 starsChanged 5 months agoMITView on GitHub

Run the test suite, read failures, patch, and re-run — looping until green or a precise blocker report. Use for any feature or module that has tests. Caps attempts so it can't run away.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use techdebt and grill.

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.
  • dbankscardSkill

    techdebt

    Find and report technical debt, duplicated code, and cleanup opportunities. Run at end of sessions.

    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 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    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. Distinctive:

    Run the relevant suites (unit, integration, e2e, accessibility — whatever the project has).

    line 11
  2. Very specific:

    Stop at green, OR after a fixed attempt cap (e.g.

    line 13
  3. Distinctive:

    Never delete or skip a failing test to "pass".

    line 15
  4. Distinctive:

    All targeted suites pass, or a clear blocker report exists.

    line 18

“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

test-and-fix

Close the loop on tests automatically, so cheaper models can self-correct safely.

Steps

  1. Run the relevant suites (unit, integration, e2e, accessibility — whatever the project has).
  2. On failure: read the actual error, form a hypothesis, patch the smallest thing, re-run.
  3. Stop at green, OR after a fixed attempt cap (e.g. 6) → write a precise blocker report (the failing test, the error, what you tried) to tasks.md and stop.
  4. Never delete or skip a failing test to "pass". Never mark done on a partial.

Done when

All targeted suites pass, or a clear blocker report exists. Coverage on changed code meets your project threshold.

Token tactics

Ideal for a cheaper/mid model — the iterative loop is where expensive models waste budget. Cap the attempts to bound cost. Pass only the failing test + the file under test, not the whole repo.

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.

Check your setup, free