agentleFS
timfewitimfewi/unix-agent-skills/skills/code/fast-checks/SKILL.md

fast-checks

Skill2 starsChanged 9 days agoMITView on GitHub

Use when selecting checks for changed behavior or diagnosing a failed check; not for unrelated read-only investigation.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Use the repository's declared gate and supported environment.

    line 8
  2. Distinctive:

    Read-only questions need source evidence, not unrelated builds.

    line 17
  3. Distinctive:

    Keep one check running per repository, preserve its handle, and reuse passing results while inputs remain unchanged.

    line 21
  4. Distinctive:

    Use workload authorization from the current request or trusted environment policy.

    line 24

≈ “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.

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

Verify the changed contract

Use the repository's declared gate and supported environment. Select additional checks from the behavior at risk, not a generic list of tools. Entering a development shell is setup, not verification.

  • For code or configuration changes, run the owning fast gate or declared equivalent.
  • For runtime, packaging, or build-output changes, also exercise the affected path: a focused test, CLI invocation, build, or request. Reuse coverage already supplied by the gate instead of rerunning the same check by habit.
  • Read-only questions need source evidence, not unrelated builds. Repository documentation uses its applicable checks; external plans need source and acceptance review.

Keep one check running per repository, preserve its handle, and reuse passing results while inputs remain unchanged. Stay within authorized workload and resource limits. Stop owned preview servers when finished. Use workload authorization from the current request or trusted environment policy. Reuse standing grants within their scope and budgets; do not infer permission for unrelated builds, VM tests, model runs or benchmarks.

On failure, retain the command, exit status, and decisive diagnostic. Distinguish baseline failures from regressions when practical. Repair task-caused failures and rerun affected checks. Keep publication paused until required checks pass; a failure does not end authorized diagnosis. Fix the cause, not the assertion; never skip or weaken a check for green output.

State what each result proves and what remains untested. A formatter, evaluator, or mocked unit test does not establish user-facing behavior.

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.