agentleFS
rubenmarcusrubenmarcus/agent-skills/skills/quality-gates/SKILL.md

quality-gates

Skill2 starsChanged 13 days agoMITView on GitHub

Design or repair checks that measure real behavior and fail under a deliberate defect. Use when adding invariants, probes, regression gates, quality thresholds, or diagnosing a green check that misses a real failure.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan.

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.
  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 3

    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:

    Read runtime effects when declarations can differ.

    line 14
  2. Distinctive:

    Keep the check within its execution budget.

    line 30
  3. Distinctive:

    Do not relax thresholds just to pass.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 24 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

Quality gates

A gate needs a behavioral contract and evidence that it can reject a broken result.

Define what it observes

Name the defect the gate should catch and a bad state that could accidentally improve its metric. Measure in the environment where the behavior matters.

Read runtime effects when declarations can differ. A constant's value does not prove a caller uses it. File existence does not prove contents or provenance.

Choose thresholds from a reference, baseline, budget, or requirement. Record the basis and units. Locate other checks of the same contract to avoid contradictory thresholds.

Prove the check

Exercise a valid baseline, a relevant broken state or deliberate mutation, and a failed or unavailable measurement.

Confirm the mutation actually applied. Preserve output showing that the check caught it, then restore the original state in the owned fixture or worktree.

A missing measurement must not become a passing zero. Represent unavailable evidence explicitly and make the completion decision respect that status.

Make failure actionable

Report the value, threshold, scenario, input identity, and reproduction command. Visual contracts need inspectable captures as well as numbers.

Keep the check within its execution budget. Document required ordering between producers and consumers of evidence. Regenerate inputs for a new revision.

Do not relax thresholds just to pass. Revisit the contract when the reference, requirement, or measurement is shown to be wrong.

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.