agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/vs-coverage-gap-not-clone/SKILL.md

vs-coverage-gap-not-clone

Skill29 starsChanged 7 months agoMITView on GitHub

Steal VS "Today I will improve test coverage" FORMAT: baseline gaps, skip no-behavior files, remeasure the same scope. Do NOT clone Test Agent or Copilot @test #solution. Do NOT claim 100% coverage. Slash: /vs-coverage-gap-not-clone.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Write tests only for gap files.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

VS coverage FORMAT — gaps, not 100%

Goal

Produce fail-closed coverage honesty for whom: ThumbGate agents about to write tests — so they baseline gaps in one scope, skip enums/re-exports, and remeasure that same scope. Never 100%. Never Copilot Test Agent.

Constraints

NEVERALWAYS
Clone Test Agent / @test #solutionnpx thumbgate coverage-gap
cov-fail-under=100 / claim 100%Floor (default 50) on behavioral files
Tests for enums, re-exports, constants-onlySkip noBehavior kinds
Remeasure a different directorySame --scope before and after
Dual-edit scripts/test-coverage.js runnerFeature-detect include/exclude stays there

Reference

Examples (show, don't tell)

Weak: Run Copilot Test Agent on the whole repo and claim 81% → 100%.

Gold:

$ npx thumbgate coverage-gap --json --coverage=tests/fixtures/coverage-gap-before.json --scope=scripts/risk --floor=50
gaps: scripts/risk/decide.js 20%
skipped: scripts/risk/enums.js
$ npx thumbgate coverage-gap --json --before=...before.json --after=...after.json --scope=scripts/risk
ok: true

Procedures

npx thumbgate coverage-gap --json --coverage=<fixture.json> --scope=scripts/<area> --floor=50
npx thumbgate coverage-gap --json --before=<a> --after=<b> --scope=scripts/<area>
npm run test:coverage-gap
npm run test:coverage   # existing runner; feature-detects include/exclude
  1. Baseline the scoped files.
  2. Skip no-behavior.
  3. Write tests only for gap files.
  4. Remeasure the same scope.
  5. Refuse --clone-test-agent and --claim-100.

Rubric

  • gold compare same scope → ok=true
  • --claim-100 / @test #solution → ok=false
  • enum-only files are skipped, not gaps
  • doctor: npm run test:coverage-gap PASS
  • evidence: command output in the same turn

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