agentleFS
Sign inStart free
SkillkeelSkillkeel/skillkeel-starter/skills/test-gap-finder/SKILL.md

test-gap-finder

Skill3 starsChanged 57 days agoMITView on GitHub

Use when the user asks what to test next, where coverage is weak, or before a refactor of untested code. Maps source modules to existing tests, ranks untested modules by churn and size, and proposes the five highest-value tests with concrete names and cases, without writing them unasked.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. navjyotnishant/nj-agents★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Very specific:

    If a coverage report is cheap, run it: pytest --cov --cov-report=term-missing -q, npx vitest run --coverage, go test -cover ./....

    line 11
  2. Distinctive:

    Do not claim a coverage percentage unless a coverage tool produced it.

    line 17
  3. Distinctive:

    Do not propose tests for generated code, vendored code, or trivial getters.

    line 18

≈ “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

test-gap-finder

Procedure

  1. Detect test layout: tests/, __tests__/, *_test.go, *.test.ts, test_*.py, spec/. Detect the runner from config (jest, vitest, pytest, go test, cargo test).
  2. Build the map: list source files (exclude generated, vendored, migrations). For each, find tests that import or name it (grep the module path/name inside test files). Result: module | test files | test count (rough: count of test functions).
  3. If a coverage report is cheap, run it: pytest --cov --cov-report=term-missing -q, npx vitest run --coverage, go test -cover ./.... Skip if it takes > 2 min or needs services.
  4. Rank untested/under-tested modules by: recent churn (git log --since=90.days --format='' --name-only | sort | uniq -c), size (wc -l), and whether they sit on a critical path (auth, payments, data writes, public API).
  5. For the top 5, propose tests: file path, test names, and 2 to 4 concrete cases each (happy path, boundary, failure). Reference the module's real function signatures (read the code).
  6. Output a table plus the proposals. Ask before writing any test files; if approved, write them following the repo's existing test style and run them.

Rules

  • Do not claim a coverage percentage unless a coverage tool produced it.
  • Do not propose tests for generated code, vendored code, or trivial getters.
  • Proposed cases must be derivable from the code read in this session.

Verify

Maintainers: bash evals/run.sh /tmp/skillkeel-evals test-gap-finder from the plugin root runs this case and grades it; records and transcripts sit in evals/test-gap-finder/. evals/test-gap-finder/: fixture Python package with auth.py (untested, high churn), utils.py (tested), payments.py (untested); expected: auth.py and payments.py ranked top, utils.py not proposed, ≥2 concrete cases per proposal, no test files written.

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