agentleFS
insapption-projectsinsapption-projects/claude-agent-team-starter/.claude/skills/test-lint/SKILL.md

test-lint

Skill1 starsChanged 8 months agoMITView on GitHub

Runs the full quality gate for the specified technology: linter, type checker, and test suite. Collects ALL errors before reporting. Used at Step 7 (after implementation) and Step 11 (after fix). Returns PASS or FAIL with a structured error report.

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. Distinctive:

    Run the FULL suite for each tool before reporting anything.

    line 24
  2. Distinctive:

    Do NOT stop at the first error.

    line 25
  3. Very specific:

    If a tool is missing (e.g., phpstan not installed):

    line 157

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Skill: /test-lint

Usage

/test-lint {technology}

technology: laravel | react | react-native | frontend | all


Critical Rule: Collect ALL Errors First

Run the FULL suite for each tool before reporting anything. Do NOT stop at the first error. Gather everything, then present a complete error report so the fix plan can address all issues in one pass.


Laravel

# 1. Code style
./vendor/bin/pint --test

# 2. Static analysis (if PHPStan is configured)
./vendor/bin/phpstan analyse --no-progress

# 3. Tests
php artisan test --parallel

Parse each tool's output. Collect:

  • Pint: list of files with style violations
  • PHPStan: list of files with type/logic errors
  • Pest: list of failing test names with their error messages

React

# 1. TypeScript type check
npx tsc --noEmit

# 2. ESLint
npx eslint src --ext .ts,.tsx --max-warnings 0

# 3. Tests
pnpm test --run

Collect:

  • TypeScript: file + line + error message
  • ESLint: file + line + rule name + message
  • Vitest: test name + failure message + diff

React Native

# 1. TypeScript type check
npx tsc --noEmit

# 2. ESLint
npx eslint src --ext .ts,.tsx --max-warnings 0

# 3. Tests
jest --watchAll=false

# 4. Expo doctor
npx expo-doctor

Collect same as React plus any expo-doctor warnings.


Frontend (HTML/CSS/JS)

# 1. HTML validation (W3C CLI if available)
npx html-validate "**/*.html"

# 2. Stylelint
npx stylelint "**/*.css" --max-warnings 0

# 3. ESLint
npx eslint "**/*.js" --max-warnings 0

# 4. Tests (Playwright or Jest)
npx playwright test   # or jest --watchAll=false

Output Format

On PASS

──────────────────────────────────────────────────────────────
  QUALITY GATE: ✅  PASS
──────────────────────────────────────────────────────────────
Technology  : {technology}
Lint        : ✅  passed
Types       : ✅  passed  (or N/A)
Tests       : ✅  passed — {count} tests in {duration}
──────────────────────────────────────────────────────────────
Next step: /merge-main
──────────────────────────────────────────────────────────────

On FAIL

──────────────────────────────────────────────────────────────
  QUALITY GATE: ❌  FAIL
──────────────────────────────────────────────────────────────
Technology  : {technology}
Lint        : ❌  {N} errors  |  ✅ passed  |  N/A
Types       : ❌  {N} errors  |  ✅ passed  |  N/A
Tests       : ❌  {N} failed  |  ✅ passed  |  N/A
──────────────────────────────────────────────────────────────

LINT ERRORS ({N}):
  1. {file}:{line} — {rule} — {message}
  2. ...

TYPE ERRORS ({N}):
  1. {file}:{line} — {message}
  2. ...

TEST FAILURES ({N}):
  1. {test_name}
     Expected: {expected}
     Received: {received}
  2. ...
──────────────────────────────────────────────────────────────
Next step: /fix-plan
──────────────────────────────────────────────────────────────

On Tool Not Found

If a tool is missing (e.g., phpstan not installed):

⚠️  {tool} not found — skipping. Install with: {install_command}

Continue with remaining tools. Note the skip in the summary.

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.