ahundt/autorun/marketplace-test

Claude Code and agent skill by ahundt/autorun

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when the user asks to "test the marketplace plugins", "run marketplace tests", "check every installed plugin", or "/ar:marketplace-test". Walks the installed marketplace plugins, finds each one's test suite, runs them from the plugin's own directory, and reports per-plugin results.

Install

npx vskill@latest install ahundt/autorun/marketplace-test

SKILL.md

Marketplace Plugin Testing

<purpose>

You are running tests for all installed Claude Code marketplace plugins to ensure they work correctly together.

Your Task

Run the test suite for all plugins in the autorun marketplace that have tests, and provide a comprehensive report of the results.

</purpose>

<workflow>

Steps

  1. List all marketplace plugins

``bash ls -la ~/.claude/plugins/repos/ ``

  1. Check which plugins have tests

``bash for plugin in ~/.claude/plugins/repos/*; do if [ -d "$plugin/tests" ]; then echo "✓ $plugin has tests" fi done ``

  1. Run tests for each plugin with tests

```bash for plugin_dir in ~/.claude/plugins/repos/*; do plugin_name=$(basename "$plugin_dir")

# Check if plugin has tests if [ -d "$plugin_dir/tests" ]; then echo "" echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" echo "Testing plugin: $plugin_name" echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"

# Change to plugin directory cd "$plugin_dir" || continue

# Check if pytest.ini or pyproject.toml exists if [ -f "pytest.ini" ] || [ -f "pyproject.toml" ]; then # Run pytest with verbose output echo "Running pytest..." uv run python -m pytest tests/ -v --tb=short

# Check exit code if [ $? -eq 0 ]; then echo "✅ $plugin_name: All tests PASSED" else echo "❌ $plugin_name: Some tests FAILED" fi else echo "⚠️ $plugin_name: No pytest configuration found" fi fi done ```

  1. Generate summary report
  • Count total plugins tested
  • Count passed/failed
  • List any plugins with test failures
  • Report total test execution time

Important Notes

  • Run in parallel when possible: Use pytest -n auto for plugins that support it
  • Don't break active sessions: Tests should use temporary directories only
  • Skip plugins without tests: Only test plugins that have a tests/ directory
  • Report test coverage: If available, include coverage information
  • Check for UV compatibility: Verify plugins use UV for dependency management

</workflow>

<output_contract>

Example Output Format

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MARKETPLACE PLUGIN TEST REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Plugins tested: 3
Plugins with tests: 3
Plugins passed: 2
Plugins failed: 1
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ autorun: PASSED (15/15 tests)
✅ plan-export: PASSED (13/13 tests)
❌ pdf-extractor: FAILED (3/10 tests failed)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Total execution time: 45.2s
Failed tests details:
- pdf-extractor/test_extraction.py::test_pdf_parse: FAILED
- pdf-extractor/test_extraction.py::test_metadata: FAILED
- pdf-extractor/test_extraction.py::test_unicode: FAILED

</output_contract>

<additional_checks>

Additional Checks

For each plugin tested, also verify:

  1. pyproject.toml exists and has [tool.uv] section
  2. pytest.ini or pytest configuration in pyproject.toml
  3. tests/ directory with test_*.py files
  4. README.md or tests/README.md documenting how to run tests

</additional_checks>

<error_handling>

Error Handling

If a plugin's tests fail to run (e.g., import errors, missing dependencies):

  • Note the error in the report
  • Continue testing other plugins
  • Don't let one plugin's test failure stop the entire process

</error_handling>

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ahundt/autorun/marketplace-test/badge)](https://verified-skill.com/skills/ahundt/autorun/marketplace-test)

Something wrong with this skill or its page? Tell us.