testing
Use when running tests to validate implementations, collecting test evidence, or debugging failures. Load in TEST state. Covers unit tests (pytest/jest), API tests (curl), browser tests (Claude-in-Chrome), database verification. All results are code-verified, not LLM-judged.
When & Why to Use This Skill
This Claude skill provides a comprehensive framework for automated testing and quality assurance. It enables seamless execution of unit tests, API validations, and browser-based UI testing, ensuring all implementations are code-verified rather than LLM-judged for maximum reliability and efficient debugging.
Use Cases
- Automating unit test execution with frameworks like pytest and jest to validate core logic and prevent regressions.
- Verifying API endpoints using curl commands to ensure correct data handling, response structures, and status codes.
- Conducting browser-based UI testing via Claude-in-Chrome to identify front-end visual or functional issues.
- Performing database verification scripts to ensure data integrity and consistency after backend changes or migrations.
- Collecting and documenting systematic test evidence to streamline the debugging process and provide proof of implementation success.
| name | testing |
|---|---|
| description | "Use when running tests to validate implementations, collecting test evidence, or debugging failures. Load in TEST state. Covers unit tests (pytest/jest), API tests (curl), browser tests (Claude-in-Chrome), database verification. All results are code-verified, not LLM-judged." |
| keywords | test, verify, pytest, jest, api, browser, evidence |
Testing
Comprehensive testing for TEST state.
Instructions
- Run unit tests:
scripts/run-unit-tests.sh - Run API tests:
scripts/run-api-tests.sh - Run browser tests (if UI): via Claude-in-Chrome MCP
- Verify database (if data):
scripts/verify-database.sh - Collect evidence:
scripts/collect-evidence.sh - Report results (code verified, not judged)
Exit Criteria (Code Verified)
# All must return exit code 0
scripts/run-unit-tests.sh
scripts/run-api-tests.sh
[ -f "/tmp/test-evidence/results.json" ]
jq '.all_passed == true' /tmp/test-evidence/results.json
References
| File | Load When |
|---|---|
| references/unit-testing.md | Writing/running unit tests |
| references/api-testing.md | Testing API endpoints |
| references/browser-testing.md | UI testing with Chrome |
| references/database-testing.md | Database verification |