Agent skill
run-tests
Run the full test suite with linting, type checking, and code quality audit
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/run-tests-benzwick-slicermousemaster
SKILL.md
Run Tests Skill
Run the full test suite with linting, type checking, and code quality audit.
When to Use
- After making code changes
- Before committing
- To verify code quality
- When asked to "run tests" or "check the code"
Quick Run
Execute all checks in sequence:
# 1. Unit tests
uv run pytest MouseMaster/Testing/Python/ -v --tb=short
# 2. Linter
uv run ruff check .
# 3. Type checker
uv run mypy MouseMaster/MouseMasterLib/
# 4. Code quality audit
grep -rn "except.*:" MouseMaster/ --include="*.py" -A1 | grep -B1 "pass$" || echo "No except:pass found"
Expected Results
| Check | Expected |
|---|---|
| Unit tests | 67+ passed |
| Ruff | 0 errors (or 1 import order) |
| Mypy | 0 errors |
| Audit | No except:pass patterns |
If Tests Fail
- Read the failing test output
- Identify which test failed and why
- Read the test file to understand what it checks
- Read the code being tested
- Fix the issue
- Re-run tests
If Lint Fails
Auto-fix safe issues:
uv run ruff check --fix .
For other issues, review and fix manually.
If Audit Finds Issues
Follow /fix-bad-practices skill to correct:
except: pass→ specific exception + loggingexcept Exception→ specific exception types- Silent continuation → explicit error handling
Report Format
After running, summarize:
## Test Results
| Check | Status |
|-------|--------|
| Tests | ✓ 67 passed |
| Lint | ✓ clean |
| Types | ✓ clean |
| Audit | ✓ no violations |
Issues: None / [list issues]
Related
- Agent:
.claude/agents/test-runner.md- Full autonomous workflow - Skill:
/audit-code-quality- Detailed audit patterns - Skill:
/fix-bad-practices- Fix patterns
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?