ReddRadar
Agent skill
test-from-docs
Generate and execute test plans based on documentation. Use after implementation to verify changes work correctly. Integrates with browser testing for UI verification.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/test-from-docs
SKILL.md
Test From Docs
Use documentation as the authoritative test blueprint. Tests verify intended behavior (from docs), not just current behavior.
When to Use
- After implementing a feature or fix
- Before marking work as complete
- When user asks "does this work?"
- As part of pre-PR validation
Risk-Based Test Selection
Calculate Risk Score
| Factor | Points |
|---|---|
| Touches auth/RLS | +3 |
| Touches billing | +3 |
| Touches schema | +2 |
| Touches AI/prompts | +2 |
| Multi-feature change | +2 |
| User-facing workflow | +1 |
| New code (not fix) | +1 |
Select Test Depth
| Score | Depth | What to Run |
|---|---|---|
| 0-2 | Light | Static + primary feature checklist |
| 3-5 | Standard | Light + impacted features + 1 workflow |
| 6-8 | Thorough | Standard + browser verification + regression |
| 9+ | Comprehensive | Full workflow suite + edge cases |
Test Phases
- Static Analysis —
npx tsc --noEmit && npm run lint - Feature Checklist — Run items from feature doc's Testing Checklist
- Integration — Verify cross-feature integration points
- Browser — Visual verification with Playwright MCP
- Workflow Smoke — One complete user journey
- Regression — Verify coupled features still work
Output
## Test Report — [feature] — [date]
**Risk Score**: [n] ([depth level])
| Phase | Passed | Failed |
|-------|--------|--------|
| Static | [n] | [n] |
| Feature | [n] | [n] |
| Browser | [n] | [n] |
| Workflow | [n] | [n] |
**Overall**: ✅ PASS / ❌ FAIL
### Failures
[Test name, expected, actual, evidence]
**Ready for Merge**: [Yes/No]
Related
- Phase details: See reference/test-phases.md
- Templates by change type: See reference/test-templates.md
- Browser testing commands: See reference/browser-testing.md
- For comprehensive testing:
/spawn-test-agent
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?