Plugin:skill pairs now read as noun:verb commands instead of repeating the plugin name. Also added concise descriptions to all SKILL.md frontmatter. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
35 lines
1.1 KiB
Markdown
35 lines
1.1 KiB
Markdown
# Resume Tailoring - Testing Guidelines
|
|
|
|
## Manual Testing Checklist
|
|
|
|
### Test 1: Happy Path
|
|
- Provide JD with clear requirements + library with 10+ resumes
|
|
- Run all phases without skipping
|
|
- **Pass:** All files generated, JD coverage >70%, no errors
|
|
|
|
### Test 2: Minimal Library
|
|
- Provide only 2 resumes
|
|
- **Pass:** Graceful warning, reasonable output, gaps clearly identified
|
|
|
|
### Test 3: Research Failures
|
|
- Use obscure company with minimal online presence
|
|
- **Pass:** Warning about limited research, falls back to JD analysis, template still reasonable
|
|
|
|
### Test 4: Experience Discovery Value
|
|
- Run with deliberate gaps in library, conduct discovery
|
|
- **Pass:** Discovers undocumented experiences, integrates into resume, improves coverage
|
|
|
|
### Test 5: Title Reframing
|
|
- Test various role transitions
|
|
- **Pass:** Multiple options provided, truthfulness maintained, rationales clear
|
|
|
|
### Test 6: Multi-format Generation
|
|
- Generate MD, DOCX, PDF, Report
|
|
- **Pass:** All formats readable, formatting professional, content consistent
|
|
|
|
## Regression Testing
|
|
After any SKILL.md changes:
|
|
1. Re-run Test 1 (happy path)
|
|
2. Verify no functionality broken
|
|
3. Commit only if passes
|