Florian BRUNIAUX
|
e6a8f1746f
|
docs: add quiz quality dashboard
**Dashboard Overview:**
- Executive summary (93.8% pass rate, +3.6% improvement)
- Category performance (4 tiers: S/A/B/C/D)
- Issue breakdown by type (0 critical, 13 warnings, 3 info)
- Improvement roadmap (3 phases)
- Root cause analysis (40% guide context extraction issues)
- Historical trends & velocity tracking
- Best practices learned
**Key Insights:**
- Perfect categories: Q05, Q07, Q11, Q13 (100%)
- At-risk categories: Q09 (79.3%), Q10 (75.0%)
- Main issue: Guide context extraction (8/16 issues)
- Velocity: +3.6% in 1 day (9 fixes)
**Next Milestone:** 95%+ pass rate (12 fixes needed)
File: claudedocs/quiz-quality-dashboard.md (tracking quality over time)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-02-04 18:10:03 +01:00 |
|
Florian BRUNIAUX
|
69f493591e
|
docs: add quiz audit report (6 critical issues found)
**Audit Results (256 questions):**
- Pass: 231 (90.2%)
- Issues: 25 (9.8%)
- Critical: 6 (wrong answer/factual error)
- Warning: 16 (ambiguous/outdated)
- Info: 3 (minor wording)
**Critical issues fixed** (see landing repo commit 94bc3db):
- Q01-001: npm vs curl for universal install
- Q03-011: CLAUDE.md location confusion
- Q08-019: auto:N threshold misunderstanding
- Q09-003: --headless flag doesn't exist
- Q09-029: Boris Cherny attribution
- Q12-012: wrong sub-agent count
**Warnings to review** (Priority 2):
- 5 ambiguities (missing guide context)
- 7 factual accuracy issues (stats without sources)
- 2 outdated info (version changes)
**Healthiest categories:** Q05, Q07, Q11, Q13 (100% pass rate)
**Need attention:** Q09 (79.3%), Q10 (75.0%)
Audit system: extract-audit-context.py → generate-audit-batches.py → 16 parallel agents → generate-audit-report.py
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-02-04 17:20:35 +01:00 |
|