Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Claude Code session analysis, tool call patterns, efficiency metrics, and anti-pattern detection
.claude/skills/session-analysis-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| Metrik | İyi | Orta | Kötü | |--------|-----|------|------| | Tokens per task | <50K | 50-100K | >100K | | Tool calls per task | <20 | 20-40 | >40 | | Repeated reads | 0-1 | 2-3 | >3 | | Blind edits | 0 | 1 | >1 | | Agent spawn efficiency | >80% useful | 50-80% | <50% |
| # | Pattern | Tespit | Fix | |---|---------|--------|-----| | 1 | Repeated Read | Aynı dosya 3+ kez okunmuş | Bilgiyi ilk seferde kaydet | | 2 | Wide Grep | Pattern'siz geniş arama | Spesifik pattern + glob filter | | 3 | Blind Edit | Dosya okumadan edit | Read → Edit sırası zorunlu | | 4 | Idle Agent | Agent spawn edilip sonuç kullanılmamış | Gereksiz spawn etme | | 5 | Cascade Fail | Aynı hata 3+ kez retry | Root cause analiz et | | 6 | Context Pollution | Ana context'te gereksiz büyük dosya okuma | Agent'a delege et | | 7 | Premature Agent | Basit iş için agent spawn | Direkt tool kullan | | 8 | Missing Parallel | Bağımsız işler sıralı | Paralel agent/tool call | | 9 | Over-Engineering | Basit fix için büyük refactoring | Minimal değişiklik |
pythondef calculate_efficiency(session): score = 100 # Penalties score -= session.repeated_reads * 5 # -5 per repeated read score -= session.blind_edits * 15 # -15 per blind edit score -= session.wide_greps * 3 # -3 per wide grep score -= session.idle_agents * 10 # -10 per idle agent score -= session.cascade_fails * 8 # -8 per cascade fail # Bonuses score += session.parallel_calls * 2 # +2 per parallel batch score += session.first_pass_success * 5 # +5 per first-try success return max(0, min(100, score))
markdown| Metrik | Session A | Session B | Delta | |--------|-----------|-----------|-------| | Total tokens | 45,000 | 120,000 | +167% | | Tool calls | 12 | 38 | +217% | | Time (min) | 3 | 12 | +300% | | Tasks completed | 2 | 2 | 0% | | Efficiency score | 88 | 42 | -52% |
bash# Session analizi btca sessions list --last 7d btca session <id> --metrics # Pattern detection btca session <id> --anti-patterns # Cost analysis btca sessions list --sort cost --desc
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.