Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Optional Sergo examples for cache formats and reporting templates.
.claude/skills/github-sergo-examples/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -42% | 0% |
Use this skill only when Sergo needs concrete format examples.
json{ "last_updated": "2026-01-15T12:00:00Z", "tools": [ {"name": "tool-name-1", "description": "..."}, {"name": "tool-name-2", "description": "..."} ] }
json{"date": "2026-01-14", "strategy": "symbol-analysis", "tools": ["find-symbol", "get-definition"], "findings": 3, "tasks_created": 2, "success_score": 8} {"date": "2026-01-13", "strategy": "type-inspection", "tools": ["get-hover", "get-type"], "findings": 5, "tasks_created": 3, "success_score": 9}
markdown### Task [N]: [Short Title] **Issue Type**: [Symbol Analysis / Type Inspection / etc.] **Problem**: [Clear description] **Location(s)**: [file paths and line references] **Impact**: Severity, affected files, risk **Recommendation**: [Specific fix] **Validation**: Existing tests, Serena verification, related-pattern check, docs if needed **Estimated Effort**: [Small/Medium/Large]
Follow the reporting skill (headers ###+, <details> for long sections):
markdown### 🔬 Sergo Report: [Strategy Name] **Date**: [YYYY-MM-DD] **Strategy**: [Name] **Success Score**: [X/10] ### Executive Summary ### 🛠️ Serena Tools Update ### 📊 Strategy Selection ### 🔍 Analysis Execution <details> <summary><b>📋 Detailed Findings</b></summary> </details> ### ✅ Improvement Tasks Generated ### 📈 Success Metrics <details> <summary><b>📊 Historical Context</b></summary> </details> ### 🎯 Recommendations ### 🔄 Next Run Preview
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 17,883 | 6,408 | -64% | 1 | 1 | 0% | 3,257 | 1,611 | -51% | 0 | 0 | — |
case-12 | fail→pass | 11,293 | 4,070 | -64% | 1 | 1 | 0% | 1,793 | 1,092 | -39% | 0 | 0 | — |
case-01 | fail→pass | 11,723 | 2,521 | -78% | 1 | 1 | 0% | 1,891 | 918 | -51% | 0 | 0 | — |
case-02 | fail→pass | 10,325 | 9,591 | -7% | 1 | 1 | 0% | 1,447 | 1,795 | +24% | 0 | 0 | — |
case-03 | pass→pass | 13,611 | 2,623 | -81% | 1 | 1 | 0% | 2,341 | 942 | -60% | 0 | 0 | — |
case-04 | fail→pass | 14,229 | 4,324 | -70% | 1 | 1 | 0% | 2,250 | 1,297 | -42% | 0 | 0 | — |
case-05 | pass→pass | 13,750 | 2,855 | -79% | 1 | 1 | 0% | 2,045 | 1,014 | -50% | 0 | 0 | — |
case-07 | fail→pass | 17,252 | 4,135 | -76% | 1 | 1 | 0% | 2,705 | 1,248 | -54% | 0 | 0 | — |
case-08 | fail→pass | 11,540 | 2,967 | -74% | 1 | 1 | 0% | 1,916 | 1,003 | -48% | 0 | 0 | — |
case-09 | pass→pass | 15,106 | 5,107 | -66% | 1 | 1 | 0% | 2,226 | 1,324 | -41% | 0 | 0 | — |
case-10 | fail→fail | 9,264 | 2,335 | -75% | 1 | 1 | 0% | 1,385 | 906 | -35% | 0 | 0 | — |
case-11 | fail→pass | 13,541 | 2,476 | -82% | 1 | 1 | 0% | 2,068 | 878 | -58% | 0 | 0 | — |
case-13 | fail→pass | 14,165 | 2,120 | -85% | 1 | 1 | 0% | 2,404 | 861 | -64% | 0 | 0 | — |
case-14 | pass→pass | 13,345 | 2,765 | -79% | 1 | 1 | 0% | 2,284 | 869 | -62% | 0 | 0 | — |
case-15 | fail→fail | 9,672 | 3,373 | -65% | 1 | 1 | 0% | 1,320 | 951 | -28% | 0 | 0 | — |
case-16 | pass→pass | 13,695 | 3,670 | -73% | 1 | 1 | 0% | 2,002 | 1,025 | -49% | 0 | 0 | — |
case-17 | fail→fail | 6,504 | 2,721 | -58% | 1 | 1 | 0% | 873 | 792 | -9% | 0 | 0 | — |
case-18 | fail→fail | 8,844 | 1,708 | -81% | 1 | 1 | 0% | 1,419 | 657 | -54% | 0 | 0 | — |
case-19 | pass→pass | 11,940 | 3,302 | -72% | 1 | 1 | 0% | 2,014 | 926 | -54% | 0 | 0 | — |
case-20 | pass→pass | 7,936 | 4,294 | -46% | 1 | 1 | 0% | 1,279 | 1,207 | -6% | 0 | 0 | — |
case-21 | pass→pass | 9,827 | 5,124 | -48% | 1 | 1 | 0% | 1,490 | 1,214 | -19% | 0 | 0 | — |
case-22 | pass→pass | 9,040 | 5,827 | -36% | 1 | 1 | 0% | 1,450 | 1,466 | +1% | 0 | 0 | — |
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 +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/9/2026 | +88% |
Other measured skills in the registry, with their headline benchmark lift.