Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI. Use PROACTIVELY for Python development, optimization, or advanced Python patterns.
.claude/skills/dokhacgiakhoa-python-pro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✓→✗ | ▼ Worse | 22% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 26% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 21% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -8% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
You are a Python expert specializing in modern Python 3.12+ development with cutting-edge tools and practices from the 2024/2025 ecosystem.
Expert Python developer mastering Python 3.12+ features, modern tooling, and production-ready development practices. Deep knowledge of the current Python ecosystem including package management with uv, code quality with ruff, and building high-performance applications with async patterns.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 41,402 | 36,689 | -11% | 1 | 1 | 0% | 8,243 | 7,510 | -9% | 0 | 0 | — |
case-02 | fail→fail | 35,492 | 47,800 | +35% | 1 | 1 | 0% | 6,490 | 7,742 | +19% | 0 | 0 | — |
case-03 | fail→fail | 31,689 | 31,295 | -1% | 1 | 1 | 0% | 6,796 | 5,940 | -13% | 0 | 0 | — |
case-04 | pass→pass | 13,002 | 13,363 | +3% | 1 | 1 | 0% | 1,493 | 1,876 | +26% | 0 | 0 | — |
case-05 | pass→pass | 8,648 | 13,186 | +52% | 1 | 1 | 0% | 1,661 | 2,018 | +21% | 0 | 0 | — |
case-06 | pass→pass | 24,291 | 20,851 | -14% | 1 | 1 | 0% | 3,921 | 3,608 | -8% | 0 | 0 | — |
case-07 | pass→pass | 15,993 | 18,180 | +14% | 1 | 1 | 0% | 3,186 | 3,368 | +6% | 0 | 0 | — |
case-08 | pass→pass | 32,394 | 24,845 | -23% | 1 | 1 | 0% | 6,111 | 4,783 | -22% | 0 | 0 | — |
case-09 | pass→pass | 14,613 | 8,600 | -41% | 1 | 1 | 0% | 1,814 | 2,047 | +13% | 0 | 0 | — |
case-10 | pass→pass | 15,603 | 13,293 | -15% | 1 | 1 | 0% | 2,068 | 1,996 | -3% | 0 | 0 | — |
case-11 | pass→pass | 18,027 | 20,221 | +12% | 1 | 1 | 0% | 2,515 | 2,980 | +18% | 0 | 0 | — |
case-12 | pass→pass | 17,808 | 16,419 | -8% | 1 | 1 | 0% | 2,517 | 2,846 | +13% | 0 | 0 | — |
case-13 | pass→pass | 14,435 | 15,573 | +8% | 1 | 1 | 0% | 1,812 | 2,305 | +27% | 0 | 0 | — |
case-14 | pass→pass | 16,870 | 19,161 | +14% | 1 | 1 | 0% | 2,133 | 3,094 | +45% | 0 | 0 | — |
case-15 | pass→pass | 21,668 | 25,513 | +18% | 1 | 1 | 0% | 3,322 | 4,810 | +45% | 0 | 0 | — |
case-16 | pass→pass | 10,965 | 9,531 | -13% | 1 | 1 | 0% | 1,083 | 1,223 | +13% | 0 | 0 | — |
case-17 | pass→pass | 16,243 | 12,722 | -22% | 1 | 1 | 0% | 3,257 | 2,769 | -15% | 0 | 0 | — |
case-18 | pass→pass | 21,361 | 19,373 | -9% | 1 | 1 | 0% | 2,612 | 2,860 | +9% | 0 | 0 | — |
case-19 | pass→fail | 19,692 | 19,741 | +0% | 1 | 1 | 0% | 3,011 | 3,679 | +22% | 0 | 0 | — |
case-20 | pass→pass | 17,905 | 17,335 | -3% | 1 | 1 | 0% | 2,457 | 2,797 | +14% | 0 | 0 | — |
case-21 | pass→pass | 14,590 | 14,504 | -1% | 1 | 1 | 0% | 2,783 | 3,364 | +21% | 0 | 0 | — |
case-22 | pass→pass | 13,611 | 17,973 | +32% | 1 | 1 | 0% | 1,714 | 2,897 | +69% | 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 -5 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.
Other measured skills in the registry, with their headline benchmark lift.