Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Python language expert -- debugging, packaging (PyInstaller/Nuitka/cx_Freeze), testing (pytest/unittest), type checking (mypy/pyright), async/concurrency patterns, performance optimization, dependency management, and cross-platform development. Handles everything from tracebacks to production builds.
.claude/skills/community-access-python-specialist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✓ | ＝ Same ✓ | -9% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 7% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | 25% | 0% |
| case-03 | ✗→✗ | ＝ Same ✗ | -2% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -11% | 0% |
Shared instructions
You are a Python language specialist -- a senior Python engineer who has shipped production applications, libraries, and tools across every major domain. You handle debugging, packaging, testing, type checking, concurrency, performance, and cross-platform development.
Knowledge domains: Python Development
pathlib.Path over os.path.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 11,737 | 10,237 | -13% | 1 | 1 | 0% | 2,137 | 2,101 | -2% | 0 | 0 | — |
case-01 | fail→fail | 14,498 | 11,091 | -23% | 1 | 1 | 0% | 2,718 | 2,414 | -11% | 0 | 0 | — |
case-02 | fail→fail | 3,127 | 11,137 | +256% | 1 | 1 | 0% | 454 | 2,203 | +385% | 0 | 0 | — |
case-04 | fail→fail | 11,252 | 7,894 | -30% | 1 | 1 | 0% | 2,013 | 1,841 | -9% | 0 | 0 | — |
case-05 | fail→fail | 15,615 | 9,611 | -38% | 1 | 1 | 0% | 2,980 | 2,187 | -27% | 0 | 0 | — |
case-06 | fail→fail | 15,453 | 11,561 | -25% | 1 | 1 | 0% | 2,543 | 2,300 | -10% | 0 | 0 | — |
case-07 | fail→fail | 15,653 | 14,617 | -7% | 1 | 1 | 0% | 2,675 | 3,079 | +15% | 0 | 0 | — |
case-08 | fail→fail | 17,605 | 15,873 | -10% | 1 | 1 | 0% | 3,286 | 3,600 | +10% | 0 | 0 | — |
case-09 | fail→fail | 9,785 | 6,681 | -32% | 1 | 1 | 0% | 1,732 | 1,544 | -11% | 0 | 0 | — |
case-10 | fail→fail | 12,722 | 11,069 | -13% | 1 | 1 | 0% | 2,266 | 2,372 | +5% | 0 | 0 | — |
case-11 | fail→fail | 10,176 | 5,385 | -47% | 1 | 1 | 0% | 1,797 | 1,320 | -27% | 0 | 0 | — |
case-12 | fail→fail | 19,571 | 14,464 | -26% | 1 | 1 | 0% | 3,483 | 2,816 | -19% | 0 | 0 | — |
case-13 | fail→fail | 12,383 | 13,274 | +7% | 1 | 1 | 0% | 2,276 | 2,748 | +21% | 0 | 0 | — |
case-14 | fail→fail | 9,836 | 6,851 | -30% | 1 | 1 | 0% | 1,644 | 1,539 | -6% | 0 | 0 | — |
case-15 | fail→fail | 15,119 | 13,059 | -14% | 1 | 1 | 0% | 2,710 | 2,643 | -2% | 0 | 0 | — |
case-16 | fail→fail | 16,142 | 12,725 | -21% | 1 | 1 | 0% | 2,836 | 2,685 | -5% | 0 | 0 | — |
case-17 | fail→fail | 10,822 | 8,458 | -22% | 1 | 1 | 0% | 1,945 | 1,816 | -7% | 0 | 0 | — |
case-18 | fail→fail | 11,699 | 7,616 | -35% | 1 | 1 | 0% | 2,159 | 1,806 | -16% | 0 | 0 | — |
case-19 | fail→fail | 12,984 | 11,082 | -15% | 1 | 1 | 0% | 2,408 | 2,302 | -4% | 0 | 0 | — |
case-20 | pass→pass | 15,025 | 12,714 | -15% | 1 | 1 | 0% | 2,861 | 2,594 | -9% | 0 | 0 | — |
case-21 | pass→pass | 11,706 | 10,609 | -9% | 1 | 1 | 0% | 2,027 | 2,171 | +7% | 0 | 0 | — |
case-22 | pass→pass | 16,002 | 16,917 | +6% | 1 | 1 | 0% | 2,925 | 3,657 | +25% | 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 0 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.