Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user asks to write code efficiently, avoid over-engineering, reduce dependencies, or prevent unnecessary abstractions. Enforces a strict efficiency ladder: YAGNI, reuse, stdlib, native platform, existing deps — before writing any new code.
.claude/skills/alirezarezvani-minimalist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 46% | 0% |
You are highly efficient. The best code is the code never written.
Use this skill whenever the goal is to solve a problem with the least code possible. It prevents common AI failure modes: inventing helper classes for single-use logic, installing packages for one-line operations, and producing boilerplate that the user will never need.
Before writing any new code, stop at the first rung that holds:
When asked to implement something:
pathlib instead of a custom file helper."| Anti-Pattern | What to do instead | |---|---| | Installing a package for a one-liner | Use the standard library | | Writing a class for a single function | Write the function | | Adding a config file for a single hardcoded value | Hardcode it until there are 2+ uses | | Creating a utility module before it's reused anywhere | Write inline, extract later | | Adding docstrings/comments the user didn't ask for | Skip them | | Building error handling for errors that can't happen | Skip it | | Adding logging before the code works | Ship the code first |
engineering/strict-api — prevents hallucinated APIs when writing minimal code; use together.engineering/zero-hallucination-coder — enforces verified-only API usage.engineering/karpathy-coder — Karpathy-inspired behavioral guidelines for LLM-assisted coding.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,554 | 3,217 | -62% | 1 | 1 | 0% | 1,688 | 1,038 | -39% | 0 | 0 | — |
case-02 | fail→pass | 7,709 | 3,747 | -51% | 1 | 1 | 0% | 1,639 | 1,441 | -12% | 0 | 0 | — |
case-03 | fail→pass | 7,401 | 2,613 | -65% | 1 | 1 | 0% | 1,068 | 1,164 | +9% | 0 | 0 | — |
case-04 | pass→fail | 3,325 | 1,839 | -45% | 1 | 1 | 0% | 625 | 1,023 | +64% | 0 | 0 | — |
case-05 | fail→pass | 6,136 | 2,608 | -57% | 1 | 1 | 0% | 857 | 1,146 | +34% | 0 | 0 | — |
case-06 | fail→pass | 4,476 | 4,411 | -1% | 1 | 1 | 0% | 868 | 1,263 | +46% | 0 | 0 | — |
case-07 | pass→pass | 4,643 | 2,256 | -51% | 1 | 1 | 0% | 905 | 1,131 | +25% | 0 | 0 | — |
case-08 | fail→pass | 8,847 | 3,025 | -66% | 1 | 1 | 0% | 1,813 | 1,265 | -30% | 0 | 0 | — |
case-09 | fail→pass | 10,436 | 2,418 | -77% | 1 | 1 | 0% | 1,609 | 1,121 | -30% | 0 | 0 | — |
case-10 | pass→pass | 4,580 | 2,409 | -47% | 1 | 1 | 0% | 745 | 1,132 | +52% | 0 | 0 | — |
case-11 | fail→pass | 8,182 | 2,018 | -75% | 1 | 1 | 0% | 1,786 | 1,086 | -39% | 0 | 0 | — |
case-12 | fail→pass | 6,499 | 2,405 | -63% | 1 | 1 | 0% | 1,289 | 1,038 | -19% | 0 | 0 | — |
case-13 | fail→fail | 5,928 | 4,313 | -27% | 1 | 1 | 0% | 947 | 1,307 | +38% | 0 | 0 | — |
case-14 | fail→fail | 7,086 | 2,857 | -60% | 1 | 1 | 0% | 1,483 | 1,200 | -19% | 0 | 0 | — |
case-15 | pass→fail | 5,798 | 2,703 | -53% | 1 | 1 | 0% | 1,035 | 1,191 | +15% | 0 | 0 | — |
case-16 | fail→pass | 13,463 | 2,617 | -81% | 1 | 1 | 0% | 2,249 | 1,194 | -47% | 0 | 0 | — |
case-17 | pass→pass | 9,309 | 2,283 | -75% | 1 | 1 | 0% | 1,351 | 1,027 | -24% | 0 | 0 | — |
case-18 | pass→pass | 6,936 | 2,866 | -59% | 1 | 1 | 0% | 1,442 | 1,244 | -14% | 0 | 0 | — |
case-19 | pass→pass | 5,509 | 4,358 | -21% | 1 | 1 | 0% | 969 | 1,515 | +56% | 0 | 0 | — |
case-20 | pass→pass | 10,742 | 3,886 | -64% | 1 | 1 | 0% | 1,988 | 1,311 | -34% | 0 | 0 | — |
case-21 | pass→pass | 9,649 | 5,536 | -43% | 1 | 1 | 0% | 2,070 | 1,737 | -16% | 0 | 0 | — |
case-22 | pass→pass | 12,693 | 5,486 | -57% | 1 | 1 | 0% | 2,719 | 1,625 | -40% | 0 | 0 | — |
case-23 | pass→pass | 4,662 | 2,499 | -46% | 1 | 1 | 0% | 1,023 | 1,213 | +19% | 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. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 cases got worse with the skill loaded, and they are 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.
Other measured skills in the registry, with their headline benchmark lift.