Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Get skill detailed instructions and usage guide (Level 2 disclosure). When you need to understand how to use a skill, check skill capabilities, or learn skill parameters.
.claude/skills/openakita-get-skill-info/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -64% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -32% | 0% |
获取技能的详细信息和指令（Level 2 披露）。
| 参数 | 类型 | 必填 | 说明 | |-----|------|-----|------| | skill_name | string | 是 | 技能名称 |
大多数外部技能（xlsx, docx, pptx, pdf 等）是指令型技能，没有预置脚本。 读取指令后应按照指令编写代码，通过 run_shell 执行，而非调用 run_skill_script。
list-skills: 列出所有技能run-shell: 执行按技能指令编写的代码| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,710 | 3,326 | -66% | 1 | 1 | 0% | 1,684 | 293 | -83% | 0 | 0 | — |
case-02 | fail→fail | 15,170 | 3,294 | -78% | 1 | 1 | 0% | 2,388 | 332 | -86% | 0 | 0 | — |
case-03 | fail→fail | 13,161 | 3,540 | -73% | 1 | 1 | 0% | 2,639 | 361 | -86% | 0 | 0 | — |
case-04 | fail→pass | 6,214 | 3,410 | -45% | 1 | 1 | 0% | 962 | 852 | -11% | 0 | 0 | — |
case-05 | fail→fail | 7,455 | 4,325 | -42% | 1 | 1 | 0% | 1,325 | 347 | -74% | 0 | 0 | — |
case-06 | fail→fail | 5,966 | 7,264 | +22% | 1 | 1 | 0% | 976 | 477 | -51% | 0 | 0 | — |
case-07 | fail→fail | 5,064 | 6,538 | +29% | 1 | 1 | 0% | 843 | 592 | -30% | 0 | 0 | — |
case-08 | fail→pass | 7,885 | 2,143 | -73% | 1 | 1 | 0% | 1,318 | 478 | -64% | 0 | 0 | — |
case-09 | fail→pass | 11,610 | 3,944 | -66% | 1 | 1 | 0% | 2,018 | 838 | -58% | 0 | 0 | — |
case-10 | pass→fail | 7,040 | 5,952 | -15% | 1 | 1 | 0% | 1,175 | 619 | -47% | 0 | 0 | — |
case-11 | pass→pass | 5,198 | 3,336 | -36% | 1 | 1 | 0% | 813 | 634 | -22% | 0 | 0 | — |
case-12 | pass→pass | 14,628 | 3,400 | -77% | 1 | 1 | 0% | 2,181 | 827 | -62% | 0 | 0 | — |
case-13 | pass→fail | 7,485 | 4,872 | -35% | 1 | 1 | 0% | 1,190 | 468 | -61% | 0 | 0 | — |
case-14 | pass→pass | 7,426 | 2,137 | -71% | 1 | 1 | 0% | 1,231 | 518 | -58% | 0 | 0 | — |
case-15 | pass→pass | 5,941 | 3,866 | -35% | 1 | 1 | 0% | 955 | 858 | -10% | 0 | 0 | — |
case-16 | fail→pass | 9,052 | 2,790 | -69% | 1 | 1 | 0% | 1,534 | 614 | -60% | 0 | 0 | — |
case-17 | fail→fail | 3,957 | 4,757 | +20% | 1 | 1 | 0% | 628 | 424 | -32% | 0 | 0 | — |
case-18 | fail→pass | 9,966 | 5,366 | -46% | 1 | 1 | 0% | 1,754 | 1,185 | -32% | 0 | 0 | — |
case-19 | pass→pass | 7,532 | 5,636 | -25% | 1 | 1 | 0% | 1,236 | 564 | -54% | 0 | 0 | — |
case-20 | fail→fail | 9,577 | 6,933 | -28% | 1 | 1 | 0% | 1,739 | 497 | -71% | 0 | 0 | — |
case-21 | fail→pass | 8,194 | 6,691 | -18% | 1 | 1 | 0% | 1,424 | 1,390 | -2% | 0 | 0 | — |
case-22 | pass→pass | 6,670 | 3,305 | -50% | 1 | 1 | 0% | 982 | 675 | -31% | 0 | 0 | — |
case-23 | pass→pass | 4,178 | 3,804 | -9% | 1 | 1 | 0% | 654 | 786 | +20% | 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, and 13 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +17 percentage points is the difference between those two pass rates over the 13 comparable cases. 3 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.