Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →读取指定的文本文档内容，提炼核心主题，并自动将其重命名为高度概括的新文件名。
.claude/skills/sdsds222-auto-renamer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 213% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -64% | 0% |
执行auto-renamer: 读取文件内容并智能重命名 <SKILL_CLEAN: auto-renamer>
第一步：内容读取与洞察 调用系统读取工具（如 Get-Content、cat 或 read 工具）查看用户指定的文本文档内容。快速分析并提炼出该文档的核心主题和关键信息。
第二步：命名推演 基于提炼的核心内容，构思 3 个候选文件名。 命名原则：简明扼要、直击重点、严禁使用系统不允许的特殊字符（如 \ / : * ? " < > |）。
第三步：工具调用与重命名 选定最优的文件名后，自主调用系统执行工具（如 Rename-Item 等指令）对该文件进行物理重命名。
第四步：总结格式 【任务状态】：(如：已成功重命名 / 重命名失败) 【文件变更】：(原文件路径及名称) -> (新文件路径及名称) 【内容摘要】：(用一句话解释为什么提取这个名字，说明文件的核心内容)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,735 | 5,060 | -63% | 1 | 1 | 0% | 2,073 | 516 | -75% | 0 | 0 | — |
case-02 | fail→fail | 10,380 | 5,039 | -51% | 1 | 1 | 0% | 1,199 | 401 | -67% | 0 | 0 | — |
case-03 | fail→fail | 6,267 | 7,412 | +18% | 1 | 1 | 0% | 433 | 935 | +116% | 0 | 0 | — |
case-04 | fail→pass | 9,303 | 6,359 | -32% | 1 | 1 | 0% | 1,864 | 1,535 | -18% | 0 | 0 | — |
case-05 | fail→fail | 5,582 | 4,571 | -18% | 1 | 1 | 0% | 263 | 510 | +94% | 0 | 0 | — |
case-06 | fail→fail | 7,695 | 5,319 | -31% | 1 | 1 | 0% | 1,350 | 507 | -62% | 0 | 0 | — |
case-07 | fail→fail | 13,892 | 5,443 | -61% | 1 | 1 | 0% | 2,750 | 570 | -79% | 0 | 0 | — |
case-08 | fail→fail | 13,594 | 5,599 | -59% | 1 | 1 | 0% | 2,858 | 517 | -82% | 0 | 0 | — |
case-09 | fail→fail | 7,856 | 6,032 | -23% | 1 | 1 | 0% | 1,550 | 685 | -56% | 0 | 0 | — |
case-10 | fail→fail | 10,571 | 20,446 | +93% | 1 | 1 | 0% | 1,878 | 2,248 | +20% | 0 | 0 | — |
case-11 | fail→pass | 6,463 | 18,873 | +192% | 1 | 1 | 0% | 1,005 | 3,141 | +213% | 0 | 0 | — |
case-12 | fail→fail | 11,554 | 14,782 | +28% | 1 | 1 | 0% | 307 | 552 | +80% | 0 | 0 | — |
case-13 | fail→pass | 20,812 | 28,121 | +35% | 1 | 1 | 0% | 2,084 | 1,731 | -17% | 0 | 0 | — |
case-14 | pass→fail | 7,594 | 5,455 | -28% | 1 | 1 | 0% | 1,334 | 474 | -64% | 0 | 0 | — |
case-15 | fail→fail | 14,202 | 4,880 | -66% | 1 | 1 | 0% | 2,571 | 471 | -82% | 0 | 0 | — |
case-16 | fail→fail | 18,461 | 5,615 | -70% | 1 | 1 | 0% | 3,359 | 582 | -83% | 0 | 0 | — |
case-17 | fail→fail | 9,074 | 10,346 | +14% | 1 | 1 | 0% | 1,537 | 501 | -67% | 0 | 0 | — |
case-18 | fail→fail | 3,998 | 6,540 | +64% | 1 | 1 | 0% | 647 | 666 | +3% | 0 | 0 | — |
case-19 | fail→fail | 11,895 | 6,268 | -47% | 1 | 1 | 0% | 2,073 | 540 | -74% | 0 | 0 | — |
case-20 | pass→fail | 8,842 | 7,371 | -17% | 1 | 1 | 0% | 1,597 | 1,582 | -1% | 0 | 0 | — |
case-21 | fail→pass | 8,572 | 10,575 | +23% | 1 | 1 | 0% | 1,516 | 2,169 | +43% | 0 | 0 | — |
case-22 | pass→pass | 7,049 | 6,950 | -1% | 1 | 1 | 0% | 1,468 | 1,452 | -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, and 6 counted toward the lift figure. The other 16 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 +9 percentage points is the difference between those two pass rates over the 6 comparable cases. 7 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.