Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →【Bug 诊断专用】当遇到程序错误、异常行为、性能问题、功能故障时必须使用本技能。触发关键词：报错、Bug、问题、异常、故障、不工作、诊断、排查、修复。本技能提供系统性根因分析，输出详细诊断报告和可执行修复方案，包含代码位置引用、步骤指导、注意事项。仅提供分析和方案，不直接修改代码。
.claude/skills/aiskillstore-bug-diagnose-and-root-cause-and-fix/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 30% | 0% |
本技能提供系统性的 Bug 诊断能力，专注于分析问题根源并提供详细的解决方案指导。
诊断问题根本原因，输出详细的解决方案报告，为用户提供修复指导。
本技能输出完整的诊断报告，用户可根据此报告进行修复：
问题概述： 简述用户报告的问题
环境信息：
根本原因分析：
文件路径:行号 格式）解决方案：
方案一：推荐/备选]
文件路径具体命令方案二（如有）：...
注意事项：
文件:行号 格式标注所有相关代码位置| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,698 | 6,021 | -76% | 1 | 1 | 0% | 3,926 | 919 | -77% | 0 | 0 | — |
case-02 | fail→pass | 20,583 | 19,538 | -5% | 1 | 1 | 0% | 3,073 | 3,719 | +21% | 0 | 0 | — |
case-03 | fail→pass | 24,176 | 22,263 | -8% | 1 | 1 | 0% | 3,657 | 4,208 | +15% | 0 | 0 | — |
case-04 | fail→pass | 21,630 | 20,096 | -7% | 1 | 1 | 0% | 3,847 | 4,095 | +6% | 0 | 0 | — |
case-05 | fail→pass | 30,588 | 22,701 | -26% | 1 | 1 | 0% | 4,869 | 4,492 | -8% | 0 | 0 | — |
case-06 | fail→fail | 21,658 | 21,475 | -1% | 1 | 1 | 0% | 3,332 | 3,858 | +16% | 0 | 0 | — |
case-07 | fail→pass | 23,713 | 25,806 | +9% | 1 | 1 | 0% | 4,025 | 5,221 | +30% | 0 | 0 | — |
case-08 | fail→pass | 24,780 | 22,936 | -7% | 1 | 1 | 0% | 4,135 | 4,463 | +8% | 0 | 0 | — |
case-09 | fail→pass | 23,685 | 22,125 | -7% | 1 | 1 | 0% | 3,953 | 4,204 | +6% | 0 | 0 | — |
case-10 | pass→fail | 6,906 | 7,198 | +4% | 1 | 1 | 0% | 1,002 | 1,495 | +49% | 0 | 0 | — |
case-11 | pass→fail | 13,224 | 10,837 | -18% | 1 | 1 | 0% | 2,197 | 2,489 | +13% | 0 | 0 | — |
case-12 | pass→pass | 23,816 | 19,287 | -19% | 1 | 1 | 0% | 4,009 | 4,145 | +3% | 0 | 0 | — |
case-13 | fail→pass | 20,694 | 23,442 | +13% | 1 | 1 | 0% | 3,216 | 4,164 | +29% | 0 | 0 | — |
case-14 | fail→pass | 16,573 | 17,053 | +3% | 1 | 1 | 0% | 2,715 | 3,183 | +17% | 0 | 0 | — |
case-15 | fail→pass | 24,472 | 33,827 | +38% | 1 | 1 | 0% | 3,771 | 3,944 | +5% | 0 | 0 | — |
case-16 | fail→pass | 24,058 | 20,611 | -14% | 1 | 1 | 0% | 3,833 | 3,901 | +2% | 0 | 0 | — |
case-17 | fail→pass | 17,632 | 20,501 | +16% | 1 | 1 | 0% | 2,862 | 3,445 | +20% | 0 | 0 | — |
case-18 | fail→fail | 29,553 | 18,522 | -37% | 1 | 1 | 0% | 3,232 | 3,276 | +1% | 0 | 0 | — |
case-19 | fail→fail | 19,427 | 6,152 | -68% | 1 | 1 | 0% | 3,023 | 747 | -75% | 0 | 0 | — |
case-20 | fail→fail | 16,573 | 6,595 | -60% | 1 | 1 | 0% | 2,727 | 1,521 | -44% | 0 | 0 | — |
case-21 | fail→fail | 21,562 | 29,198 | +35% | 1 | 1 | 0% | 3,576 | 3,449 | -4% | 0 | 0 | — |
case-22 | fail→fail | 17,195 | 14,363 | -16% | 1 | 1 | 0% | 2,867 | 2,971 | +4% | 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 20 counted toward the lift figure. The other 2 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 +45 percentage points is the difference between those two pass rates over the 20 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.