Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Inspect WeChat Official Account followers and safely review or update custom menus with explicit before-and-after confirmation.
.claude/skills/devin-axis-wechat-official-community/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -75% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -5% | 0% |
用于理解关注者范围和管理自定义菜单。
list-followers 获取有界分页结果，不导出或扩大收集用户数据。get-menu，展示现有菜单与拟议完整菜单的差异。update-menu；菜单链接、事件 key 和跳转目标不得猜测。| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,344 | 7,559 | -43% | 1 | 1 | 0% | 1,189 | 477 | -60% | 0 | 0 | — |
case-02 | fail→fail | 14,618 | 22,109 | +51% | 1 | 1 | 0% | 1,430 | 733 | -49% | 0 | 0 | — |
case-13 | fail→fail | 10,905 | 15,893 | +46% | 1 | 1 | 0% | 891 | 596 | -33% | 0 | 0 | — |
case-14 | fail→fail | 13,362 | 16,677 | +25% | 1 | 1 | 0% | 1,232 | 786 | -36% | 0 | 0 | — |
case-03 | fail→fail | 17,746 | 15,891 | -10% | 1 | 1 | 0% | 2,013 | 603 | -70% | 0 | 0 | — |
case-04 | fail→pass | 22,632 | 9,400 | -58% | 1 | 1 | 0% | 3,063 | 760 | -75% | 0 | 0 | — |
case-05 | fail→fail | 29,374 | 13,495 | -54% | 1 | 1 | 0% | 2,731 | 1,477 | -46% | 0 | 0 | — |
case-06 | fail→fail | 10,636 | 8,787 | -17% | 1 | 1 | 0% | 824 | 766 | -7% | 0 | 0 | — |
case-07 | fail→pass | 15,436 | 12,719 | -18% | 1 | 1 | 0% | 1,705 | 1,222 | -28% | 0 | 0 | — |
case-08 | fail→pass | 15,012 | 16,786 | +12% | 1 | 1 | 0% | 1,549 | 1,983 | +28% | 0 | 0 | — |
case-09 | fail→fail | 19,017 | 11,181 | -41% | 1 | 1 | 0% | 2,298 | 1,030 | -55% | 0 | 0 | — |
case-10 | fail→fail | 15,351 | 11,305 | -26% | 1 | 1 | 0% | 1,444 | 1,046 | -28% | 0 | 0 | — |
case-11 | pass→pass | 20,946 | 16,009 | -24% | 1 | 1 | 0% | 2,343 | 1,636 | -30% | 0 | 0 | — |
case-12 | fail→fail | 13,325 | 11,921 | -11% | 1 | 1 | 0% | 1,214 | 1,189 | -2% | 0 | 0 | — |
case-15 | fail→fail | 13,396 | 16,125 | +20% | 1 | 1 | 0% | 1,572 | 639 | -59% | 0 | 0 | — |
case-16 | fail→fail | 14,283 | 12,412 | -13% | 1 | 1 | 0% | 1,507 | 1,283 | -15% | 0 | 0 | — |
case-17 | fail→pass | 24,684 | 13,260 | -46% | 1 | 1 | 0% | 3,317 | 1,325 | -60% | 0 | 0 | — |
case-18 | fail→pass | 10,920 | 9,621 | -12% | 1 | 1 | 0% | 868 | 822 | -5% | 0 | 0 | — |
case-19 | fail→fail | 18,483 | 19,181 | +4% | 1 | 1 | 0% | 2,375 | 820 | -65% | 0 | 0 | — |
case-20 | pass→pass | 16,556 | 9,507 | -43% | 1 | 1 | 0% | 2,019 | 921 | -54% | 0 | 0 | — |
case-21 | pass→pass | 16,190 | 10,507 | -35% | 1 | 1 | 0% | 2,143 | 1,049 | -51% | 0 | 0 | — |
case-22 | pass→pass | 18,909 | 17,353 | -8% | 1 | 1 | 0% | 2,524 | 2,501 | -1% | 0 | 0 | — |
case-23 | pass→pass | 18,523 | 16,108 | -13% | 1 | 1 | 0% | 2,555 | 2,140 | -16% | 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 19 counted toward the lift figure. The other 4 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 +22 percentage points is the difference between those two pass rates over the 19 comparable cases.
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.