Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
.claude/skills/a5c-ai-hook-management/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -51% | 0% |
All hook changes are session-scoped. Disabling a hook only affects the current session and does not persist.
/hook:enable [hookName] -- Enable a disabled hook/hook:disable [hookName] -- Disable a hook for this session/hook:status -- Show all hook states and profiling dataclaudekit-orchestrator (hook pipeline setup)claudekit-safety-pipeline (hook profiling)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,157 | 7,489 | +5% | 1 | 1 | 0% | 1,133 | 1,970 | +74% | 0 | 0 | — |
case-02 | fail→pass | 6,865 | 2,174 | -68% | 1 | 1 | 0% | 1,092 | 725 | -34% | 0 | 0 | — |
case-03 | fail→pass | 6,334 | 2,156 | -66% | 1 | 1 | 0% | 1,079 | 692 | -36% | 0 | 0 | — |
case-04 | pass→pass | 7,893 | 1,393 | -82% | 1 | 1 | 0% | 1,387 | 579 | -58% | 0 | 0 | — |
case-05 | fail→pass | 10,791 | 2,073 | -81% | 1 | 1 | 0% | 1,753 | 697 | -60% | 0 | 0 | — |
case-06 | fail→pass | 8,147 | 1,856 | -77% | 1 | 1 | 0% | 1,266 | 623 | -51% | 0 | 0 | — |
case-07 | fail→fail | 9,792 | 1,622 | -83% | 1 | 1 | 0% | 1,589 | 616 | -61% | 0 | 0 | — |
case-08 | fail→pass | 6,999 | 2,010 | -71% | 1 | 1 | 0% | 1,195 | 704 | -41% | 0 | 0 | — |
case-09 | fail→pass | 7,667 | 1,767 | -77% | 1 | 1 | 0% | 1,297 | 652 | -50% | 0 | 0 | — |
case-10 | fail→pass | 7,757 | 2,238 | -71% | 1 | 1 | 0% | 1,370 | 771 | -44% | 0 | 0 | — |
case-11 | fail→pass | 12,958 | 1,127 | -91% | 1 | 1 | 0% | 2,188 | 545 | -75% | 0 | 0 | — |
case-12 | fail→pass | 6,000 | 1,356 | -77% | 1 | 1 | 0% | 966 | 592 | -39% | 0 | 0 | — |
case-13 | fail→pass | 14,429 | 1,277 | -91% | 1 | 1 | 0% | 2,479 | 560 | -77% | 0 | 0 | — |
case-14 | fail→pass | 12,731 | 973 | -92% | 1 | 1 | 0% | 2,022 | 492 | -76% | 0 | 0 | — |
case-15 | fail→pass | 12,799 | 990 | -92% | 1 | 1 | 0% | 2,189 | 497 | -77% | 0 | 0 | — |
case-16 | fail→pass | 13,561 | 1,685 | -88% | 1 | 1 | 0% | 2,236 | 664 | -70% | 0 | 0 | — |
case-17 | fail→pass | 10,767 | 2,054 | -81% | 1 | 1 | 0% | 1,842 | 714 | -61% | 0 | 0 | — |
case-18 | fail→pass | 12,136 | 1,274 | -90% | 1 | 1 | 0% | 1,833 | 520 | -72% | 0 | 0 | — |
case-19 | fail→pass | 12,331 | 1,480 | -88% | 1 | 1 | 0% | 2,079 | 596 | -71% | 0 | 0 | — |
case-20 | fail→fail | 13,786 | 11,625 | -16% | 1 | 1 | 0% | 2,567 | 2,769 | +8% | 0 | 0 | — |
case-21 | fail→fail | 9,680 | 8,867 | -8% | 1 | 1 | 0% | 1,979 | 2,190 | +11% | 0 | 0 | — |
case-22 | fail→fail | 9,140 | 6,531 | -29% | 1 | 1 | 0% | 1,770 | 1,590 | -10% | 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. The headline lift of +77 percentage points is the difference between those two pass rates over the 22 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.