Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Claude Code hooks configuration specialist. Use when creating hooks for tool validation, logging, notifications, or custom automation in Claude Code.
.claude/skills/aiskillstore-claude-hooks/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -75% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -54% | 0% |
Creates and configures hooks for Claude Code to automate workflows and extend functionality.
references/CLAUDE_HOOK.template.md - Hook configuration examples and patterns| Event | Trigger | Use Case | |-------|---------|----------| | PreToolUse | Before tool executes | Validation, blocking | | PostToolUse | After tool completes | Logging, cleanup | | Notification | Claude sends notification | Alerts | | Stop | Claude stops | Final reports |
Hooks are configured in ~/.claude/settings.json under the hooks key.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,777 | 6,164 | -43% | 1 | 1 | 0% | 1,876 | 1,358 | -28% | 0 | 0 | — |
case-02 | pass→pass | 9,399 | 2,905 | -69% | 1 | 1 | 0% | 1,712 | 792 | -54% | 0 | 0 | — |
case-03 | pass→pass | 6,241 | 2,887 | -54% | 1 | 1 | 0% | 998 | 694 | -30% | 0 | 0 | — |
case-04 | pass→pass | 12,382 | 5,243 | -58% | 1 | 1 | 0% | 1,776 | 1,034 | -42% | 0 | 0 | — |
case-05 | fail→pass | 11,425 | 8,396 | -27% | 1 | 1 | 0% | 1,771 | 943 | -47% | 0 | 0 | — |
case-06 | pass→pass | 11,266 | 2,896 | -74% | 1 | 1 | 0% | 1,834 | 662 | -64% | 0 | 0 | — |
case-07 | pass→pass | 8,970 | 3,241 | -64% | 1 | 1 | 0% | 1,615 | 818 | -49% | 0 | 0 | — |
case-08 | pass→pass | 14,737 | 15,467 | +5% | 1 | 1 | 0% | 2,277 | 2,804 | +23% | 0 | 0 | — |
case-09 | pass→pass | 12,448 | 8,513 | -32% | 1 | 1 | 0% | 1,884 | 1,601 | -15% | 0 | 0 | — |
case-10 | pass→pass | 9,690 | 4,282 | -56% | 1 | 1 | 0% | 1,411 | 909 | -36% | 0 | 0 | — |
case-11 | pass→pass | 16,439 | 19,705 | +20% | 1 | 1 | 0% | 2,472 | 2,689 | +9% | 0 | 0 | — |
case-12 | pass→pass | 7,699 | 6,258 | -19% | 1 | 1 | 0% | 1,129 | 1,145 | +1% | 0 | 0 | — |
case-13 | fail→pass | 20,405 | 11,171 | -45% | 1 | 1 | 0% | 3,246 | 2,237 | -31% | 0 | 0 | — |
case-14 | pass→pass | 5,069 | 2,955 | -42% | 1 | 1 | 0% | 905 | 736 | -19% | 0 | 0 | — |
case-15 | fail→pass | 15,094 | 2,575 | -83% | 1 | 1 | 0% | 2,551 | 640 | -75% | 0 | 0 | — |
case-16 | pass→pass | 3,916 | 2,809 | -28% | 1 | 1 | 0% | 513 | 568 | +11% | 0 | 0 | — |
case-17 | pass→pass | 4,183 | 1,726 | -59% | 1 | 1 | 0% | 688 | 462 | -33% | 0 | 0 | — |
case-18 | pass→pass | 15,425 | 9,125 | -41% | 1 | 1 | 0% | 2,213 | 1,512 | -32% | 0 | 0 | — |
case-19 | pass→pass | 12,116 | 5,520 | -54% | 1 | 1 | 0% | 1,823 | 1,043 | -43% | 0 | 0 | — |
case-20 | pass→pass | 10,150 | 8,519 | -16% | 1 | 1 | 0% | 1,752 | 1,741 | -1% | 0 | 0 | — |
case-21 | pass→pass | 9,799 | 5,688 | -42% | 1 | 1 | 0% | 1,628 | 1,121 | -31% | 0 | 0 | — |
case-22 | pass→pass | 13,028 | 12,319 | -5% | 1 | 1 | 0% | 2,103 | 2,263 | +8% | 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 +18 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.