Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create runbook creator operations. Auto-activating skill for Technical Documentation. Triggers on: runbook creator, runbook creator Part of the Technical Documentation skill category. Use when working with runbook creator functionality. Trigger with phrases like "runbook creator", "runbook creator", "runbook".
.claude/skills/dicklesworthstone-runbook-creator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 33% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 7% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -22% | 0% |
This skill provides automated assistance for runbook creator tasks within the Technical Documentation domain.
This skill activates automatically when you:
Example: Basic Usage Request: "Help me with runbook creator" Result: Provides step-by-step guidance and generates appropriate configurations
| Error | Cause | Solution | |-------|-------|----------| | Configuration invalid | Missing required fields | Check documentation for required parameters | | Tool not found | Dependency not installed | Install required tools per prerequisites | | Permission denied | Insufficient access | Verify credentials and permissions |
Part of the Technical Documentation skill category. Tags: documentation, markdown, api-docs, readme, technical-writing
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 28,440 | 32,394 | +14% | 1 | 1 | 0% | 3,789 | 5,035 | +33% | 0 | 0 | — |
case-02 | pass→pass | 27,158 | 25,144 | -7% | 1 | 1 | 0% | 3,027 | 3,637 | +20% | 0 | 0 | — |
case-03 | pass→pass | 28,428 | 28,557 | +0% | 1 | 1 | 0% | 3,950 | 4,238 | +7% | 0 | 0 | — |
case-04 | pass→pass | 27,642 | 21,152 | -23% | 1 | 1 | 0% | 4,057 | 3,181 | -22% | 0 | 0 | — |
case-05 | pass→pass | 24,796 | 29,471 | +19% | 1 | 1 | 0% | 3,217 | 4,649 | +45% | 0 | 0 | — |
case-06 | fail→fail | 63,456 | 59,251 | -7% | 1 | 1 | 0% | 1,374 | 1,140 | -17% | 0 | 0 | — |
case-07 | fail→fail | 24,637 | 26,154 | +6% | 1 | 1 | 0% | 3,581 | 4,250 | +19% | 0 | 0 | — |
case-08 | pass→pass | 24,975 | 22,595 | -10% | 1 | 1 | 0% | 3,528 | 3,409 | -3% | 0 | 0 | — |
case-09 | fail→fail | 24,364 | 26,446 | +9% | 1 | 1 | 0% | 3,337 | 4,148 | +24% | 0 | 0 | — |
case-10 | fail→fail | 29,464 | 32,890 | +12% | 1 | 1 | 0% | 4,166 | 5,374 | +29% | 0 | 0 | — |
case-11 | fail→fail | 28,109 | 27,544 | -2% | 1 | 1 | 0% | 3,544 | 3,960 | +12% | 0 | 0 | — |
case-12 | pass→pass | 24,022 | 27,950 | +16% | 1 | 1 | 0% | 3,118 | 4,661 | +49% | 0 | 0 | — |
case-13 | pass→pass | 33,342 | 32,665 | -2% | 1 | 1 | 0% | 4,517 | 4,851 | +7% | 0 | 0 | — |
case-14 | fail→fail | 25,838 | 35,378 | +37% | 1 | 1 | 0% | 3,414 | 5,581 | +63% | 0 | 0 | — |
case-15 | fail→fail | 24,130 | 26,686 | +11% | 1 | 1 | 0% | 3,387 | 3,996 | +18% | 0 | 0 | — |
case-16 | fail→pass | 25,231 | 28,598 | +13% | 1 | 1 | 0% | 3,407 | 4,290 | +26% | 0 | 0 | — |
case-17 | fail→fail | 26,278 | 25,668 | -2% | 1 | 1 | 0% | 3,561 | 3,999 | +12% | 0 | 0 | — |
case-18 | pass→pass | 28,671 | 27,707 | -3% | 1 | 1 | 0% | 4,369 | 4,172 | -5% | 0 | 0 | — |
case-19 | pass→pass | 24,538 | 27,252 | +11% | 1 | 1 | 0% | 3,139 | 4,174 | +33% | 0 | 0 | — |
case-20 | pass→pass | 21,742 | 22,168 | +2% | 1 | 1 | 0% | 3,659 | 4,180 | +14% | 0 | 0 | — |
case-21 | pass→pass | 16,054 | 16,615 | +3% | 1 | 1 | 0% | 2,016 | 2,438 | +21% | 0 | 0 | — |
case-22 | pass→pass | 24,291 | 30,337 | +25% | 1 | 1 | 0% | 3,175 | 4,602 | +45% | 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 21 counted toward the lift figure. The other 1 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 +5 percentage points is the difference between those two pass rates over the 21 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.