Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.
.claude/skills/dokhacgiakhoa-changelog-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-07 | ✓→✗ | ▼ Worse | -1% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 35% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 32% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 35% | 0% |
Patterns and tools for automating changelog generation, release notes, and version management following industry standards.
resources/implementation-playbook.md.resources/implementation-playbook.md for detailed patterns, templates, and examples.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 4,754 | 34,656 | +629% | 1 | 1 | 0% | 868 | 1,169 | +35% | 0 | 0 | — |
case-02 | pass→pass | 3,043 | 3,968 | +30% | 1 | 1 | 0% | 585 | 775 | +32% | 0 | 0 | — |
case-03 | pass→pass | 3,226 | 3,380 | +5% | 1 | 1 | 0% | 562 | 758 | +35% | 0 | 0 | — |
case-04 | pass→pass | 5,447 | 4,484 | -18% | 1 | 1 | 0% | 1,088 | 878 | -19% | 0 | 0 | — |
case-05 | pass→pass | 4,875 | 3,116 | -36% | 1 | 1 | 0% | 806 | 841 | +4% | 0 | 0 | — |
case-06 | pass→pass | 4,402 | 3,171 | -28% | 1 | 1 | 0% | 834 | 781 | -6% | 0 | 0 | — |
case-07 | pass→fail | 8,571 | 5,336 | -38% | 1 | 1 | 0% | 1,258 | 1,250 | -1% | 0 | 0 | — |
case-08 | pass→pass | 7,134 | 6,684 | -6% | 1 | 1 | 0% | 1,355 | 1,280 | -6% | 0 | 0 | — |
case-09 | pass→pass | 5,961 | 4,811 | -19% | 1 | 1 | 0% | 1,012 | 1,050 | +4% | 0 | 0 | — |
case-10 | fail→pass | 4,475 | 3,537 | -21% | 1 | 1 | 0% | 646 | 785 | +22% | 0 | 0 | — |
case-11 | pass→pass | 5,673 | 2,987 | -47% | 1 | 1 | 0% | 870 | 743 | -15% | 0 | 0 | — |
case-12 | pass→pass | 5,844 | 5,307 | -9% | 1 | 1 | 0% | 1,012 | 1,298 | +28% | 0 | 0 | — |
case-13 | pass→pass | 4,457 | 3,419 | -23% | 1 | 1 | 0% | 872 | 816 | -6% | 0 | 0 | — |
case-14 | pass→pass | 2,833 | 2,474 | -13% | 1 | 1 | 0% | 514 | 700 | +36% | 0 | 0 | — |
case-15 | pass→pass | 3,252 | 2,754 | -15% | 1 | 1 | 0% | 505 | 696 | +38% | 0 | 0 | — |
case-16 | pass→pass | 3,777 | 2,785 | -26% | 1 | 1 | 0% | 768 | 780 | +2% | 0 | 0 | — |
case-17 | pass→pass | 2,706 | 2,307 | -15% | 1 | 1 | 0% | 506 | 594 | +17% | 0 | 0 | — |
case-18 | pass→pass | 6,397 | 3,840 | -40% | 1 | 1 | 0% | 1,323 | 807 | -39% | 0 | 0 | — |
case-19 | pass→pass | 3,924 | 3,549 | -10% | 1 | 1 | 0% | 675 | 817 | +21% | 0 | 0 | — |
case-20 | pass→pass | 9,919 | 16,677 | +68% | 1 | 1 | 0% | 1,522 | 1,438 | -6% | 0 | 0 | — |
case-21 | pass→pass | 14,135 | 7,806 | -45% | 1 | 1 | 0% | 2,515 | 1,637 | -35% | 0 | 0 | — |
case-22 | pass→pass | 17,861 | 12,291 | -31% | 1 | 1 | 0% | 2,843 | 2,577 | -9% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.