Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
.claude/skills/composiohq-changelog-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 66% | 0% |
This skill transforms technical git commits into polished, user-friendly changelogs that your customers and users will actually understand and appreciate.
From your project repository:
Create a changelog from commits since last releaseGenerate changelog for all commits from the past weekCreate release notes for version 2.5.0Create a changelog for all commits between March 1 and March 15Create a changelog for commits since v2.4.0, using my changelog
guidelines from CHANGELOG_STYLE.mdUser: "Create a changelog for commits from the past 7 days"
Output:
markdown# Updates - Week of March 10, 2024 ## ✨ New Features - **Team Workspaces**: Create separate workspaces for different projects. Invite team members and keep everything organized. - **Keyboard Shortcuts**: Press ? to see all available shortcuts. Navigate faster without touching your mouse. ## 🔧 Improvements - **Faster Sync**: Files now sync 2x faster across devices - **Better Search**: Search now includes file contents, not just titles ## 🐛 Fixes - Fixed issue where large images wouldn't upload - Resolved timezone confusion in scheduled posts - Corrected notification badge count
Inspired by: Manik Aggarwal's use case from Lenny's Newsletter
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 4,383 | 4,372 | -0% | 1 | 1 | 0% | 757 | 1,327 | +75% | 0 | 0 | — |
case-02 | fail→pass | 5,614 | 8,896 | +58% | 1 | 1 | 0% | 932 | 1,209 | +30% | 0 | 0 | — |
case-03 | fail→pass | 3,473 | 2,395 | -31% | 1 | 1 | 0% | 600 | 1,020 | +70% | 0 | 0 | — |
case-04 | fail→fail | 4,014 | 4,185 | +4% | 1 | 1 | 0% | 746 | 1,314 | +76% | 0 | 0 | — |
case-05 | pass→pass | 5,524 | 5,268 | -5% | 1 | 1 | 0% | 867 | 1,358 | +57% | 0 | 0 | — |
case-06 | fail→pass | 6,251 | 2,111 | -66% | 1 | 1 | 0% | 913 | 1,032 | +13% | 0 | 0 | — |
case-07 | pass→pass | 3,799 | 3,324 | -13% | 1 | 1 | 0% | 631 | 1,225 | +94% | 0 | 0 | — |
case-08 | pass→pass | 5,316 | 5,160 | -3% | 1 | 1 | 0% | 818 | 1,548 | +89% | 0 | 0 | — |
case-09 | fail→fail | 6,795 | 3,599 | -47% | 1 | 1 | 0% | 1,121 | 1,238 | +10% | 0 | 0 | — |
case-10 | pass→pass | 4,995 | 5,601 | +12% | 1 | 1 | 0% | 558 | 1,243 | +123% | 0 | 0 | — |
case-11 | fail→pass | 5,183 | 4,029 | -22% | 1 | 1 | 0% | 942 | 1,279 | +36% | 0 | 0 | — |
case-12 | pass→pass | 3,413 | 2,795 | -18% | 1 | 1 | 0% | 497 | 1,042 | +110% | 0 | 0 | — |
case-13 | fail→fail | 6,012 | 5,324 | -11% | 1 | 1 | 0% | 981 | 1,361 | +39% | 0 | 0 | — |
case-14 | pass→fail | 3,584 | 3,679 | +3% | 1 | 1 | 0% | 644 | 1,254 | +95% | 0 | 0 | — |
case-15 | pass→pass | 4,027 | 3,243 | -19% | 1 | 1 | 0% | 674 | 1,229 | +82% | 0 | 0 | — |
case-16 | pass→pass | 3,825 | 3,897 | +2% | 1 | 1 | 0% | 649 | 1,295 | +100% | 0 | 0 | — |
case-17 | fail→pass | 4,381 | 3,081 | -30% | 1 | 1 | 0% | 757 | 1,256 | +66% | 0 | 0 | — |
case-18 | fail→fail | 5,049 | 3,585 | -29% | 1 | 1 | 0% | 958 | 1,209 | +26% | 0 | 0 | — |
case-19 | pass→pass | 5,185 | 4,326 | -17% | 1 | 1 | 0% | 841 | 1,311 | +56% | 0 | 0 | — |
case-20 | fail→fail | 5,757 | 3,462 | -40% | 1 | 1 | 0% | 942 | 1,196 | +27% | 0 | 0 | — |
case-21 | pass→pass | 16,966 | 14,595 | -14% | 1 | 1 | 0% | 3,705 | 4,794 | +29% | 0 | 0 | — |
case-22 | fail→pass | 7,026 | 6,740 | -4% | 1 | 1 | 0% | 1,065 | 1,728 | +62% | 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. 2 cases got worse with the skill loaded, and they are 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.