Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.
.claude/skills/tobihagemann-changelog-rules/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 156% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 130% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 111% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 94% | 0% |
The changelog is kept in CHANGELOG.md at the project root. The format is based on Keep a Changelog, and projects using these conventions adhere to Semantic Versioning.
markdown# Changelog All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). ## [Unreleased] ## [1.2.0] - 2024-03-15 ### Added - Add dark mode support ([#38](https://github.com/owner/repo/issues/38), [#42](https://github.com/owner/repo/pull/42)) ### Fixed - Fix crash on startup ([#40](https://github.com/owner/repo/issues/40), [#43](https://github.com/owner/repo/pull/43)) [Unreleased]: https://github.com/<owner>/<repo>/compare/v1.2.0...HEAD [1.2.0]: https://github.com/<owner>/<repo>/compare/v1.1.0...v1.2.0 [1.1.0]: https://github.com/<owner>/<repo>/releases/tag/v1.1.0
Not every change belongs in a changelog. Changelogs are for humans, not machines.
Skip changes that are purely internal:
Include changes that affect users:
Entries describe what changed for the user. Focus on outcomes and impact.
Entries describe the change relative to the last released version.
git show <last-tag>:<path>, plus git log --follow -- <path> when the file moved. A path that exists at the tag settles nothing on its own, since new behavior often lands in files that were already there.Reference both the PR and any associated GitHub issue in each entry using inline parenthetical format with linked numbers in ascending order.
markdown- Add dark mode support ([#38](https://github.com/owner/repo/issues/38), [#42](https://github.com/owner/repo/pull/42))
To discover associated issues for a PR, run:
bashgh pr view <number> --json closingIssuesReferences --jq '.closingIssuesReferences[].number'
Standard types in this order when present: Added, Changed, Deprecated, Removed, Fixed, Security. Omit empty sections.
YYYY-MM-DD)v-prefixed tags (e.g., v1.0.0) or bare tags (e.g., 1.0.0) and match that convention in comparison links| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | pass→pass | 5,216 | 4,850 | -7% | 1 | 1 | 0% | 873 | 1,998 | +129% | 0 | 0 | — |
case-01 | fail→pass | 4,413 | 4,176 | -5% | 1 | 1 | 0% | 805 | 2,060 | +156% | 0 | 0 | — |
case-02 | fail→fail | 6,959 | 7,368 | +6% | 1 | 1 | 0% | 1,316 | 2,657 | +102% | 0 | 0 | — |
case-17 | pass→pass | 5,273 | 3,083 | -42% | 1 | 1 | 0% | 1,044 | 1,916 | +84% | 0 | 0 | — |
case-03 | fail→pass | 4,569 | 3,720 | -19% | 1 | 1 | 0% | 860 | 1,979 | +130% | 0 | 0 | — |
case-04 | fail→pass | 5,962 | 4,006 | -33% | 1 | 1 | 0% | 1,252 | 2,034 | +62% | 0 | 0 | — |
case-05 | fail→pass | 5,935 | 4,737 | -20% | 1 | 1 | 0% | 1,048 | 2,213 | +111% | 0 | 0 | — |
case-06 | fail→pass | 6,352 | 5,734 | -10% | 1 | 1 | 0% | 1,198 | 2,323 | +94% | 0 | 0 | — |
case-07 | fail→pass | 4,703 | 5,268 | +12% | 1 | 1 | 0% | 846 | 2,208 | +161% | 0 | 0 | — |
case-08 | fail→pass | 6,599 | 8,559 | +30% | 1 | 1 | 0% | 1,117 | 2,886 | +158% | 0 | 0 | — |
case-09 | fail→pass | 4,183 | 5,927 | +42% | 1 | 1 | 0% | 689 | 2,334 | +239% | 0 | 0 | — |
case-10 | fail→pass | 6,180 | 5,792 | -6% | 1 | 1 | 0% | 1,053 | 2,471 | +135% | 0 | 0 | — |
case-16 | pass→pass | 5,553 | 3,081 | -45% | 1 | 1 | 0% | 1,068 | 1,732 | +62% | 0 | 0 | — |
case-11 | pass→pass | 4,305 | 9,284 | +116% | 1 | 1 | 0% | 851 | 3,221 | +278% | 0 | 0 | — |
case-12 | pass→pass | 3,499 | 5,847 | +67% | 1 | 1 | 0% | 569 | 2,305 | +305% | 0 | 0 | — |
case-13 | pass→pass | 3,886 | 4,515 | +16% | 1 | 1 | 0% | 739 | 2,189 | +196% | 0 | 0 | — |
case-14 | fail→fail | 5,575 | 4,474 | -20% | 1 | 1 | 0% | 951 | 2,069 | +118% | 0 | 0 | — |
case-15 | fail→pass | 8,674 | 5,529 | -36% | 1 | 1 | 0% | 1,437 | 2,182 | +52% | 0 | 0 | — |
case-18 | pass→pass | 3,445 | 4,270 | +24% | 1 | 1 | 0% | 665 | 2,100 | +216% | 0 | 0 | — |
case-19 | fail→pass | 6,497 | 4,492 | -31% | 1 | 1 | 0% | 1,203 | 1,981 | +65% | 0 | 0 | — |
case-20 | fail→pass | 7,474 | 3,972 | -47% | 1 | 1 | 0% | 1,297 | 1,879 | +45% | 0 | 0 | — |
case-21 | pass→pass | 3,953 | 7,094 | +79% | 1 | 1 | 0% | 791 | 2,741 | +247% | 0 | 0 | — |
case-22 | pass→pass | 3,026 | 3,419 | +13% | 1 | 1 | 0% | 551 | 1,841 | +234% | 0 | 0 | — |
case-24 | pass→pass | 4,153 | 2,603 | -37% | 1 | 1 | 0% | 637 | 1,600 | +151% | 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. 24 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 24 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.