agentleFS
Sign inStart free
kakarot-oncloudkakarot-oncloud/claude-dev-skills/skills/changelog-writer/SKILL.md

changelog-writer

Skill0 starsChanged 7 months agoMITView on GitHub

Writes CHANGELOG.md entries in Keep a Changelog format from a list of commits, PRs, or a diff between two versions. Groups changes into Added, Changed, Deprecated, Removed, Fixed, Security. Use this skill when the user asks to "update the changelog", "write release notes", needs entries for a new version bump, or wants to convert git log output into a readable changelog.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use test-writer.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • leonardomsoSkill

    test-writer

    Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only Fixed/Security → patch

    line 68

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Changelog Writer

You produce CHANGELOG.md entries following Keep a Changelog 1.1.0 and SemVer.

Format

## [1.4.0] - 2026-04-19

### Added
- New `--dry-run` flag for the migrate command (#142)

### Changed
- Default timeout increased from 5s to 30s for slow networks

### Deprecated
- `parseConfig()` — use `loadConfig()` instead, will be removed in 2.0

### Removed
- Legacy v0 API endpoints (`/api/v0/*`)

### Fixed
- Race condition when refreshing tokens during concurrent requests (#138)

### Security
- Bumped `lodash` to 4.17.21 to patch CVE-2021-23337

Categories (use only those that apply)

  • Added — new features
  • Changed — changes to existing functionality
  • Deprecated — features still working but to be removed
  • Removed — features removed in this version
  • Fixed — bug fixes
  • Security — vulnerability fixes (always include CVE if known)

Rules

  1. Audience is the user/integrator, not the contributor. "Added a flag" not "Implemented argparse handler in cli.py".
  2. One entry per user-visible change. Squash multiple commits that fixed one bug into one entry.
  3. Skip internal changes — refactors, test additions, CI tweaks — unless they affect users (e.g. perf improvement).
  4. Reference issues/PRs with (#123) at the end of the entry, not as a link in the middle.
  5. Breaking changes: prefix with **BREAKING:** and explain migration in the description.
  6. Date format: YYYY-MM-DD.
  7. Version order: newest at the top.
  8. Unreleased section at the very top for in-flight changes:
    ## [Unreleased]
### Added
- ...

Process

  1. Get the input (commit list, PR titles, or diff).
  2. Filter out non-user-facing changes.
  3. Group by category.
  4. Rewrite each in past tense, present-user-impact phrasing.
  5. Recommend the version bump (major / minor / patch) based on what's in the changelog:
    • Has Removed or Breaking → major
    • Has Added → minor
    • Only Fixed/Security → patch

Output the markdown ready to paste at the top of CHANGELOG.md, plus a one-line version bump recommendation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free