agentleFS
tilomitratilomitra/release-kit-claude-skills/changelog/SKILL.md

changelog

Skill2 starsChanged 10 months agoMITView on GitHub

Generate or update CHANGELOG.md entries from git history, PRs, and issues using Keep a Changelog format. Triggered by requests to update changelogs, document changes, or summarize what changed between versions.

  • Reads credentials

160 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

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.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 149 edited versions we read keep these.

  • 7

    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:

    When asked to generate a changelog entry (e.g., for a version or tag range), collect context from multiple sources.

    line 12
  2. Distinctive:

    If you can't determine the user impact of a change, omit it or group it under internal improvements

    line 82
  3. Distinctive:

    Never mention file names, function names, or technical internals in the output

    line 87
  4. Distinctive:

    Use active voice: "Add dark mode" not "Dark mode has been added"

    line 88
  5. Distinctive:

    Write entries in Keep a Changelog format:

    line 94
  6. Distinctive:

    If a CHANGELOG.md already exists, prepend the new entry below the header

    line 137
  7. Distinctive:

    If no CHANGELOG.md exists, create one with a header and the new entry

    line 138

“Common” is measured: kept by at least 6 in 10 of the 149 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 Generator

Generate CHANGELOG.md entries by analyzing code changes, PRs, and issues — not just commit messages.

Gathering Context

When asked to generate a changelog entry (e.g., for a version or tag range), collect context from multiple sources. Commit messages are often vague or useless, so prioritize richer signals.

Step 1: Determine the version range

# Get the two most recent tags
CURRENT_TAG=$(git describe --tags --abbrev=0)
PREVIOUS_TAG=$(git describe --tags --abbrev=0 "$CURRENT_TAG^")

# Or if the user specifies a version:
# CURRENT_TAG="v2.4.0"
# PREVIOUS_TAG=$(git describe --tags --abbrev=0 "$CURRENT_TAG^")

# Get the date of the previous tag for filtering PRs/issues
SINCE_DATE=$(git log -1 --format=%aI "$PREVIOUS_TAG")

Step 2: Gather signals (in order of usefulness)

PRs merged since last release:

gh pr list --state merged --search "merged:>=$SINCE_DATE" --json number,title,body,labels --limit 100

Issues closed since last release:

gh issue list --state closed --search "closed:>=$SINCE_DATE" --json number,title,body,labels --limit 100

Diff between tags:

git diff "$PREVIOUS_TAG".."$CURRENT_TAG" -- '*.ts' '*.js' '*.tsx' '*.jsx' '*.py' '*.go' '*.rs' ':!*.lock' ':!*.min.*'

Files changed:

git diff --name-only "$PREVIOUS_TAG".."$CURRENT_TAG"

New or changed test descriptions (reveal intent):

git diff "$PREVIOUS_TAG".."$CURRENT_TAG" -- '**/*.test.*' '**/*.spec.*' '**/test_*' '**/*_test.*'

Config and dependency changes:

git diff "$PREVIOUS_TAG".."$CURRENT_TAG" -- 'package.json' '*.toml' '*.yaml' '*.yml' '*.env.example' '*.config.*'

Commit messages (last resort):

git log --oneline "$PREVIOUS_TAG".."$CURRENT_TAG"

Categorizing Changes

Classify every change into one of these Keep a Changelog categories:

  • Added — new features or capabilities
  • Changed — changes to existing functionality
  • Deprecated — features that will be removed
  • Removed — features that were removed
  • Fixed — bug fixes
  • Security — vulnerability fixes

Filtering rules

  • Skip refactors, test-only changes, CI config, and code style changes unless they have user-facing impact
  • Group minor internal improvements under a single "Internal improvements" bullet if worth mentioning at all
  • Prioritize user-facing changes over developer-facing ones
  • If you can't determine the user impact of a change, omit it or group it under internal improvements

Writing Rules

  • Lead with user benefit: "Add bulk CSV export for reports" not "Implement exportToCsv utility function"
  • Never mention file names, function names, or technical internals in the output
  • Use active voice: "Add dark mode" not "Dark mode has been added"
  • Be specific: "Fix crash when opening files larger than 2GB" not "Fix file handling bug"
  • Each entry should be one line. No paragraphs.

Output Format

Write entries in Keep a Changelog format:

## [2.4.0] - 2025-01-15

### Added
- Add bulk CSV export for all report types
- Add keyboard shortcuts for common actions (Ctrl+K to search, Ctrl+N for new)

### Changed
- Improve search performance for large datasets

### Fixed
- Fix crash when opening files larger than 2GB
- Fix incorrect totals on the billing summary page

Example: Bad Commits → Good Changelog

Typical commit messages:

fix stuff
wip
update deps
refactor handler
PR #142: misc changes

What the skill produces by analyzing PRs, issues, diffs, and test descriptions:

## [1.8.0] - 2025-01-10

### Added
- Add real-time collaboration for shared documents
- Add Slack notifications for failed deployments

### Fixed
- Fix duplicate entries appearing in search results
- Fix password reset emails not sending for SSO users

Final Steps

  • If a CHANGELOG.md already exists, prepend the new entry below the header
  • If no CHANGELOG.md exists, create one with a header and the new entry
  • Show the user what was generated and ask if they want to adjust anything before writing

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.