agentleFS
Sign inStart free
Kuan-AI-comKuan-AI-com/agent-skills/skills/changelog/SKILL.md

changelog

Skill0 starsChanged 6 days agoMITView on GitHub

Write release notes or a CHANGELOG.md entry from git history. Use when the user says "write the changelog", "release notes for v2.3", "what changed since the last release/tag", or is preparing a release or version bump.

165 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

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 154 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No tags at all: ask, or use the last CHANGELOG.md entry's date (git log --since=<date>).

    line 11
  2. Very specific:

    If the repo squash-merges or merges PRs, PR titles carry the meaning: also read git log <range> --merges --first-parent --format='%h %s'.

    line 15
  3. Distinctive:

    Never claim an effect you did not see in the diff (performance gains, "fixes crashes").

    line 31
  4. Very specific:

    If CHANGELOG.md exists, copy its exact heading and section style (often Keep a Changelog: ## [1.4.0] - 2026-11-09).

    line 34

“Common” is measured: kept by at least 6 in 10 of the 154 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 from commits

1. Fix the range

  • User gave a range or versions: use it.
  • Otherwise: git describe --tags --abbrev=0 to get the last tag, range <tag>..HEAD.
  • No tags at all: ask, or use the last CHANGELOG.md entry's date (git log --since=<date>). State the range you used at the top of your answer.

2. Collect, from the right source

  • git log <range> --no-merges --format='%h %s%n%b' for the commits.
  • If the repo squash-merges or merges PRs, PR titles carry the meaning: also read git log <range> --merges --first-parent --format='%h %s'.
  • For any commit whose subject is vague ("fix", "wip", "updates") read git show --stat <hash> and the diff before classifying it. Do not guess from the message.

3. Detect breaking changes (check all, they are the most expensive to miss)

  • BREAKING CHANGE: footer or type!: in Conventional Commits.
  • Removed or renamed: public functions/exports, CLI flags, env vars, config keys, API endpoints or fields.
  • Database migrations that drop/rename columns; changed defaults; raised minimum runtime versions. Each breaking item needs a migration line: what the user must change, before -> after.

4. Classify by impact on the reader, not by commit type

Order: Breaking changes, New, Improved, Fixed, Security (if any), Deprecated. Drop: refactors, CI, tests, formatting, dependency bumps with no user effect, reverted pairs (a commit and its revert cancel out). Keep a dependency bump only if it fixes a vulnerability or changes behaviour.

5. Rewrite each item

  • User language, present tense, one line: "Exports now include the customer email" not "feat(export): add email col".
  • End with the reference: (#123) or (abc1234). Merge several commits for one feature into one line with all refs.
  • Never claim an effect you did not see in the diff (performance gains, "fixes crashes"). If unsure what it changes for users, put it under Needs review at the end instead of guessing.

6. Format and placement

  • If CHANGELOG.md exists, copy its exact heading and section style (often Keep a Changelog: ## [1.4.0] - 2026-11-09). Otherwise use the order above with ## version heading and ### sections.
  • Suggest the next version with semver: breaking -> major (minor if still 0.x), New -> minor, only fixes -> patch. Say it is a suggestion.
  • Show the entry first. Write it to the file only if asked; never commit, tag or push without being asked.

Output

  1. Range used and number of commits read.
  2. The entry.
  3. Needs review: commits you could not classify, with hashes.

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