agentleFS
electronxelectronx/wiredkits-free/skills/release-notes/SKILL.md

release-notes

Skill5 starsChanged 21 days agoMITView on GitHub

Write release notes or a CHANGELOG entry from the commits and merged PRs since the last release. Use when asked for "release notes", "update the changelog", "what changed since v1.2", or before tagging a release.

  • Reads credentials
  • Commits and pushes

176 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brainstorm-experiments-existing, brainstorm-ideas-new 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.
  • skytiger6724Skill

    brainstorm-experiments-existing

    Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.

    Also in 6 projects that use this

  • skytiger6724Skill

    brainstorm-ideas-new

    Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.

    Also in 6 projects that use this

  • 45ckSkill

    pestle-analysis

    Also in 6 projects that use this

  • About-IntelligenceSkill

    positioning-ideas

    Brainstorm product positioning ideas differentiated from competitors.

    Also in 6 projects that use this

  • About-IntelligenceSkill

    product-name

    Brainstorm 5 unique, memorable product names with rationale aligned to brand values and target audience.

    Also in 6 projects that use this

  • +7 more from skytiger6724

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 162 edited versions we read keep these.

  • 3

    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:

    If the range is empty, say so and stop.

    line 17
  2. Distinctive:

    Add the PR or issue link and the author's handle if the existing changelog does.

    line 35
  3. Distinctive:

    If the project uses semver, suggest the next version: major if anything is breaking (minor while below 1.0), minor for new features, patch …

    line 41

“Common” is measured: kept by at least 6 in 10 of the 162 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

Write release notes

You turn a range of commits into notes a user of the project can act on: what's new, what's fixed, and what they must change. Internal churn stays out.

1. Find the range

  1. A range or versions in the request ("since v1.2", "v1.2..v1.3"): use it.
  2. Otherwise from the latest tag to HEAD: git describe --tags --abbrev=0. If there are no tags, ask where to start, or use the last CHANGELOG.md entry's date.

List the commits: git log <from>..<to> --no-merges --format='%h %s%n%b---'. If the repo uses GitHub and gh works, also get merged PRs in the range (gh pr list --state merged --search "merged:>=<date of from>" --json number,title,body,labels,author), because PR titles and labels are usually better than commit messages.

If the range is empty, say so and stop.

2. Learn the format

If CHANGELOG.md (or CHANGES, HISTORY.md, docs/changelog*) exists, copy its format exactly: heading style, version and date format, section names, link style. If it says "Keep a Changelog", use its sections: Added, Changed, Deprecated, Removed, Fixed, Security. If there is no changelog, use: Breaking changes, New, Improved, Fixed.

3. Sort every change

For each commit or PR, read the diff when the title doesn't make the user-facing effect clear (git show --stat <sha>, then the relevant hunks). Then put it in one bucket:

  • Breaking: anything a user must change to upgrade: removed or renamed APIs, flags, config keys, env vars, changed defaults, dropped runtime versions, schema migrations. Check this hardest. A commit titled "refactor" can still break a public API.
  • New, Improved, Fixed, Security: user-visible changes.
  • Leave out: refactors with no behavior change, tests, CI, formatting, dependency bumps with no user effect, reverted pairs (a commit and its revert cancel out). Mention dependency bumps only for security fixes or a raised minimum version.

4. Write it

  • One line per change, written for users: "Retries failed webhooks up to 3 times", not "add retry logic to WebhookSender class".
  • Merge commits that are parts of one change into one line.
  • Add the PR or issue link and the author's handle if the existing changelog does.
  • Under Breaking, say what to do: "Rename API_KEY to ACME_API_KEY in your env."
  • Order inside a section: biggest user impact first.

5. Suggest the version

If the project uses semver, suggest the next version: major if anything is breaking (minor while below 1.0), minor for new features, patch for fixes only. Say why in one line. Don't tag or publish.

6. Deliver

Show the notes. If asked to update the changelog, insert the entry at the top under any intro text, keep an ## Unreleased section if the file has one, and show the diff. Don't commit, tag or create a GitHub release unless asked; for a release, use gh release create <tag> --notes-file <file> only after the user confirms the tag.

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.