agentleFS
anza-xyzanza-xyz/kit/.agents/skills/changesets/SKILL.md

changesets

Skill702 starsChanged 9 months agoMITView on GitHub

Generate a changeset file with a changelog entry for package releases. Use when a PR introduces user-facing changes that should trigger a version bump.

7 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions7 projects use a version of this.

    Word for word · 1

    1. lorisleiva/skills★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 6

    1. Effect-TS/effect★ 18ksame name
    2. primer/octicons★ 8.8ksame name
    3. primer/react★ 3.9ksame name
    4. portabletext/editor★ 285same name
    5. lxsmnsyc/agent-skills★ 4same name
    6. joostme/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 8

    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. Distinctive:

    Create a new changeset file for the current project using the changesets CLI, then fill it with a proper changelog entry based on recent …

    line 10
  2. Very specific:

    ALWAYS use npx changeset add --empty to generate a new changeset file with a random name.

    line 18
  3. Distinctive:

    No changeset needed for: docs-only changes, CI config, dev dependency updates, test-only changes.

    line 19
  4. Distinctive:

    Do NOT modify any existing changeset files.

    line 20
  5. Distinctive:

    Only create one new changeset file per invocation.

    line 21
  6. Distinctive:

    Write a concise but informative changelog entry (1-3 sentences).

    line 38
  7. Distinctive:

    Start with a verb — e.g. "Add", "Remove", "Replace", "Fix", "Update".

    line 39
  8. Very specific:

    Add a BREAKING CHANGES section (bold paragraph, not a header) after the changelog entry when:

    line 45
  9. Distinctive:

    Not every breaking change needs a diff — use them when there's a clear before/after code change to show.

    line 74
  10. Distinctive:

    When invoked as a command, follow these steps:

    line 78
  11. Very specific:

    Determine the change source: Check git status for uncommitted changes.

    line 86

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

Generate Changeset

Create a new changeset file for the current project using the changesets CLI, then fill it with a proper changelog entry based on recent changes.

Key Rules

  • Any PR that should trigger a package release MUST include a changeset.
  • Identify affected packages by mapping changed files to their nearest package.json.
  • Choose the right bump: patch for fixes, minor for features, major for breaking changes.
  • While a project is pre-1.0, minor bumps may be treated as breaking.
  • ALWAYS use npx changeset add --empty to generate a new changeset file with a random name. NEVER create changeset files manually.
  • No changeset needed for: docs-only changes, CI config, dev dependency updates, test-only changes.
  • Do NOT modify any existing changeset files.
  • Only create one new changeset file per invocation.

Guidelines

Changeset Format

---
'<package-a>': patch
'<package-b>': patch
---

<concise changelog entry>

Changelog Entries

  • Write a concise but informative changelog entry (1-3 sentences).
  • Start with a verb — e.g. "Add", "Remove", "Replace", "Fix", "Update".
  • Focus on what changed from the user's perspective, not implementation details.
  • Mention renamed or removed APIs explicitly.

Breaking Changes

Add a **BREAKING CHANGES** section (bold paragraph, not a header) after the changelog entry when:

  • The bump level is major, OR
  • The bump level is minor AND the current major version is 0 (i.e. pre-1.0)

...and the changes actually introduce breaking changes.

The breaking changes section should list each breaking change with a bold title summarizing the change, followed by a brief explanation and a diff code block showing the before/after migration when applicable. For example:

Replace the `useGranularImports` boolean option with a new `importStrategy` option.

**BREAKING CHANGES**

**`useGranularImports` replaced with `importStrategy`.** The boolean option has been replaced with a string union for finer control.

\`\`\`diff
- renderVisitor('./output', { useGranularImports: true });
+ renderVisitor('./output', { importStrategy: 'granular' });
\`\`\`

**Default import behavior changed.** The default strategy is now `'preferRoot'`, which falls back to granular packages for symbols not on the root entrypoint.

\`\`\`diff
- renderVisitor('./output'); // equivalent to useGranularImports: false
+ renderVisitor('./output'); // equivalent to importStrategy: 'preferRoot'
\`\`\`

Not every breaking change needs a diff — use them when there's a clear before/after code change to show. For type removals or behavioral changes, a text explanation is sufficient.

Command Process

When invoked as a command, follow these steps:

Arguments

  • [patch|minor|major] (optional): Override the bump level for all affected packages.

Steps

  1. Determine the change source. Check git status for uncommitted changes. If there are meaningful working tree changes, use those. Otherwise, use the latest commit(s) on the current branch (compared to the base branch from .changeset/config.json).
  2. Identify which packages changed. Look at which files were modified and map them to their nearest package.json to determine affected packages. Ignore changes that are not relevant to a changeset — e.g. typo fixes in comments, dependency version bumps in package.json, changes to CI config, docs-only changes in non-doc packages, etc. Use your judgement to filter out noise.
  3. Run npx changeset add --empty to generate a new changeset file with a random name.
  4. Identify the newly created file — it will be the most recently created .md file in .changeset/ (excluding README.md).
  5. Write the changeset file with the proper frontmatter listing each affected package and the bump level, followed by the changelog entry.

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.