agentleFS
stijnvanhullestijnvanhulle/agents/.agents/skills/changeset/SKILL.md

changeset

Skill2 starsChanged 53 days agoMITView on GitHub

Writes or reviews a Changesets release note with the correct semver bump. Use whenever a change reaches a versioned package, before its commit, when asked to add, write, or check a changeset, or before a PR that needs one.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use better-auth-best-practices, turborepo and 3 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.
  • anasahmed07Skill

    better-auth-best-practices

    Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

    Also in 3 projects that use this

  • VercelSkill

    turborepo

    Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 3 projects that use this

  • VercelSkill

    vercel-react-best-practices

    React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use the bump the command passed when it is patch, minor, or major.

    line 25
  2. Distinctive:

    Leave out file paths, PR numbers, reviewer talk, and emoji.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 14 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

Changeset

A changeset is the release note for a change. Its reader is upgrading a package, not reviewing the diff.

1. Decide whether one is needed

A change that reaches a versioned package needs one. Docs, CI, and tests do not. When unsure, check that the package is in the workspace and not under ignore in .changeset/config.json, since private packages can be versioned too.

2. Pick the bump

BumpForExample
patchA fix, including a behavior fix in a skill or promptThe resolver no longer caches a miss
minorNew behavior that existing code survivesA new unionType option
majorA rename, a removal, or a changed defaultenumType now defaults to asConst

Use the bump the command passed when it is patch, minor, or major. When none was passed, or the table does not settle it, follow the ask skill with patch, minor, and major. Recommend the bump the repo's recent changesets or CHANGELOG.md give the same kind of change, and name the entries you matched. When that history differs from the table, as in a repo that ships new options as patches, recommend the history's bump and offer the table's as the alternative. Write no file until the bump is known. Do not default to patch and report it as a guess. When the question goes unanswered, stop and say the bump is missing.

3. Write the file

Name it .changeset/<slug>.md for whoever reads git log: plugin-resolver-cache.md, not fix.md. List only the packages you changed. Then, in order:

  1. One sentence on what the user gets. It becomes the changelog headline, so it stands alone.
  2. One bullet per user-visible change, verb first, naming the real option, export, or command. One line each, saying what the user gets, not how it works. Five at most, and none for a one-line change.
  3. A code example whenever users write something differently: a diff fence for a few lines, otherwise before and after blocks.
  4. For a major, a closing line on what to change to upgrade.

Leave out file paths, PR numbers, reviewer talk, and emoji. Changesets adds the commit link.

---
'@scope/core': minor
---

Add `unionType` so one type covers every variant of a discriminated schema.

- Accepts `unionType: 'asConst' | 'asLiteral'`, defaulting to `asConst`.
- Leaves output unchanged when the option is not set.

```diff
- export type PetDog = { type: 'dog'; bark: string }
- export type PetCat = { type: 'cat'; meow: string }
+ export type Pet = PetDog | PetCat
```

A patch is usually one sentence and no example: "Resolve nested plugin paths on Windows, which broke on a backslash separator."

Output

The file at .changeset/<slug>.md. For a review: the bump verdict, then one bullet per problem with what to change and why, then the rewritten file, or "bump and text are right".

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.