Skip to content

fix(add-changeset): trim token bloat (~20% reduction) #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
unional merged 1 commit into from
May 27, 2026
Merged

fix(add-changeset): trim token bloat (~20% reduction) #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 1 addition & 35 deletions skills/add-changeset/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,6 @@ description: "Use this skill when a published-package change needs a changeset (

# Add Changeset

A changeset declares which packages are affected by a change, the semver bump type, and a user-facing summary. It lives as a markdown file in `.changeset/` and is consumed automatically by CI to version and publish packages.

Also use when asked to add a changeset, run `add cs`, or when CI reports a missing changeset. Detects monorepos and selects affected packages automatically.

## When to Add One

**Add a changeset when the change:**
Expand Down Expand Up @@ -112,29 +108,7 @@ Add `retry` option to fetch client.
- For packages in a `fixed` group, list every package in the group with the same bump type
- The body is the user-facing summary (see summary rules below)

**Summary rules** — the body appears verbatim in `CHANGELOG.md`:
- Imperative mood: "Add support for X" not "Added support for X"
- User-facing: describe the effect, not the implementation
- End with a period (`.`)
- Wrap code identifiers (component names, prop names, function names) in backticks
- One line is enough; add bullet points only for breaking changes that need migration steps
- No references to internal file names or commit SHAs

Good: `Add \`retry\` option to fetch client.`
Bad: `Updated fetchClient.ts to handle retries in the error handler`

**Breaking change example** — include migration steps in the body:

```markdown
---
"package-name": major
---

Remove deprecated `oldOption` config key. Use `newOption` instead.

Migration:
- Replace `oldOption: true` with `newOption: true`
```
**Summary** — appears verbatim in `CHANGELOG.md`: imperative mood, user-facing effect, ends with a period, code identifiers in backticks, no internal file names or commit SHAs. For breaking changes, add a `Migration:` bullet list.

### 5. Commit the changeset

Expand All @@ -147,14 +121,6 @@ git commit -m "docs: add changeset"

If staged or unstaged changes existed (scope cases 1 or 2), tell the user the changeset file has been created and let them include it in their own commit.

## What Happens Next (don't intervene)

Once the changeset is merged to the base branch, the CI release workflow (`changesets/action`) will automatically:
1. Open or update a **"Version Packages"** PR that bumps `package.json` versions and updates `CHANGELOG.md`
2. When that PR is merged, publish to npm and create GitHub releases

**Never manually edit `CHANGELOG.md`** — it is fully generated by `changeset version`. **Never add changesets to a "Version Packages" PR** — it will be overwritten.

## Verification

- [ ] File exists in `.changeset/` with a descriptive or slug filename
Expand Down