agentleFS
StormixStormix/transcripts-mcp/.agents/skills/changeset/SKILL.md

changeset

Skill8 starsChanged 2 months agoMITView on GitHub

Generate a changeset file describing the current PR's changes. Use when asked to "create a changeset", "add a changeset", "/changeset", or after implementing a feature/fix that needs a changelog entry. Produces a randomly named `.changeset/*.md` file with affected packages, bump type, and an 80-character-max user-facing summary.

17 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use better-auth-best-practices, turborepo and 2 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

  • 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

11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If origin/main is not available, fall back to staged + unstaged changes (git status and git diff).

    line 21
  2. Distinctive:

    Create one for: new features, bug fixes, breaking changes, performance improvements, security fixes.

    line 25
  3. Distinctive:

    If a changeset is not needed, tell the user and stop.

    line 29
  4. Distinctive:

    Only include packages directly modified.

    line 43
  5. Very specific:

    Verify the filename does not already exist in .changeset/ before writing.

    line 59
  6. Very specific:

    Write to .changeset/<random-name>.md using this exact format:

    line 63
  7. Very specific:

    Start with an imperative verb (Add, Fix, Improve, Remove, Update)

    line 78
  8. Distinctive:

    No trailing period required

    line 80
  9. Distinctive:

    No emojis, no markdown formatting in the summary line

    line 81
  10. Distinctive:

    Run the git command to gather changed files

    line 122
  11. Distinctive:

    Write the file with frontmatter and an 80-char-max summary

    line 126

“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

Create a Changeset

Generate a properly formatted changeset file in .changeset/ describing the work on the current branch / PR. Follow the project's changeset conventions in .cursor/rules/090-changesets.mdc.

Instructions

1. Gather Context

Determine what changed on the current branch versus the default branch:

echo "=== BRANCH ===" && git rev-parse --abbrev-ref HEAD && echo "=== CHANGED FILES ===" && git diff --name-only origin/main...HEAD && echo "=== DIFF SUMMARY ===" && git diff --stat origin/main...HEAD

If origin/main is not available, fall back to staged + unstaged changes (git status and git diff).

2. Decide If A Changeset Is Needed

Create one for: new features, bug fixes, breaking changes, performance improvements, security fixes.

Skip for: refactors with no user impact, formatting, docs-only, tests-only, internal tooling, dev dependency bumps.

If a changeset is not needed, tell the user and stop.

3. Determine Affected Packages

Map changed file paths to package names from package.json files. Common mappings:

PathPackage name
packages/core/**@transcripts-mcp/core
packages/adapters/**@transcripts-mcp/adapters
packages/search/**@transcripts-mcp/search
apps/mcp/**@transcripts-mcp/mcp
packages/<name>/**@transcripts-mcp/<name>

Only include packages directly modified. Do not include transitive dependents.

4. Determine Bump Type

TypeWhen
patchBug fixes, small internal-facing changes with user impact
minorNew features, backwards-compatible additions
majorBreaking changes that require user action

5. Generate Filename

Pick a random kebab-case filename matching the existing convention adjective-noun-verb.md (three short words, lowercase, hyphen-separated).

Examples already in .changeset/: swift-foxes-leap.md, gentle-cats-gather.md, brave-otters-fall.md.

Verify the filename does not already exist in .changeset/ before writing. If it collides, pick another.

6. Write the Changeset

Write to .changeset/<random-name>.md using this exact format:

---
"@transcripts-mcp/<package>": <patch|minor|major>
---

<Summary, max 80 characters, starts with a verb, user-facing>

For multiple affected packages, list each on its own line in the frontmatter.

Summary rules:

  • Hard limit: 80 characters
  • Start with an imperative verb (Add, Fix, Improve, Remove, Update)
  • Describe what changed from the user's perspective, not how
  • No trailing period required
  • No emojis, no markdown formatting in the summary line

Good summaries:

Add dark mode toggle to settings page
Fix crash when processing large files
Improve queue processing performance by 50%

Bad summaries:

Updated code
Fixed bug
Refactored component
chore: refactor download logic to use streams (over 80 chars and not user-facing)

7. Confirm

Print the path to the created file and its contents. Do not stage or commit it unless asked — it will be committed alongside the user's code changes.

Example Output

Created .changeset/brave-foxes-hunt.md:

---
"@transcripts-mcp/search": patch
---

Fix incorrect job retry logic in queue processor

Example Usage

User: "/changeset", "create a changeset", or "add a changeset for this PR"

Response:

  1. Run the git command to gather changed files
  2. Decide if a changeset is warranted; stop if not
  3. Map paths to packages and pick a bump type
  4. Generate a unique random filename
  5. Write the file with frontmatter and an 80-char-max summary
  6. Print the resulting path and contents

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.