changesets
Use when changing public APIs or behavior, deprecating usage, recommending replacements, or preparing releases; maintain changesets and versioned migration…
Skill by primer
Chalk Labs
Need help deploying changesets?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/primer-changesets
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/changesets
What's inside
- Skill name
changesets- Description
- Use when changing public APIs or behavior, deprecating usage, recommending replacements, or preparing releases; maintain changesets and versioned migration guides.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: references/migrations.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# Changesets
For every backwards-incompatible public API or behavior change, deprecation,
or recommended replacement, update the migration docs in the same pull request.
This is required even when no changeset is needed. Keep guides concise: a brief
change description, versioned before/after snippets, and verification steps;
add explicit migration steps only when needed. Read the migration reference
for the index format and release handling.
| Reference | When to read |
| :------------------------------------- | :----------------------------------------------------------------------------------------------------------- |
| [Migrations](references/migrations.md) | Documenting breaking changes, deprecations, or replacements, and finalizing migration versions for a release |
Add a changeset when a pull request changes the public API or user-visible
behavior of the published `@primer/agent-eval` package. Public API includes:
- Exported functions, classes, types, constants, and package entry points
- CLI commands, options, output, and exit behavior
- Experiment and scenario configuration accepted from consumers
- Documented runtime behavior that consumers rely on
Do not add a changeset for scenarios, experiments, tests, internal refactors, or
repository tooling that do not affect consumers of `@primer/agent-eval`.
Do not create changesets for updates to features, fixes, or other changes that
have not been released yet.
## Write a changeset
1. Give each distinct public API change its own changeset. Do not group multiple
public API changes in one changeset.
2. Run `pnpm changeset` from the repository root.
3. Select `@primer/agent-eval`.
4. Choose the version bump based on consumer impact:
- `patch` for a backwards-compatible fix to existing behavior.
- `minor` for a public API addition, enhancement, or breaking change that
requires consumers to update their code or configuration.
Do not use a `major` changeset while `@primer/agent-eval` is pre-1.0.
5. Write a concise summary from the consumer's perspective.
Describe the public API or behavior that was added, changed, fixed, or removed.
For breaking changes, state what consumers need to change. Do not describe
implementation details, internal refactors, file changes, or the development
process unless they directly affect consumers.
Prefer:
> Add support for filtering scenarios by multiple tags.
Avoid:
> Refactor the scenario loader and update its internal filtering helper.From primer/agent-eval, MIT.
More from primer/agent-eval
- 0.603score
agent-eval-investigate
primer
Use when investigating model behavior in agent-eval experiment or benchmark results, explaining why an agent did or did not call a tool, follow an…
SkillAFreshness: A★ 2Claude Code +9 - 0.594score
write-skill
primer
Use when creating, updating, or reviewing agent skills
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
agent-eval
primer
Use when installing or using @primer/agent-eval, designing agent evaluations, creating benchmarks, experiments, scenarios, checks, judges, or treatments, and…
SkillAFreshness: A★ 2Claude Code +9 - 0.589score
ui
primer
Use to understand how to build and verify UI-related work
SkillAFreshness: A★ 2Claude Code +9 - 0.573score
testing
primer
Use when adding, updating, or reviewing tests in agent-eval, choosing test coverage, organizing Vitest tests, or isolating filesystem, Docker, and other…
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 16
- Last commit (this folder)
- Oct 21, 2026 (11 days ago)
- Last release
- Oct 21, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/primer/agent-eval
- Website
- primer.github.io/agent-eval/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from primer
- 0.603score
agent-eval-investigate
primer
Use when investigating model behavior in agent-eval experiment or benchmark results, explaining why an agent did or did not call a tool, follow an…
SkillAFreshness: A★ 2Claude Code +9 - 0.594score
write-skill
primer
Use when creating, updating, or reviewing agent skills
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
agent-eval
primer
Use when installing or using @primer/agent-eval, designing agent evaluations, creating benchmarks, experiments, scenarios, checks, judges, or treatments, and…
SkillAFreshness: A★ 2Claude Code +9 - 0.589score
ui
primer
Use to understand how to build and verify UI-related work
SkillAFreshness: A★ 2Claude Code +9 - 0.573score
testing
primer
Use when adding, updating, or reviewing tests in agent-eval, choosing test coverage, organizing Vitest tests, or isolating filesystem, Docker, and other…
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get changesets running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
changesets skill. Agent Mart. https://agentmart.dev/skills/primer-changesets (last updated 2026-10-24)