Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
openai avatar

Changeset Validation

  • 113 installs
  • 3.5k repo stars
  • Updated August 4, 2026
  • openai/openai-agents-js

openai-agents-js changeset validation using LLM judgment against git diffs.

About

openai-agents-js changeset validation skill. Uses LLM judgment to verify that changeset files in .changeset/ accurately describe the git diff for modified packages. Runs when packages/ or .changeset/ are modified or when verifying release notes before publish. Compares declared version bump type and changelog entries against actual code changes including uncommitted local work, catching mismatches between changeset prose and implementation before merge.

  • LLM judgment validates changesets against git diffs
  • Includes uncommitted local changes in diff comparison
  • Triggers when packages/ or .changeset/ are modified
  • Catches version bump type mismatches before publish
  • Verifies changelog entries match actual implementation

Changeset Validation by the numbers

  • 113 all-time installs (skills.sh)
  • +4 installs in the week ending Jul 26, 2026 (Skillselion tracking)
  • Ranked #106 of 248 Release Management skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
At a glance

changeset-validation capabilities & compatibility

Capabilities
validate changeset · compare git diff · verify bump type
Use cases
code review · ci cd
From the docs

What changeset-validation says it does

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes).
SKILL.md
npx skills add https://github.com/openai/openai-agents-js --skill changeset-validation

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs113
repo stars3.5k
Last updatedAugust 4, 2026
Repositoryopenai/openai-agents-js

Does this changeset accurately describe the code changes?

Validate changesets in openai-agents-js using LLM judgment against git diffs including uncommitted local changes.

Who is it for?

Maintainers verifying changesets before openai-agents-js releases.

Skip if: Changes with no package or changeset impact.

When should I use this skill?

packages/ or .changeset/ modified or user asks to verify changeset accuracy.

What you get

Changeset validated or corrected to match git diff including local uncommitted changes.

Files

SKILL.mdMarkdownGitHub ↗

Changeset Validation

Overview

This skill validates whether changesets correctly reflect package changes and follow the repository rules. It relies on the shared prompt in references/validation-prompt.md so local Codex reviews and GitHub Actions share the same logic. Experimental or preview-only feature additions that are explicitly labeled as such in the diff may remain a patch bump when they do not change existing behavior. Major bumps are only allowed after the first major release; before that, do not use major bumps for feature-level changes.

Quick start

Local (Codex-driven):

1. Run:

   pnpm changeset:validate-prompt

2. Apply the rules from references/validation-prompt.md to the generated prompt. 3. Respond with a JSON verdict containing ok/errors/warnings/required_bump (English-only strings).

CI (Codex Action):

1. Run:

   pnpm changeset:validate-prompt -- --ci --output .github/codex/prompts/changeset-validation.generated.md

2. Use openai/codex-action with the generated prompt and JSON schema to get a structured verdict.

Workflow

1. Generate the prompt context via pnpm changeset:validate-prompt. 2. Apply the rules in references/validation-prompt.md to judge correctness. 3. Provide a clear verdict and required bump (patch/minor/major/none). 4. If the changeset needs edits, update it and re-run the validation.

Branch-level changeset rule (do not skip)

  • If any .changeset/*.md file is already present in the current branch diff, treat it as the active changeset. Do not add a new changeset file.
  • Instead, update the existing changeset file by rewriting its summary to reflect the primary change relative to `main`. Do not try to capture every incremental update.
  • Keep the summary at one line; replace the line as needed rather than appending. If you must include multiple points, compress them into a single line.

Shared source of truth

  • Keep the prompt file as the single source of validation rules.
  • Keep the script lightweight: it should only gather context and emit the prompt.

Resources

  • references/validation-prompt.md

Related skills

FAQ

What does validation compare?

Changeset files against git diff including uncommitted local changes.

When should I run this?

When packages/ or .changeset/ are modified or before release publish.

How is judgment applied?

LLM evaluates whether changelog entries and bump type match the actual diff.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.