CH

changeset-validation

Validates changeset compliance for package updates using LLM-based logic.

Install

mkdir -p .claude/skills/changeset-validation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5895" && unzip -o skill.zip -d .claude/skills/changeset-validation && rm skill.zip

Installs to .claude/skills/changeset-validation

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.
221 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Judges changeset compliance against repository versioning rules
  • Determines appropriate semver bump levels (patch/minor/major)
  • Updates existing changeset summary lines in the repository
  • Evaluates diffs for experimental flag compliance

How it works

It invokes an LLM to compare git diffs against a codified set of versioning rules stored in markdown references.

Inputs & outputs

You give it
Git diff and existing changeset files
You get back
JSON verdict with required version bump and compliance status

When to use changeset-validation

  • Verify PR changeset compliance
  • Check version bump levels
  • Validate package changes

About this skill

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

When not to use it

  • When the repository does not use the changeset workflow
  • When making trivial changes that do not impact package versions

Prerequisites

pnpmgit

Limitations

  • Rules are specific to the openai-agents-js repository logic
  • Changeset files must be updated rather than appended

How it compares

It provides a deterministic versioning verdict based on code diffs rather than relying on manual developer judgment.

Compared to similar skills

changeset-validation side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
changeset-validation (this skill)13moReviewIntermediate
dependency-upgrade265moReviewIntermediate
ast-grep-find37moReviewIntermediate
nx-workspace46moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

skill-installer

openai

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

29141

figma-implement-design

openai

Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection.

2460

figma

openai

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

2266

gh-fix-ci

openai

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

1234

transcribe

openai

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

1148

gh-address-comments

openai

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

1059

Search skills

Search the agent skills registry