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.zipInstalls 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.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
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):
- Run:
pnpm changeset:validate-prompt - Apply the rules from
references/validation-prompt.mdto the generated prompt. - Respond with a JSON verdict containing ok/errors/warnings/required_bump (English-only strings).
CI (Codex Action):
- Run:
pnpm changeset:validate-prompt -- --ci --output .github/codex/prompts/changeset-validation.generated.md - Use
openai/codex-actionwith the generated prompt and JSON schema to get a structured verdict.
Workflow
- Generate the prompt context via
pnpm changeset:validate-prompt. - Apply the rules in
references/validation-prompt.mdto judge correctness. - Provide a clear verdict and required bump (patch/minor/major/none).
- If the changeset needs edits, update it and re-run the validation.
Branch-level changeset rule (do not skip)
- If any
.changeset/*.mdfile 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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| changeset-validation (this skill) | 1 | 3mo | Review | Intermediate |
| dependency-upgrade | 26 | 5mo | Review | Intermediate |
| ast-grep-find | 3 | 7mo | Review | Intermediate |
| nx-workspace | 4 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by openai
View all by openai →You might also like
dependency-upgrade
wshobson
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
ast-grep-find
parcadei
AST-based code search and refactoring via ast-grep MCP
nx-workspace
nrwl
Explore and understand Nx workspaces. USE WHEN answering any questions about the nx workspace, the projects in it or tasks to run. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What targets can I run?', 'What's affected by my changes?', 'Which projects depend on library Y?', or any questions about Nx workspace structure, project configuration, or available tasks.
positron-pr-helper
posit-dev
Generates well-structured PR bodies with dynamically fetched e2e test tags
code-review
jonatron55
Instructions for reviewing changes and ensuring quality before completion. Use when asking for a review or before committing changes.
pr
BuddiesOfBudgie
Create a pull request for the current branch