release
Assembles a reviewable release PR by computing versions from change intents and generating release documentation.
Install
mkdir -p .claude/skills/release-mattstyles && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16758" && unzip -o skill.zip -d .claude/skills/release-mattstyles && rm skill.zipInstalls to .claude/skills/release-mattstyles
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.
Assemble a reviewable release PR — versions computed from accumulated .changes/ intents, changelogs written, narrative synthesized, release meta emitted. Use when the user says "cut a release", "release the core train", "assemble a release", or invokes /release. Releases are deliberate; never run this automatically on merge.Key capabilities
- →Preflight check for pending release intents
- →Create a release branch with computed version
- →Apply versions to train members and prepend changelog sections
- →Synthesize a release narrative for GitHub Release body
- →Verify manifest and changelog consistency
How it works
The skill performs a preflight check, branches, assembles release artifacts by applying versions and generating changelogs, synthesizes a release narrative, verifies consistency, and then creates a pull request.
Inputs & outputs
When to use release
- →Cut a release
- →Release the core train
- →Assemble a release
About this skill
Release assembly
Deterministic mechanics are scripts (internal/exfil, fixture-tested);
judgment — the release narrative — is yours. The release PR is the review
surface and merge is the commitment point ([[0004-release-strategy]]).
Flow
-
Preflight — on a clean
main, run:bun run exfil statusIf no train has pending intents, stop and say so. Confirm with the user which train(s) they expect to depart if the status disagrees with them.
-
Branch —
release/<train>-<next-version>(both trains departing →release/<date-slug>). -
Assemble — run:
bun run exfil assembleThis applies versions to every train member, prepends per-package
CHANGELOG.mdsections from intent prose, consumes the intent files, and emitsreleases/<train>-<version>.jsonplus a narrative skeletonreleases/<train>-<version>.md. -
Narrate — replace the skeleton body with a release narrative that will become the GitHub Release body. Synthesize from three sources; do not concatenate entries:
- the intent prose (consumer-addressed, already reviewed),
- manifest diffs (
git diff main -- '**/urban-manifest.json') for the factual API surface changes, - linked PR descriptions (
gh pr list --search <sha>/gh pr view) for motivation, migration detail, and screenshots — best effort only: if offline, the narrative from intents + manifests alone is still correct.
-
Verify —
mise run manifest-checkandhk check --allmust pass; changelog and version diffs should match the status output from step 1. -
PR — commit everything (versions, changelogs, consumed intents, releases/ meta + narrative) and open a PR titled
Release: <train> v<version>describing what departs and why now. Merging the release PR is what triggers the publish plane — do not merge without the user's say-so.
When not to use it
- →When no train has pending intents for release
- →When the user does not explicitly request to cut a release
Limitations
- →The skill does not automatically merge the release PR.
- →The skill requires a clean `main` branch for preflight.
How it compares
This skill automates the complex process of assembling a release, including version computation, changelog generation, and narrative synthesis, which is more efficient and consistent than manual preparation.
Compared to similar skills
release side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| release (this skill) | 0 | 1mo | Review | Advanced |
| github-workflow-automation | 11 | 2mo | Review | Advanced |
| testing-workflow | 16 | 9mo | Review | Intermediate |
| github-actions-templates | 7 | 3mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
testing-workflow
amo-tech-ai
Comprehensive testing workflow for E2E, integration, and unit tests. Use when testing applications layer-by-layer, validating user journeys, or running test suites.
github-actions-templates
wshobson
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
glab
NikiforovAll
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
create-pr
n8n-io
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
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.