autoship
Runs a changesets npm release through the version PR, CI publish, and registry verification.
Skill by mblode
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/mblode-autoship
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
Use cases: devops
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. Checked Oct 25, 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/autoship
What's inside
- Skill name
autoship- Description
- Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish.
- License
- MIT
- Compatibility
- Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow.
- Instructions
- 136 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- evals.json · evals/
- changeset-and-commit.md · references/
- ci-polling.md · references/
- version-pr-and-publish.md · references/
SKILL.md (first lines)
# Autoship
Drive an npm release end to end: changeset, fix loop, push, CI watch, Version Packages PR merge, publish watch, npm verification.
- **IS:** the full release pipeline for an existing changesets-based npm package, from writing the changeset file to confirming the new version on the registry, plus diagnosing why a release run did not version or publish.
- **IS NOT:** opening a feature PR (use `pr-creator`), monitoring a feature PR for reviews, conflicts, or CI (use `pr-babysitter`), general build or type fixes outside a release flow, or scaffolding a new package (use `scaffold-cli`, which hands off to autoship for the first release).
## The Release Loop
One workflow, two successive runs. Misreading it as two workflows causes most autoship mistakes.
1. Push a commit containing a pending `.changeset/*.md` file to the default branch.
2. The release workflow runs: `changesets/action` sees pending changesets, runs `changeset version` in CI, and opens or updates a PR on branch `changeset-release/<default-branch>` (title "Version Packages", suffixed "(next)" in pre mode) carrying the `package.json` bump and `CHANGELOG.md` entry.
3. Merge that PR once every check is green.
4. The same workflow runs again. With no pending changesets left, the action runs its publish script (`changeset publish`), which publishes to npm and, by default, pushes the git tag and creates a GitHub release.
The local job ends at "push the changeset file". CI owns versioning and publishing.
The action has two live majors with different input names: `@v1` takes `publish:`, `@v2` takes `publish-script:`. Read the `uses:` line before diagnosing a run that versioned but never published.
## Reference Files
| File | Read when |
|------|-----------|
| `references/changeset-and-commit.md` | Steps 1-3: writing the changeset file, discovering and running gates non-interactively, staging the release commit |
| `references/ci-polling.md` | Step 4 and Step 5 watches: the Monitor tool, the commit watch script, failure classification, the Changeset Status check |
| `references/version-pr-and-publish.md` | Once CI is green: workflow shape, finding and merging the Version Packages PR, the publish run, npm verification, publish failure diagnosis |
| `evals/evals.json` | Only when changing this skill; never loads during a release |
## Intent Map
| Intent | Steps | Notes |
|--------|-------|-------|
| Full autoship (ship / release / publish) | 1-5 | Default entry point. End to end through publish, no intermediate prompts |
| Create changeset only | 1 | Stage a release without pushing |
| Fix gates and push | 1-3 | Changeset, fixes, commit, no CI watch |
| Watch CI only | 4-5 | Changeset already pushed |
| Merge Version Packages PR only | 4b-5 | CI already green; merges once preconditions hold |
| Fix gates only | 2 | Inside a release flow; no changeset needed |
| Diagnose a release that did not publish | read-only | `references/version-pr-and-publish.md` (PR-wait timeout checks, publish failure table) |
"Ship it" with no npm release context routes to `pr-creator`.
## Safety Tiers
Invoking autoship is standing consent for the full release flow. Do not pause mid-flow to re-confirm; gate risky steps on objective preconditions instead.
- **Green (execute directly):** reads: CI and PR state, `npm view`, pending changesets, `package.json` scripts, git history and status.
- **Yellow (announce in one line, then execute):** writing changeset files, running lint/type/test/format fixers, `git add/commit/push`, starting watches, and merging the Version Packages PR once its identity is confirmed and every check passes.
- **Red (explicit confirmation required):** force-pushes, history rewrites, repository settings changes, any destructive git operation.
## Workflow
Copy this checklist to track progress:
```text
Autoship progress:
- [ ] Step 1: Create changeset (default patch)
- [ ] Step 2: Fix lint, types, tests, format
- [ ] Step 3: Commit and push the changeset
- [ ] Step 4a: Watch CI on the pushed commit
- [ ] Step 4b: Find and merge the Version Packages PR
- [ ] Step 5: Watch the publish run, verify on npm
```
### Step 1: Create changeset (default patch)
- Load `references/changeset-and-commit.md`.
- Inspect pending changesets and their package coverage. Reuse those covering the requested release; add one only for uncovered changes. Ask only if unrelated pending releases make the publish scope ambiguous.
- Default to `patch`; `minor` or `major` only on explicit user instruction.
- Write the file directly (the interactive prompt needs a TTY); the summary is user-facing changelog text inferred from `git log --oneline -10`.
- `pnpm changeset status` validates the file: a misspelled package name fails here instead of in CI.
### Step 2: Fix lint, types, tests, format
- Discover commands from `package.json` scripts (`check`, `lint`, `typecheck`, `test`, `format`, `fix`); in non-Node repos check `Makefile`, `Cargo.toml`, `pyproject.toml`, `go.mod`.
- Run lint, typecheck, test, format. After any code change, re-run from the first gate: a type fix routinely breaks lint, and a lint autofix can break a test.
- Scope auto-fixers to changed files where supported, then check `git status`: broad `fix`/`format` scripts reformat files outside the change (MDX is a frequent casualty). Undo only fixer changes introduced by this run, preserving pre-existing edits in the same files.
- Cap the loop at 5 fix iterations per gate, reporting the remaining error count each pass; then stop and report the gate, remaining error count, and last error output.
### Step 3: Commit and push the changeset
- Stage the changeset file and in-scope fixes by explicit path; sweep `git status --porcelain` for hook artifacts (a root `schema.gql` is a known one) before committing.
- Commit (`chore: add <type> changeset for <package>`) and push.
- The pushed commit must still contain `.changeset/*.md` (first Gotcha).
### Step 4a: Watch CI on the pushed commit
- Load `references/ci-polling.md`.
- Start the commit watch on the pushed SHA. It emits a line per state change and one `TERMINAL:` line when every run for that commit (CI and the release workflow) completes. An idle first poll is normal; runs take time to queue.
- On failure, classify from `gh run view <id> --log-failed`: flaky or infra gets `gh run rerun <id> --failed` (max 3); a real failure gets a fix, commit, push, and a fresh watch on the new SHA.
### Step 4b: Find and merge the Version Packages PR
- Load `references/version-pr-and-publish.md`.
- Find the open PR whose head is `changeset-release/<default-branch>`. If absent, run the PR-wait watch (10-minute cap).
- Merge only when all three hold:
- Head branch is `changeset-release/<default-branch>` (title normally "Version Packages", but `pr-title` can rename it). Never merge any other PR.
- `gh pr checks <n> --json name,bucket` reports `bucket: pass` for every check.
- `gh pr view <n> --json mergeable` reports `MERGEABLE` (on `UNKNOWN`, wait and re-query).
- Announce ("Merging Version Packages PR #N: <package>@<version>"), then `gh pr merge <n> --squash --delete-branch`, or the merge method the repo allows. Any failed precondition: stop and report, never merge.
### Step 5: Watch the publish run, verify on npm
- Merging triggers the same workflow again; with no pending changesets it publishes.
- Take the merge SHA (`gh pr view <n> --json mergeCommit --jq .mergeCommit.oid`) and run the commit watch on it.
- On failure: read the log, match it against the publish failure table in `references/version-pr-and-publish.md`, report, and stop. Publish failures are never retried blind; every cause on that table needs a config or settings change.
- On success: `npm view <package>@<version> version` must print the merged version, and `npm view <package> dist-tags` must show `latest` pointing at it (unless pre mode). Stop remaining watches and report both outputs; they are the completion evidence.
## Failure Recovery
Stop and report on a gate still failing after 5 iterations or any failed merge precondition; never override failing checks or resolve conflicts in the bot PR. Diagnosis lives with each stage: CI and Changeset Status failures in `references/ci-polling.md`, a missing Version Packages PR and publish failures in `references/version-pr-and-publish.md`.
## Gotchas
- **Never run `pnpm changeset version` locally.** It consumes `.changeset/*.md`, so the pushed commit has no pending changeset, "Changeset Status" fails, and no Version Packages PR opens. Recovery is reverting the bump, not rerunning CI.
- Never run `pnpm publish` or `npm publish` directly. It bypasses changesets, skips the changelog and tag, and leaves the Version Packages PR describing an already-shipped version, which then fails with "You cannot publish over the previously published versions".
- Never hand-edit `CHANGELOG.md` or the `package.json` `version`. CI generates both in the Version Packages PR; local edits make the bot PR `CONFLICTING`.
- `changesets/action@v2` renamed every input (`publish` to `publish-script`, `version` to `version-script`, `title` to `pr-title`, `commit` to `commit-message`, `branch` to `pr-base-branch`). The old names are ignored with only a warning, so a `@v2` workflow still using `publish:` opens the Version PR and then completes green without publishing anything.From mblode/agent-skills, MIT.
More from mblode/agent-skills
- 0.791score
agent-ready
mblode
Implements agent-readiness on public sites and docs from Mintlify Agent Score, AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench reports, or from…
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
agent-skills-creator
mblode
Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
agents-md
mblode
Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
ax-audit
mblode
Audits agentic products for tool parity, authority, approval payloads, recovery, and trust using 24 rules and a ship verdict.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
chat-history
mblode
Recovers decisions, previous fixes, research, and what followed a prompt from past AI conversations, with source evidence.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
ci-speedup
mblode
Speeds up CI and the merge path: finds where changes wait between push and deploy, then fixes the critical path, check placement, merge queue or post-merge…
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
codebase-architecture
mblode
Designs module interfaces, deepens shallow modules, and installs enforceable repository guardrails and agent wayfinding.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
dx-audit
mblode
Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
eli5
mblode
Picks the form that explains best and applies the house explanation style: plain prose, controlled English modelled on ASD-STE100, a diagram, an interactive…
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
ghostwriter
mblode
Writes, rewrites, and critiques messages, posts, review comments, tickets, PRDs, design docs, talk scripts, docs, READMEs, and copy as the user or their…
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
multi-tenant-architecture
mblode
Designs tenant isolation, hostname routing, custom-domain lifecycle, and plan limits on Cloudflare or Vercel.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
planning
mblode
Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria.
SkillAFreshness: A★ 162Claude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 162
- Forks
- 14
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mblode/agent-skills
- Website
- blode.co/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mblode
- 0.791score
agent-ready
mblode
Implements agent-readiness on public sites and docs from Mintlify Agent Score, AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench reports, or from…
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
agent-skills-creator
mblode
Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
agents-md
mblode
Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
ax-audit
mblode
Audits agentic products for tool parity, authority, approval payloads, recovery, and trust using 24 rules and a ship verdict.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
chat-history
mblode
Recovers decisions, previous fixes, research, and what followed a prompt from past AI conversations, with source evidence.
SkillAFreshness: A★ 162Claude Code +9 - 0.791score
ci-speedup
mblode
Speeds up CI and the merge path: finds where changes wait between push and deploy, then fixes the critical path, check placement, merge queue or post-merge…
SkillAFreshness: A★ 162Claude Code +9
Cite this page
autoship skill. Agent Mart. https://agentmart.dev/skills/mblode-autoship (last updated 2026-10-24)