Agent skill

Autoship

by mblode in mblode/agent-skills

Runs a changesets npm release through the version PR, CI publish, and registry verification.

MITAuto-check passed

Install Autoship

skills CLI
$ npx skills add mblode/agent-skills --skill autoship -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mblode/agent-skills autoship --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mblode/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/autoship .claude/skills/autoship && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autoship
GitHub stars
144
Token cost
~3k tokens
SKILL.md length
1,597 words
Files
5 (incl. references)
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Runs a changesets npm release through the version PR, CI publish, and registry verification.

  • Works in 4 steps: Create changeset (default patch) → Fix lint, types, tests, format → Commit and push the changeset → …
  • Asked to release this package
  • SKILL.md covers The Release Loop, Reference Files, Intent Map and Safety Tiers, plus 4 more sections
  • Calls gh, npm and git; needs NPM_TOKEN

What it does

Autoship is an agent skill from mblode/agent-skills. 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.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `evals/evals.json`, `references/changeset-and-commit.md` and `references/ci-polling.md`). Compatibility notes: Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow.

It works with npm. The repository describes itself as: Nobody ships AI slop on purpose. These skills make sure you don’t. The licence is MIT.

When your agent uses it

  • Asked to release this package
  • Merge Version Packages
  • Diagnose a release that did not publish

Example prompts

  • “release this package”
  • “autoship”
  • “merge Version Packages”
  • “/autoship”

Requirements

  • Node.js
  • A credential in NPM_TOKEN
  • Compatibility (from SKILL.md): Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Create changeset (default patch)
  2. Fix lint, types, tests, format
  3. Commit and push the changeset
  4. Watch the publish run, verify on npm

What it can do on your machine

Read from SKILL.md and the folder at commit 5a781a8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • npm
    • git
    • changeset
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, npm, git and npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • NPM_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow.

    From compatibility in the SKILL.md frontmatter.

Context cost

Autoship loads about 3k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 1,597 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mblode/agent-skills at commit 5a781a8, republished under its MIT licence (© mblode). 1,597 words, ~2,978 tokens.

Download SKILL.mdSave it as .claude/skills/autoship/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
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.
compatibility
Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow.

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

FileRead when
references/changeset-and-commit.mdSteps 1-3: writing the changeset file, discovering and running gates non-interactively, staging the release commit
references/ci-polling.mdStep 4 and Step 5 watches: the Monitor tool, the commit watch script, failure classification, the Changeset Status check
references/version-pr-and-publish.mdOnce CI is green: workflow shape, finding and merging the Version Packages PR, the publish run, npm verification, publish failure diagnosis
evals/evals.jsonOnly when changing this skill; never loads during a release

Intent Map

IntentStepsNotes
Full autoship (ship / release / publish)1-5Default entry point. End to end through publish, no intermediate prompts
Create changeset only1Stage a release without pushing
Fix gates and push1-3Changeset, fixes, commit, no CI watch
Watch CI only4-5Changeset already pushed
Merge Version Packages PR only4b-5CI already green; merges once preconditions hold
Fix gates only2Inside a release flow; no changeset needed
Diagnose a release that did not publishread-onlyreferences/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.
  • npx 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-npm 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.
Show full SKILL.md (620 more words)Show less
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 npx 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 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.
  • setup-node with node-version: 22 ships npm 10.9.x. Trusted publishing needs npm 11.5.1 or later, so changeset publish fails ENEEDAUTH even with id-token: write set. Use Node 24 or add npm install -g npm@latest before publishing.
  • A workflow authenticating with an NPM_TOKEN secret that holds a classic token fails ENEEDAUTH: npm revoked every classic token on 9 December 2025. Move to trusted publishing rather than minting a new token; write-capable granular tokens expire within 90 days.
  • npm does not validate a trusted publisher when you save it. A workflow filename that differs from .github/workflows/<file>.yml by case or extension surfaces only at publish time, as ENEEDAUTH.
  • New personal repos block Actions from opening PRs. The release run fails with "GitHub Actions is not permitted to create or approve pull requests" and no Version PR appears. Fix: Settings, Actions, General, "Allow GitHub Actions to create and approve pull requests" (an org-level setting can override it). Red tier: report it, do not change settings unasked.
  • gh pr list --json headBranch and gh pr checks --json conclusion are invalid fields and error. Use headRefName and bucket.
  • The Monitor tool's default timeout_ms is 300000 (5 minutes). A CI run that outlasts it kills the watch with a timeout that looks like silence. Pass timeout_ms: 3600000 for CI watches.
  • Poll every 30 seconds or slower. Faster loops burn the GitHub API rate limit (gh api rate_limit --jq .resources.core.remaining) and stall the flow mid-release.
  • git add -A commits pre-commit-hook artifacts and fixer churn into the release commit. Stage explicit paths.
  • major without explicit instruction signals breaking changes to every consumer. Default to patch.
  • scaffold-cli: scaffolds a new TypeScript package with changesets and OIDC publishing, then hands off to autoship for its first release.
  • pr-creator: opens feature PRs. Autoship merges only the bot-opened Version Packages PR.
  • pr-babysitter: watches feature PRs (reviews, conflicts, CI). Autoship watches release CI only; never babysit a Version Packages PR autoship is driving.

© mblode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/autoship of mblode/agent-skills.

  • SKILL.md
  • evals/evals.json
  • references/changeset-and-commit.md
  • references/ci-polling.md
  • references/version-pr-and-publish.md

Open the folder on GitHubat commit 5a781a8

Compare with similar skills

Autoship next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autoship compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autoship this skillmblode/agent-skills144—~3kAutomated safety check: PassMIT
Defuddlekepano/obsidian-skills49k11 repos~208Automated safety check: PassMIT
Vercel Deploybytedance/deer-flow84k10 repos~797Automated safety check: PassMIT
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Knap Markdown Templateskepano/obsidian-skills49k2 repos~986Automated safety check: PassMIT
Nx Run Tasksnomcopter/react-mosaic4.8k8 repos~613Automated safety check: PassCustom licence

Similar skills

  • Defuddle

    kepano/obsidian-skills

    Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

    49k GitHub starsUsed in 11 repos~208 tokens
    Knowledge ManagementAuto-check passed
  • Vercel Deploy

    bytedance/deer-flow

    Deploys a project to Vercel with one script and no login, then returns a live preview URL and a claim link for moving the deployment into your own Vercel account.

    84k GitHub starsUsed in 10 repos~797 tokens
    DevOps & CloudAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Knap Markdown Templates

    kepano/obsidian-skills

    Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.

    49k GitHub starsUsed in 2 repos~986 tokens
    Documents & OfficeAuto-check passed
  • Nx Run Tasks

    nomcopter/react-mosaic

    Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 8 repos~613 tokens
    DevelopmentAuto-check passed
  • Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

    16k GitHub starsUsed in 1 repo~2.1k tokens
    Testing & QAAuto-check: notes

More from mblode/agent-skills

All 28 skills in this repo
  • Agent Ready

    mblode/agent-skills

    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 server logs of agents 404ing on guessed…

    144 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Agent Skills Creator

    mblode/agent-skills

    Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions.

    144 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Chat History

    mblode/agent-skills

    Recovers decisions, previous fixes, research, and what followed a prompt from past AI conversations, with source evidence.

    144 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • CI Speedup

    mblode/agent-skills

    Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding, trimming setup and sharing test module state, with a before/after ledger.

    144 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • PR Babysitter

    mblode/agent-skills

    Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes.

    144 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • UI Animation

    mblode/agent-skills

    Builds, reviews, and measures UI motion, including springs, gestures, scroll effects, curve fitting from recordings, and sparse interface sound.

    144 GitHub stars~5.7k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Autoship

What does Autoship do?

Runs a changesets npm release through the version PR, CI publish, and registry verification. Autoship is an agent skill from mblode/agent-skills. Runs a changesets npm release through the version PR, CI publish, and registry verification.

When should I use Autoship?

Autoship fits situations like: asked to release this package; merge Version Packages; diagnose a release that did not publish.

How do I install Autoship in Claude Code?

Run `npx skills add mblode/agent-skills --skill autoship -a claude-code`. Or copy the skill folder (skills/autoship in mblode/agent-skills) into .claude/skills/autoship in your project. Claude Code loads it when a task matches its description.

How do I install Autoship in Codex?

Run `npx skills add mblode/agent-skills --skill autoship -a codex`. Or copy the skill folder (skills/autoship in mblode/agent-skills) into .agents/skills/autoship in your project. Codex loads it when a task matches its description.

Can I use Autoship in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mblode/agent-skills --skill autoship -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoship, .gemini/skills/autoship, .github/skills/autoship and .opencode/skills/autoship in your project.

What does Autoship need to run?

Going by SKILL.md and its folder, Autoship needs the command-line tools its instructions call (gh, npm, git, changeset and npx) and credentials named NPM_TOKEN. Our summary lists: Node.js; A credential in NPM_TOKEN. Compatibility (from SKILL.md): Requires a Git checkout, GitHub CLI authentication, Node.js, and a changesets-based npm release workflow..

Does Autoship access the network?

SKILL.md contains no URLs. Its commands use gh, npm, git and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Autoship safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Autoship use?

Autoship is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autoship use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.

What are the alternatives to Autoship?

Skills that share tags, products or a category with Autoship: Defuddle (kepano/obsidian-skills, 49k stars), Vercel Deploy (bytedance/deer-flow, 84k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and Knap Markdown Templates (kepano/obsidian-skills, 49k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autoship?

mblode (a GitHub user) maintains it in mblode/agent-skills, which has 144 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: mblode/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.