Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release.

MITAuto-check: notesDevelopment

Install Ship

skills CLI
$ npx skills add catlog22/Claude-Code-Workflow --skill ship -a claude-code

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

GitHub CLI
$ gh skill install catlog22/Claude-Code-Workflow ship --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/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ship .claude/skills/ship && 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
ship
GitHub stars
2.1k
Token cost
~1.8k tokens
SKILL.md length
431 words
Files
8
Skills in repo
82
Repo updated
First seen
Licence
MIT

At a glance

Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release.

  • Works in 5 steps: Phase Gates: Each phase must pass before… → Multi-Project Support: Detects npm… → AI-Powered Review: Uses CCW CLI to run… → …
  • Tasks that involve Changelog and release notes
  • SKILL.md covers Key Design Principles, Architecture Overview, Execution Flow and Pre-Flight Checklist (Quick…, plus 2 more sections
  • Calls git, npm and python

What it does

Ship is an agent skill from catlog22/Claude-Code-Workflow. Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release. Triggers on "ship", "release", "publish".

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `phases/01-preflight-checks.md`, `phases/02-code-review.md` and `phases/03-version-bump.md`).

It sits in Development, covering Changelog and release notes and Code review. It works with GitHub, npm and Git. The repository describes itself as: JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution. The licence is MIT.

When your agent uses it

  • Tasks that involve Changelog and release notes
  • Tasks that involve Code review

Example prompts

  • “release”
  • “publish”
  • “/ship”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Bash, Glob, Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Phase Gates: Each phase must pass before the next begins — no shipping broken code
  2. Multi-Project Support: Detects npm (package.json), Python (pyproject.toml), and generic (VERSION) projects
  3. AI-Powered Review: Uses CCW CLI to run automated code review before release
  4. Audit Trail: Each phase produces structured output for traceability
  5. Safe Defaults: Warns on risky operations (direct push to main, major version bumps)

What it can do on your machine

Read from SKILL.md and the folder at commit 07491b0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm
    • python

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

  • Network

    No URLs in SKILL.md. Its commands use git and npm, 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 no API keys, tokens, secrets or passwords.

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

Context cost

Ship loads about 1.8k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 431 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash, Glob, Grep

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 catlog22/Claude-Code-Workflow at commit 07491b0, republished under its MIT licence (© catlog22). 431 words, ~1,794 tokens.

Download SKILL.mdSave it as .claude/skills/ship/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
ship
description
Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release. Triggers on "ship", "release", "publish".
allowed-tools
Read, Write, Bash, Glob, Grep

Ship

Structured release pipeline that guides code from working branch to a published release through 7 gated phases: pre-flight checks, automated code review, version bump, changelog generation, PR creation, platform publish (npm/PyPI/etc.), and GitHub release.

Phases 5 (PR) and 6 (Publish) are conditionally skippable — trunk-based workflows that commit directly to main skip Phase 5; private packages skip Phase 6. Phase 7 (GitHub release) is the terminal phase and always runs unless the publish step failed.

Key Design Principles

  1. Phase Gates: Each phase must pass before the next begins — no shipping broken code
  2. Multi-Project Support: Detects npm (package.json), Python (pyproject.toml), and generic (VERSION) projects
  3. AI-Powered Review: Uses CCW CLI to run automated code review before release
  4. Audit Trail: Each phase produces structured output for traceability
  5. Safe Defaults: Warns on risky operations (direct push to main, major version bumps)

Architecture Overview

User: "ship" / "release" / "publish"
         |
         v
┌──────────────────────────────────────────────────────────┐
│  Phase 1: Pre-Flight Checks                              │
│  → git clean? branch ok? tests pass? build ok?           │
│  → Output: preflight-report.json                         │
│  → Gate: ALL checks must pass                            │
├──────────────────────────────────────────────────────────┤
│  Phase 2: Code Review                                    │
│  → detect merge base, diff against base                  │
│  → ccw cli --tool gemini --mode analysis                 │
│  → flag high-risk changes                                │
│  → Output: review-summary                                │
│  → Gate: No critical issues flagged                      │
├──────────────────────────────────────────────────────────┤
│  Phase 3: Version Bump                                   │
│  → detect version file (package.json/pyproject.toml/VERSION)
│  → determine bump type from commits or user input        │
│  → update version file                                   │
│  → Output: version change record                         │
│  → Gate: Version updated successfully                    │
├──────────────────────────────────────────────────────────┤
│  Phase 4: Changelog & Commit                             │
│  → generate changelog from git log since last tag        │
│  → update CHANGELOG.md                                   │
│  → create release commit, push to remote                 │
│  → Output: commit SHA                                    │
│  → Gate: Push successful                                 │
├──────────────────────────────────────────────────────────┤
│  Phase 5: PR Creation (skippable for trunk-based)        │
│  → gh pr create with structured body                     │
│  → auto-link issues from commits                         │
│  → Output: PR URL                                        │
│  → Gate: PR created OR skipped (direct-to-main)          │
├──────────────────────────────────────────────────────────┤
│  Phase 6: Platform Publish (skippable if private)        │
│  → detect registry (npm / PyPI / crates.io)              │
│  → npm publish / twine upload / cargo publish            │
│  → verify new version is live on registry                │
│  → Output: published artifact metadata                   │
│  → Gate: registry confirms version OR skipped (private)  │
├──────────────────────────────────────────────────────────┤
│  Phase 7: GitHub Release                                 │
│  → git tag -a vX.Y.Z + push tag                          │
│  → gh release create with structured notes               │
│  → Output: release URL                                   │
│  → Gate: release URL returned                            │
└──────────────────────────────────────────────────────────┘

Execution Flow

Execute phases sequentially. Each phase has a gate condition — if the gate fails, stop and report status.

  1. Phase 1: Pre-Flight Checks -- Validate git state, branch, tests, build
  2. Phase 2: Code Review -- AI-powered diff review with risk assessment
  3. Phase 3: Version Bump -- Detect and update version across project types
  4. Phase 4: Changelog & Commit -- Generate changelog, create release commit, push
  5. Phase 5: PR Creation -- Create PR with structured body and issue links (skip for trunk-based)
  6. Phase 6: Platform Publish -- Publish to npm / PyPI / crates.io (skip for private packages)
  7. Phase 7: GitHub Release -- Tag release commit and publish GitHub release notes
Show full SKILL.md (180 more words)Show less

Pre-Flight Checklist (Quick Reference)

CheckCommandPass Condition
Git cleangit status --porcelainEmpty output
Branchgit branch --show-currentNot main/master
Testsnpm test / pytestExit code 0
Buildnpm run build / python -m buildExit code 0

Completion Status Protocol

This skill follows the Completion Status Protocol defined in SKILL-DESIGN-SPEC.md sections 13-14.

Every execution terminates with one of:

StatusWhen
DONEAll applicable phases completed, GitHub release published
DONE_WITH_CONCERNSRelease published but with review warnings, skipped publish (private pkg), or non-critical issues
BLOCKEDA gate failed (dirty git, tests fail, push rejected, publish failed, tag conflict)
NEEDS_CONTEXTCannot determine bump type, ambiguous branch target, unclear registry target
Escalation

Follows the Three-Strike Rule (SKILL-DESIGN-SPEC section 14). On 3 consecutive failures at the same step, stop and output diagnostic dump.

Reference Documents

DocumentPurpose
phases/01-preflight-checks.mdGit, branch, test, build validation
phases/02-code-review.mdAI-powered diff review
phases/03-version-bump.mdVersion detection and bump
phases/04-changelog-commit.mdChangelog generation and release commit
phases/05-pr-creation.mdPR creation with issue linking (skippable)
phases/06-platform-publish.mdnpm / PyPI / crates.io publish (skippable)
phases/07-github-release.mdTag and GitHub release notes
../_shared/SKILL-DESIGN-SPEC.mdSkill design spec (completion protocol, escalation)

© catlog22, 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 7 other files in .claude/skills/ship of catlog22/Claude-Code-Workflow.

  • SKILL.md
  • phases/01-preflight-checks.md
  • phases/02-code-review.md
  • phases/03-version-bump.md
  • phases/04-changelog-commit.md
  • phases/05-pr-creation.md
  • phases/06-platform-publish.md
  • phases/07-github-release.md

Open the folder on GitHubat commit 07491b0

Compare with similar skills

Ship 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.

Ship compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ship this skillcatlog22/Claude-Code-Workflow2.1k—~1.8kAutomated safety check: NotesMIT
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Hunk Release Workflowmodem-dev/hunk9.5k—~3.8kAutomated safety check: PassMIT
ZCF Release AutomationUfoMiao/zcf6.1k—~3.4kAutomated safety check: PassMIT
ClawRouter Release ChecklistBlockRunAI/ClawRouter6.6k—~1.4kAutomated safety check: PassMIT
Release Clawpatchopenclaw/clawpatch813—~1.1kAutomated safety check: PassMIT

Similar skills

  • Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Hunk Release Workflow

    modem-dev/hunk

    Maintainer workflow for preparing, publishing, verifying and curating Hunk releases, with confirmation gates before tags, publishes and public edits.

    9.5k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Automates a version release with changesets: analyzes code changes, writes a bilingual CHANGELOG, bumps the version and commits through a release branch and pull request.

    6.1k GitHub stars~3.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • ClawRouter Release Checklist

    BlockRunAI/ClawRouter

    Walks the agent through every ClawRouter release step in order, from the version bump and changelog entry to build, tests, npm publish, git tag and GitHub release.

    6.6k GitHub stars~1.4k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Release Clawpatch

    openclaw/clawpatch

    clawpatch release: version/changelog, CI, npm publish, GitHub release, verify.

    813 GitHub stars~1.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Release

    OvenMediaLabs/OvenPlayer

    Release ovenplayer to npm — confirm the version, verify the committed dist/ bundle is current, write the release notes, and open a draft GitHub Release for the user to publish.

    592 GitHub stars~1.3k tokensUpdated 24 days ago
    DevelopmentAuto-check passed

More from catlog22/Claude-Code-Workflow

All 82 skills in this repo
  • Prompt Generator

    catlog22/Claude-Code-Workflow

    Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files.

    2.1k GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check: notes
  • Ccw Help

    catlog22/Claude-Code-Workflow

    CCW command help system. An agent skill from catlog22/Claude-Code-Workflow.

    2.1k GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Team Ultra Analyze

    catlog22/Claude-Code-Workflow

    Deep collaborative analysis team skill. An agent skill from catlog22/Claude-Code-Workflow.

    2.1k GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check: notes
  • Brainstorm

    catlog22/Claude-Code-Workflow

    Unified brainstorming skill with dual-mode operation — auto mode (framework generation, parallel multi-role analysis, cross-role synthesis) and single role analysis.

    2.1k GitHub stars~4.8k tokensUpdated 3 mo ago
    Auto-check: notes
  • Ccw Chain

    catlog22/Claude-Code-Workflow

    Chain-based CCW workflow orchestrator. An agent skill from catlog22/Claude-Code-Workflow.

    2.1k GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check: notes
  • Delegation Check

    catlog22/Claude-Code-Workflow

    Check workflow delegation prompts against agent role definitions for content separation violations.

    2.1k GitHub stars~2.8k tokensUpdated 3 mo ago
    Auto-check: notes

Works with

Categories

Questions about Ship

What does Ship do?

Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release. Ship is an agent skill from catlog22/Claude-Code-Workflow. Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release.

When should I use Ship?

Ship fits situations like: tasks that involve Changelog and release notes; tasks that involve Code review.

How do I install Ship in Claude Code?

Run `npx skills add catlog22/Claude-Code-Workflow --skill ship -a claude-code`. Or copy the skill folder (.claude/skills/ship in catlog22/Claude-Code-Workflow) into .claude/skills/ship in your project. Claude Code loads it when a task matches its description.

How do I install Ship in Codex?

Run `npx skills add catlog22/Claude-Code-Workflow --skill ship -a codex`. Or copy the skill folder (.claude/skills/ship in catlog22/Claude-Code-Workflow) into .agents/skills/ship in your project. Codex loads it when a task matches its description.

Can I use Ship 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 catlog22/Claude-Code-Workflow --skill ship -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ship, .gemini/skills/ship, .github/skills/ship and .opencode/skills/ship in your project.

What does Ship need to run?

Going by SKILL.md and its folder, Ship needs the command-line tools its instructions call (git, npm and python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Bash, Glob, Grep.

Does Ship access the network?

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

Is Ship safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Ship use?

Ship 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 Ship use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ship?

Skills that share tags, products or a category with Ship: Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars), Hunk Release Workflow (modem-dev/hunk, 9.5k stars), ZCF Release Automation (UfoMiao/zcf, 6.1k stars) and ClawRouter Release Checklist (BlockRunAI/ClawRouter, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ship?

catlog22 (a GitHub user) maintains it in catlog22/Claude-Code-Workflow, which has 2,130 GitHub stars. The repository holds 82 skills in this directory. The repository was last updated on June 18, 2026.

Source: catlog22/Claude-Code-Workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.