New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ship Workflow

by Mathews-Tom in Mathews-Tom/armory

Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation.

MITAuto-check passedDevelopment

Install Ship Workflow

skills CLI
$ npx skills add Mathews-Tom/armory --skill ship-workflow -a claude-code

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

GitHub CLI
$ gh skill install Mathews-Tom/armory ship-workflow --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/Mathews-Tom/armory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ship-workflow .claude/skills/ship-workflow && 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-workflow
GitHub stars
328
Token cost
~1.7k tokens
SKILL.md length
695 words
Files
3 (incl. references)
Skills in repo
80
Repo updated
First seen
Licence
MIT

At a glance

Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation.

  • Works in 8 steps: Pre-flight Checks → Merge Default Branch → Run Tests → …
  • Prepare for release
  • SKILL.md covers Pipeline Overview, Step 1: Pre-flight Checks, Step 2: Merge Default Branch and Step 3: Run Tests, plus 7 more sections
  • Calls git, gh and make

What it does

Ship Workflow is an agent skill from Mathews-Tom/armory. Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `evals/cases.yaml` and `references/project-detection.md`).

It sits in Development, covering Pull requests and Changelog and release notes. The repository describes itself as: Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously. The licence is MIT.

When your agent uses it

  • Prepare for release
  • Tasks that involve Pull requests
  • Tasks that involve Changelog and release notes

Example prompts

  • “ship it”
  • “release this”
  • “prepare for release”
  • “/ship-workflow”

Workflow steps

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

  1. Pre-flight Checks
  2. Merge Default Branch
  3. Run Tests
  4. Pre-Landing Review
  5. Version Bump
  6. Update Changelog
  7. Create Bisectable Commits
  8. Push and Create PR

What it can do on your machine

Read from SKILL.md and the folder at commit 4594fb7. 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:

    • git
    • gh
    • make
    • uv
    • cargo
    • go
    • bundle

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

  • Network

    Links to these hosts (documentation or services it may open):

    • keepachangelog.com

    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 Workflow loads about 1.7k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 695 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

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 Mathews-Tom/armory at commit 4594fb7, republished under its MIT licence (© Mathews-Tom). 695 words, ~1,749 tokens.

Download SKILL.mdSave it as .claude/skills/ship-workflow/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
ship-workflow
description
Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".
metadata.version
1.0.1
metadata.category
review
metadata.tags
release, ci-cd, pull-request, changelog
metadata.difficulty
intermediate
metadata.phase
ship

Ship Workflow

Automated release pipeline that takes a feature branch from working state to merged PR. Executes a deterministic sequence of pre-flight checks, testing, review, versioning, and PR creation — stopping immediately on any failure with specific remediation instructions.

Pipeline Overview

pre-flight → merge main → test → review → version bump → changelog → bisectable commits → push → PR

Each step has explicit stop conditions. The pipeline never auto-resolves ambiguity.

Step 1: Pre-flight Checks

Run all three checks before proceeding:

  1. Not on default branch — detect the default branch dynamically:

    bash
    git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@'

    If the current branch matches: STOP. Instruct the user to create a feature branch.

  2. Clean working tree — git status --porcelain must produce no output. If dirty: STOP. List the uncommitted files and instruct the user to commit or stash.

  3. Up-to-date with remote — git fetch origin then compare local HEAD with origin/<current-branch>. If the remote is ahead: STOP. Instruct the user to pull or rebase.

If any check fails, STOP with the specific remediation instruction. Do not proceed.

Step 2: Merge Default Branch

bash
git fetch origin
git merge origin/<default-branch>
  • If merge conflicts occur: STOP. Report the conflicting files. Do not auto-resolve.
  • If clean: proceed.

Step 3: Run Tests

Detect the test command from project configuration using references/project-detection.md:

IndicatorTest Command
Makefile with test targetmake test
package.json with test script<detected-pkg-manager> run test
pyproject.toml with pytest configuv run pytest (or detected runner)
Cargo.tomlcargo test
go.modgo test ./...
Gemfile + Rakefilebundle exec rake test

Detection order: check each indicator top-to-bottom; use the first match.

  • If tests fail: STOP. Report the failure output. Do not proceed.
  • If no test command detected: warn the user and ask whether to proceed without tests.

Step 4: Pre-Landing Review

Invoke the pre-landing-review skill if available. Otherwise, perform a lightweight diff review against the default branch:

bash
git diff origin/<default-branch>...HEAD

Review the diff for:

  • Obvious bugs or logic errors
  • Security concerns (credentials, injection vectors)
  • Missing error handling on new code paths

Classification:

  • CRITICAL findings: STOP. Resolve before proceeding.
  • INFORMATIONAL findings: note them for inclusion in the PR description. Proceed.

Step 5: Version Bump

Detect the version strategy from project configuration using references/project-detection.md:

IndicatorVersion Location
VERSION fileUpdate file contents directly
package.json version fieldUpdate the field
pyproject.toml version fieldUpdate the field
Cargo.toml version fieldUpdate the field
Git tags onlyCreate tag at push time

Default bump level: PATCH.

  • For MINOR or MAJOR bumps: STOP. Confirm with the user before proceeding.
  • If no version strategy detected: skip the version bump entirely. Note the skip in the PR description.
Show full SKILL.md (298 more words)Show less

Step 6: Update Changelog

  • If CHANGELOG.md exists: prepend an entry in Keep a Changelog format.
  • If no changelog file exists: skip.

Auto-generate the entry from commit messages since the last tag or release. Group entries by conventional commit type:

markdown
## [<new-version>] - <date>

### Added

- feat: ...

### Fixed

- fix: ...

### Changed

- refactor: ...

Step 7: Create Bisectable Commits

Organize staged changes into logical, bisectable commit groups in this order:

  1. Infrastructure / config changes — build files, CI config, dependencies
  2. Models / services / core logic — domain layer, business rules
  3. Controllers / views / API endpoints — presentation and routing
  4. Version bump + changelog — always last

Each commit uses a descriptive conventional commit message. Each commit should pass tests independently when possible (verify if CI turnaround allows it; otherwise trust the ordering).

If all changes are already committed in a reasonable structure, skip reorganization.

Step 8: Push and Create PR

bash
git push -u origin <current-branch>

Create the PR:

bash
gh pr create \
  --title "<conventional-format-title>" \
  --body "<generated-body>"

PR body includes:

  • Summary of changes (grouped by commit)
  • Test results (pass confirmation)
  • Version bump details (old → new, or "skipped")
  • Any INFORMATIONAL findings from Step 4

Output the PR URL as the final result.

Stop Conditions

The pipeline halts immediately and reports when any of these occur:

ConditionStepAction
On default branch1Stop, instruct to create feature branch
Dirty working tree1Stop, list files, instruct to commit/stash
Behind remote1Stop, instruct to pull/rebase
Merge conflicts2Stop, report conflicting files
Test failures3Stop, report failure output
Critical review findings4Stop, resolve before proceeding
MINOR/MAJOR version bump5Stop, confirm with user

Important Notes

  • This skill modifies the repository: it creates commits, pushes code, and opens PRs.
  • All branch names and test commands are detected dynamically — nothing is hardcoded.
  • The version strategy is inferred from project files, not assumed.
  • If the pre-landing-review skill is not available, the review step degrades to a lightweight diff scan rather than skipping entirely.

© Mathews-Tom, 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 2 other files (references) in skills/ship-workflow of Mathews-Tom/armory.

  • SKILL.md
  • evals/cases.yaml
  • references/project-detection.md

Open the folder on GitHubat commit 4594fb7

Compare with similar skills

Ship Workflow 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 Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ship Workflow this skillMathews-Tom/armory328—~1.7kAutomated safety check: PassMIT
StarRocks Release NotesStarRocks/starrocks12k—~1.9kAutomated safety check: NotesApache-2.0
Git Workflow and Versioningaddyosmani/agent-skills103k2 repos~3.5kAutomated safety check: NotesMIT
Changesetbiomejs/biome26k—~839Automated safety check: PassApache-2.0
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
pybind11 Release Preparationpybind/pybind1118k—~1.7kAutomated safety check: PassCustom licence

Similar skills

  • StarRocks Release Notes

    StarRocks/starrocks

    Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.

    12k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check: notes

  • Git Workflow and Versioning

    addyosmani/agent-skills

    Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.

    103k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes

  • Changeset

    biomejs/biome

    Official

    A skill your agent uses when a Biome change may affect users and you must decide whether it needs a changeset, choose the release level, or create and edit .changeset/.md release-note text.

    26k GitHub stars~839 tokensUpdated today
    DevelopmentAuto-check passed

  • Verdaccio Pull Request Workflow

    verdaccio/verdaccio

    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 yesterday
    DevelopmentAuto-check passed

  • pybind11 Release Preparation

    pybind/pybind11

    Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.

    18k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed

  • AionUi Version Bump

    iOfficeAI/AionUi

    Automates an AionUi release: checks the latest AionCore release and its artifacts, updates package.json, writes the changelog, opens a PR and tags the release.

    33k GitHub stars~2.1k tokensUpdated 29 days ago
    DevelopmentAuto-check passed

More from Mathews-Tom/armory

All 80 skills in this repo

  • Architecture Reviewer

    Mathews-Tom/armory

    Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports.

    328 GitHub stars~4.6k tokensUpdated 2 days ago
    Auto-check passed

  • Concept To Image

    Mathews-Tom/armory

    Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG.

    328 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed

  • Watch

    Mathews-Tom/armory

    A skill your agent uses when analyzing an existing video URL or local recording: "watch this video", "analyze youtube video", "summarize this video", "youtube transcript", "find this moment", "what…

    328 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed

  • Code Refiner

    Mathews-Tom/armory

    Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust.

    328 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed

  • Concept To Video

    Mathews-Tom/armory

    Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.

    328 GitHub stars~4.9k tokensUpdated 2 days ago
    Auto-check passed

  • Decision Map

    Mathews-Tom/armory

    Maps the unresolved architecture, policy, and scope decisions that must be answered before planning can start: one durable decision ticket per question on the issue tracker, typed and blocker-linked…

    328 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Ship Workflow

What does Ship Workflow do?

Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Ship Workflow is an agent skill from Mathews-Tom/armory. Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation.

When should I use Ship Workflow?

Ship Workflow fits situations like: prepare for release; tasks that involve Pull requests; tasks that involve Changelog and release notes.

How do I install Ship Workflow in Claude Code?

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

How do I install Ship Workflow in Codex?

Run `npx skills add Mathews-Tom/armory --skill ship-workflow -a codex`. Or copy the skill folder (skills/ship-workflow in Mathews-Tom/armory) into .agents/skills/ship-workflow in your project. Codex loads it when a task matches its description.

Can I use Ship Workflow 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 Mathews-Tom/armory --skill ship-workflow -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-workflow, .gemini/skills/ship-workflow, .github/skills/ship-workflow and .opencode/skills/ship-workflow in your project.

What does Ship Workflow need to run?

Going by SKILL.md and its folder, Ship Workflow needs the command-line tools its instructions call (git, gh, make, uv, cargo and go).

Does Ship Workflow access the network?

SKILL.md names 1 domain. As links in the text: keepachangelog.com. This is read from the text; nothing was executed.

Is Ship Workflow 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 Ship Workflow use?

Ship Workflow 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 Workflow use?

About 1.7k tokens (SKILL.md is roughly 7k 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 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Ship Workflow?

Skills that share tags, products or a category with Ship Workflow: StarRocks Release Notes (StarRocks/starrocks, 12k stars), Git Workflow and Versioning (addyosmani/agent-skills, 103k stars), Changeset (biomejs/biome, 26k stars) and Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ship Workflow?

Mathews-Tom (a GitHub user) maintains it in Mathews-Tom/armory, which has 328 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on October 6, 2026.

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