Change the priority of a pending job (low, normal, high)
Cancel a pending or running job
Regenerate CHANGELOG.md from git tags, check for drift, or initialize the post-release docs sync config. Wraps `shipyard changelog`.
Check if a branch is ready to merge based on evidence
Dispatch and inspect GitHub Actions workflows from Shipyard
Post-release docs sync — regenerate CHANGELOG.md from git tags, install the post-tag GitHub Actions hook, and diagnose drift. Use when a release just landed and the CHANGELOG didn't update, when a project wants to adopt shipyard-managed release notes, or when CI flags "CHANGELOG.md out of date".
Cross-platform CI coordination with Shipyard — validates, ships, manages queue, and runs cloud workflows
Shipyard operations guardrails. Use when working in /Users/danielraffel/Code/shipyard, /Users/danielraffel/Code/shipyard-rust, or /Users/danielraffel/Code/shipyard-macos-gui on parity checks, drift checks, sandbox validation, live Tailscale/GitHub webhook validation, release signing, GUI validation, Pulp/consumer pin cutover, or any go/no-go migration work.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Cross-platform CI for AI agents. Validates the exact commit on every machine you configure — local Mac, SSH-reachable VMs, cloud runners — and merges only when everything is green.
curl -fsSL https://generouscorp.com/Shipyard/install.sh | sh
cd my-project
shipyard init # detects your project, probes your machines
shipyard run # validates on every platform you configured
shipyard ship # validate, open PR, merge on green
shipyard watch # live-tail an in-flight ship
shipyard wait pr 151 --state green # wait on release / PR / run conditions
shipyard auto-merge <pr> # cron-friendly one-shot merge-on-green
shipyard rescue <pr> # cancel + redispatch every stuck queued run on a PR
shipyard runner watch --kill-hung-workers # daemon-mode prevent + auto-kill hung Workers
shipyard update # self-update the CLI (or `--check` to peek)
shipyard doctor --rate-limit # inspect REST + GraphQL buckets separately
shipyard release-bot setup # guided RELEASE_BOT_TOKEN setup
shipyard cloud retarget # switch one target's runner mid-flight
shipyard cloud add-lane # append a new lane to an in-flight PR
shipyard changelog init # opt in to post-release CHANGELOG auto-sync
shipyard ship refuses to merge unless
every required platform has passing evidence for the exact HEAD SHA —
not the most-recent run, not the branch tip, the SHA.solo or multi); one CLI command makes GitHub branch protection,
tag protection, and workflow token permissions match.shipyard init recognises CMake, Swift,
Xcode, Rust, Go, Node (pnpm/bun/yarn/npm), Python (uv/poetry/pip),
Gradle, Maven, .NET, Flutter, Dart, Deno, Ruby, Elixir, PHP.shipyard runner status /
cleanup --fix / watch --fix / watch --kill-hung-workers detect
and auto-recover the stuck-runner failure mode (orphaned busy state,
hung worker, stale queued runs). runner kill --pid <pid> is the
explicit one-shot equivalent. See docs/runner-watchdog.md.shipyard rescue <pr> cancels and
redispatches every stuck queued workflow run on a PR onto
github-hosted (or any provider via --to). --rerun-failed
also re-arms watchdog-cancelled runs; --all-stuck is the
repo-wide variant. Pairs with the watchdog to form a complete
prevent → recover toolkit.shipyard update is the discoverable
upgrade path (no more curl-pipe to remember); --check reports
installed-vs-available, --to v0.55.0 pins a specific tag for
rollback.shipyard auto-merge
and shipyard wait pr fall back to REST automatically when
GraphQL exhausts (separate 5000/hr bucket). shipyard doctor --rate-limit shows both buckets so you can see which one is hot.shipyard metrics records local command
timings, imports GitHub Actions jobs, and imports optional tartci VM timing
exports into a small SQLite store. Agents can ask for summaries, drift
findings, and placement advice without requiring tartci or any observability
service.Two commands to register the marketplace and install the plugin:
claude plugin marketplace add danielraffel/Shipyard
claude plugin install shipyard
Then set up your project:
/shipyard:init
The plugin uses the CLI under the hood. On first session start it
auto-installs the binary if it can't find shipyard on PATH — and
skips the install if it can. If you've already installed the CLI
(via install.sh or a project pinner like pulp's
tools/install-shipyard.sh), make sure its bin directory is on
PATH before you install the plugin; that way the plugin respects
your existing pin instead of installing its own copy alongside it.
Plugin + CLI are independently versioned; the plugin's version covers slash commands / skills / hooks, while the CLI's version covers the binary. It's safe to have both.
npx claudepluginhub danielraffel/shipyard --plugin shipyardAI-powered design thinking partner that helps explore ideas, generate visuals, and create prototypes through natural conversation
Generate agent team orchestration prompts from any task description
Create and manage JUCE audio plugin projects from the JUCE-Plugin-Starter template
Apply Google Research's prompt repetition technique to improve LLM performance on non-reasoning tasks
Claude Code plugin for the Pulp audio framework — build, test, design, and ship audio plugins and apps
Build CI/CD pipelines for GitHub Actions, GitLab CI, Jenkins, and more
Task-focused agents for test, review, debug, docs, CI, security, refactoring, research, performance, and search-replace — with teammate and subagent role guidance
CI/CD generation, deployment preflight, and Dockerfile validation with zero-downtime patterns.
Use this agent when setting up CI/CD pipelines, configuring Docker containers, deploying applications to cloud platforms, setting up Kubernetes clusters, implementing infrastructure as code, or automating deployment workflows. Examples: <example>Context: User is setting up a new project and needs deployment automation. user: "I've built a FastAPI application and need to deploy it to production with proper CI/CD" assistant: "I'll use the deployment-engineer agent to set up a complete deployment pipeline with Docker, GitHub Actions, and production-ready configurations."</example> <example>Context: User mentions containerization or deployment issues. user: "Our deployment process is manual and error-prone. We need to automate it." assistant: "Let me use the deployment-engineer agent to design an automated CI/CD pipeline that eliminates manual steps and ensures reliable deployments."</example>
Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.
Plugin-first Claude Code workflows with planning, CI/CD debugging, reusable agents, TODOs, and MCP safety policies.