ship
Use when implementation is complete, tests pass, and code needs to reach main — via PR with auto-merge (CI up) or local shallow-clone merge (CI down)
- Installs
- 388
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/camacho/ai-skills --skill ship- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ship automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Ship
Get the branch onto main. Two paths: PR (CI up) or local merge (CI down).
Announce: "Using /ship to integrate this branch."
Prerequisites
- On a feature branch (not main).
/review(Step 6) passed, or user explicitly approved.- Worktree path is known (needed for cleanup).
- No pending tasks. Run
TaskList(Claude Code) or check.branch-context.mdchecklist (Codex). If any step is stillpendingorin_progress, that step was skipped — go back and complete it before shipping.
If any prerequisite is missing, say which and stop.
Step 1: Validate
pnpm validate
If validation fails, stop. Fix first.
Step 2: Determine target branch
Resolution order (use the first that succeeds):
- Plan file frontmatter — read the
Target:field fromai-workspace/plans/<name>.mdif a plan exists. - Reflog parent — the branch's reflog records what it was created from:
TARGET=$( git -C <worktree> reflog show HEAD --pretty=format:'%gs' \ | grep "^branch: Created from" \ | head -1 \ | sed 's/branch: Created from //' \ | sed 's|^origin/||' ) - Remote HEAD —
git -C <worktree> symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||' - Default
main— final fallback. If ambiguous between sources, ask.
Step 3: Present options
CI status comes from conversation context — if the user has said CI is down, frozen, or at billing cap, treat as down. No auto-detection.
CI up (default):
Ready to ship.
1. Open PR + auto-merge
2. Keep branch as-is
3. Discard
CI down:
Ready to ship (CI down — local merge with review gate).
1. Local merge to main
2. Keep branch as-is
3. Discard
Option 1a: PR + auto-merge (CI up)
git -C <worktree> push -u origin <branch>
GH_REPO=<owner/repo> gh pr create \
--base "$TARGET" \
--title "<conventional-commit-title>" \
--body "$(cat <<'EOF'
## Summary
<2-3 bullets>
## Test plan
- [ ] <verification steps>
EOF
)"
GH_REPO=<owner/repo> gh pr merge --auto --merge
Report the PR URL. Proceed to worktree cleanup.
If CI blocks or fails after PR is up: STOP. Ask the user. No self-rescue, no local merge fallback, no force-merge.
Option 1b: Local merge (CI down)
Dispatch the code-reviewer agent on the diff first — all autonomous code must be reviewed before merge:
claude --agent code-reviewer "Review diff: git -C <worktree> diff $TARGET..HEAD"
If reviewer returns P0/P1 findings, STOP. Fix before proceeding.
Invoke /local-merge with BRANCH=<branch>, TARGET=$TARGET, PRIMARY=<primary-worktree-path>, MESSAGE="merge: <branch> into $TARGET". It handles the shallow clone, push with retry, and non-destructive propagation to primary.
Option 2: Keep as-is
Report: "Keeping branch <name>. Worktree preserved at <path>."
Do not clean up.
Option 3: Discard
Require typed "discard" confirmation. Show branch name, commit list, worktree path.
git -C <primary> worktree remove <worktree-path>
git -C <primary> branch -d <branch>
If branch -d fails (unmerged work), warn the user and stop — do NOT use branch -D. Only delete the remote branch after local delete succeeds:
git push origin --delete <branch>
Worktree Cleanup
After PR (1a) or local merge (1b):
# Unlock first (matches the lock applied by /isolate)
git -C <primary> worktree unlock <worktree-path> 2>/dev/null || true
git -C <primary> worktree remove <worktree-path>
Then prune the dead branch from local refs if git-trim is installed (handles squash-merged, rebase-merged, and [gone] upstream cases):
if command -v git-trim >/dev/null 2>&1; then
git -C <primary> trim --delete
fi
| Path | Cleanup worktree? |
|---|---|
| PR + auto-merge | Yes |
| Local merge | Yes |
| Discard | Yes (in discard step) |
| Keep as-is | No |
Integration
Called by: /task (Step 8) Pairs with: /isolate (cleans up worktree it created), /review (must pass before /ship)
FAQ
What does the ship skill do?
Use when implementation is complete, tests pass, and code needs to reach main — via PR with auto-merge (CI up) or local shallow-clone merge (CI down)
How do I install ship?
Run npx skills add https://github.com/camacho/ai-skills --skill ship in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ship/ (personal) or .claude/skills/ship/ (project).
Which AI agents can use ship?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ship safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains ship?
It is published by camacho in camacho/ai-skills. It has 388 recorded installs.
More from camacho/ai-skills
archive
camacho/ai-skills
Fills Outcomes & Learnings in a plan file and renames it to .done.md.
bail
camacho/ai-skills
Reflects, updates GitHub Issue, closes PR if open, cleans up worktree/branch.
capture
camacho/ai-skills
Creates a draft GitHub Issue with triage label from natural language description.
plan-review
camacho/ai-skills
Auto-assembles review panel using deterministic rules, dispatches agents against plan file, collects verdicts.
orient
camacho/ai-skills
Fetches issue context, auto-detects task type, maps to branch prefix, presents brief.
reflect
camacho/ai-skills
Use after merging a branch or completing a task to consolidate learnings into memory layers, close out issues, and verify the phase gate.
Popular devops & cloud skills
microsoft-foundry
microsoft/azure-skills
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure
azure-diagnostics
microsoft/azure-skills
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.
azure-prepare
microsoft/azure-skills
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.
azure-ai
microsoft/azure-skills
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
azure-deploy
microsoft/azure-skills
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
azure-validate
microsoft/azure-skills
Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.