ship
Skill1 starsChanged 6 days agoMITView on GitHub
Ships finished work end to end: checks, commits (via the commit skill), versioning, push, pull request (via the pr skill), CI pipeline watching, release and publish verification. Use when the user says "ship it", "ship this", "push and watch CI", "release", "cut a release", "publish", "bump the version", "anything uncommitted/unpushed?", "did the release run?", or invokes /ship.
- Reads credentials
- Commits and pushes
194 other projects use a version of this.
Adopted by
Most recently taken up by
- wboayue/rust-ibapitheir own version, first seen Nov 9, 2026
- haiggoh/run-to-completiontheir own version, first seen Nov 8, 2026
- sanmidable/skillstheir own version, first seen Nov 8, 2026
- Yesterday-AI/ytstacktheir own version, first seen Nov 8, 2026
- gaoyu06/harnesstheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ios-sync, open-gstack-browser and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 10 projects that use this
ayudaySkillsetup-deploy
Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".
Also in 19 projects that use this
ShreyRaviSkilllanding-report
Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)
Also in 9 projects that use this
zebbernSkilldebug-fix
Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)
Also in 4 projects that use this
ramybarsoumSkilldocument-release
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped.
Also in 23 projects that use this
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- garrytan/gstack★ 141ksame name
- rtk-ai/rtk★ 86ksame name
- simstudioai/sim★ 30ksame name
- millionco/react-doctor★ 15ksame name
- BuilderIO/agent-native★ 7.6ksame name
- nightly-labs/openbot★ 6.3ksame name
- fallow-rs/fallow★ 5.3ksame name
- puncsky/system-design-and-architecture★ 3.6ksame name
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- ShenSeanChen/waku-agent★ 2ksame name
184 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 23
Never force-push, skip hooks (--no-verify), or edit CI secrets.
- Distinctive: line 24
Don't bump a version that release tooling bumps itself.
- Very specific: line 54
Read .github/workflows/* to learn what runs on push, PR, tag and merge, and which commands CI runs (tests, lint, build).
- Distinctive: line 57
No release setup and no version file: skip versioning unless the user asks for it.
- Distinctive: line 72
Commit with the commit skill.
- Very specific: line 89
release-please: after the push to the default branch, find the release PR (gh pr list --label "autorelease: pending"), show its version and …
- Distinctive: line 92
Tag-driven: after the user confirms, push the tag, then watch the tag workflow.
- Distinctive: line 98
If a release workflow didn't run or didn't publish, find out why (missing trigger, failed job, skipped step, version already published) …
“Common” is measured: kept by at least 6 in 10 of the 180 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ship Skill
Take finished work from the working tree to a verified release, using the project's own release setup. Each step builds on the one before; stop and report when a step fails.
Ground rules
- Commits go through the commit skill, PRs through the pr skill. Never run
git commitorgh pr createdirectly. - Invoking this skill approves the commit + push for the current work. Merges, tags, publishing, and deploys to production still need the user's explicit OK, asked with AskUserQuestion.
- Never force-push, skip hooks (
--no-verify), or edit CI secrets. - Don't bump a version that release tooling bumps itself.
1. Preflight
Run in parallel:
git status --short,git branch --show-current,git log @{u}..HEAD --oneline(unpushed),git fetchthengit log HEAD..@{u} --oneline(behind)git remote get-url originandgh auth statusgit log $(git describe --tags --abbrev=0 2>/dev/null)..HEAD --oneline(since last tag)
Check:
- GitHub account: remotes may use SSH host aliases (for example
github.com-work). Make sureghis logged in as the account that owns the repo; if not, tell the user to rungh auth switch. - Behind the remote: pull/rebase first if the branch is behind.
- Secrets: scan the diff for tokens, keys,
.envfiles, and credentials before anything is committed. Stop and report if found.
2. Detect the release setup
| Found | Release mechanism | Version bump |
release-please-config.json / release-please action | Release PR from Conventional Commits; merging it tags, releases, publishes | Never manual |
.changeset/ | Changesets | Add a changeset (npx changeset), don't edit versions |
| semantic-release config | Fully automatic on push | Never manual |
Workflow on tags: | Pushing a tag triggers the release (Docker images, binaries) | Bump manifest if it holds the version, then tag vX.Y.Z |
package.json + npm publish without tooling | Manual | npm version <x> --no-git-tag-version |
Cargo.toml / pyproject.toml / gradle.properties / build.gradle(.kts) | Manual or tag-driven | Edit the version field |
| Xcode project | App Store / TestFlight | MARKETING_VERSION (+ CURRENT_PROJECT_VERSION build number) |
| Pages / deploy on push only | No versions | Nothing to bump |
Read .github/workflows/* to learn what runs on push, PR, tag and merge, and which
commands CI runs (tests, lint, build).
No release setup and no version file: skip versioning unless the user asks for it.
3. Pick the version (only when bumping manually)
Load the versioning skill: it detects the project's versioning scheme and decides the next version. Include the proposed version in the plan for approval.
4. Plan, then local checks
Show one short plan: commits to make, version (if any), push target, PR or not, what CI and release will do. Then run the same checks CI runs (tests, lint, typecheck, build) locally. Fix failures before committing; report anything you can't fix.
5. Commit and push
- Commit with the commit skill.
- Pick the target branch with the branching skill: it detects the project's branching strategy and says whether this work goes on a feature branch with a PR (opened with the pr skill) or straight to the default branch.
- Push with
git push -u origin <branch>. If a tag triggers the release, push the tag only after the user confirms.
6. Watch the pipelines
- Find the runs:
gh run list --branch <branch> --limit 5(andgh pr checks <pr>for PRs). - Watch them with
gh run watch <id> --exit-statusas a background command; don't poll in a loop. - On failure:
gh run view <id> --log-failed, find the cause, fix it, commit with the commit skill, push, and watch again. Report flaky or unrelated failures instead of retrying blindly.
7. Release and verify
- release-please: after the push to the default branch, find the release PR
(
gh pr list --label "autorelease: pending"), show its version and changelog, and ask the user before merging. After the merge, watch the release workflow. - Tag-driven: after the user confirms, push the tag, then watch the tag workflow.
- Verify the artifact actually exists:
- npm:
npm view <pkg>@<version> version - GitHub release:
gh release view <tag> - Docker: the image tag in the registry (workflow output or
docker manifest inspect) - Pages / deploy: the deploy run succeeded and the URL returns 200 (
curl -sI)
- npm:
- If a release workflow didn't run or didn't publish, find out why (missing trigger, failed job, skipped step, version already published) before suggesting a re-run.
8. Loose ends
- Open Dependabot PRs: list them with their check status (
gh pr list --author app/dependabot). Merge only when the user says so. - Leftover uncommitted or unpushed work: list it.
9. Report
End with what shipped: commits, version, PR link, workflow run results, release / package / deploy links, and anything still pending (release PR waiting, review pending, failed checks).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

