ship
Skill227 starsChanged 50 days agoMITView on GitHub
Take the current branch from working tree to a ready PR that the merge queue merges. Use when the user says "ship" or a loop prompt reaches the PR step.
194 other projects use a version of this.
Adopted by
Most recently taken up by
- claudialnathan/skillstheir own version, first seen Nov 15, 2026
- saleem-hadad/skillstheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- felipeam86/pipe-skillstheir own version, first seen Nov 15, 2026
- ShipfoxHQ/shipfoxtheir own version, first seen Nov 15, 2026
- nightly-labs/openbottheir own version, first seen Nov 14, 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★ 142ksame name
- rtk-ai/rtk★ 87ksame name
- simstudioai/sim★ 30ksame name
- millionco/react-doctor★ 15ksame name
- nightly-labs/openbot★ 7.9ksame name
- BuilderIO/agent-native★ 7.7ksame name
- fallow-rs/fallow★ 5.3ksame name
- puncsky/system-design-and-architecture★ 3.6ksame name
- plugin87/ux-ui-agent-skills★ 3.2ksame name
- ShenSeanChen/waku-agent★ 2.2ksame 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.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- chaosSkill
- google-sync-debugSkill
- qa-test-stagingSkill
- simplifySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 181 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Self-check: Read the complete base-to-head diff as a stranger would: state, races, cleanup, keyboard and focus paths, accessibility, auth, …
- Distinctive: line 45
No label is involved. The required checks are the whole gate: no line-count rail, no path denylist, nothing to look for or wait on.
- Distinctive: line 48
Do not wait for a human on a PR that is green and mergeable.
- Distinctive: line 54
Never close/reopen the PR, push empty commits, or merge main in just to re-run CI (merge main only for a real conflict).
“Common” is measured: kept by at least 6 in 10 of the 181 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
Status lives on the GitHub issue (labels, open PR, closed state). Nothing in the repo records it.
Steps
- Preflight.
git status; work on a branch offorigin/main, never onmain;gh auth status; find any existing PR for the branch. Verify.
bun run verify --strict. Fix failures and rerun, at most two retries.VERDICT: INCOMPLETEmeans Chromium is missing: runbunx playwright install chromiumand rerun. Never weaken a test, widen a timeout, or change test order to get there.The local verdict is evidence; CI is the gate. When
test:web,test:a11y, ortest:e2efails, verify reruns the failing files on the branch and onorigin/mainin a temporary worktree and prints aBaseline against origin/main:block that sorts each failure into NEW (fails only on the branch), PRE-EXISTING (fails on main too), or FLAKY (passed on rerun). Only NEW failures make the verdictFAIL; fix those. Paste the PRE-EXISTING and FLAKY lists into the PR body as-is. A failure verify cannot classify (a crash, an error outside a test) staysFAIL; show why it is environmental in the PR or treat it as real.- Self-check. Read the complete base-to-head diff as a stranger would:
state, races, cleanup, keyboard and focus paths, accessibility, auth,
data loss. If the diff added more than a screen of new abstraction, run
the
simplifyskill. Confirmed problems become isolated fix commits, then rerun step 2. - PR. Open a draft PR against
mainusing.github/PULL_REQUEST_TEMPLATE.md:Fixes #N, what changed and why, the pastedVERDICT:line and checks run. No unchecked manual-testing boxes. Mark it ready once step 2 is satisfied; reviews run on ready PRs only, so a draft that never becomes ready is a stop, not a handoff. Merge. Mark the PR ready and run
gh pr merge --auto.maintakes changes only through the merge queue, so a direct merge is refused by rule; GitHub squash-merges through the queue once required checks pass. No label is involved. The required checks are the whole gate: no line-count rail, no path denylist, nothing to look for or wait on.Do not wait for a human on a PR that is green and mergeable. If the queue drops the PR on a check the diff cannot reach (a runner timeout, a UI test in a surface you did not touch) and the same check passed on the PR head, say so once on the PR and run
gh pr merge --autoagain. A second drop for the same reason is a human call: comment the evidence and stop.Never close/reopen the PR, push empty commits, or merge
mainin just to re-run CI (mergemainonly for a real conflict).
Escalate
Comment on the issue with the decision needed, the recommended option, and
the cost of waiting, then label agent-loop-needs-human. Reasons: product
ambiguity, production deploy, secrets, OAuth grants, deletion, access grants,
verify still failing after two retries.
Anti-patterns
See anti-patterns.md.
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.

