ship
Skill7 starsChanged 11 days agoMITView on GitHub
Ship a finished change: archive, save, pass CI or review, check the preview, squash-merge; runs /apply first if unfinished.
- Deletes or force-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.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-browserSkill
- applySkill
- browserSkill
- closeSkill
- connectSkill
- continueSkill
- dailySkill
- dream-memorySkill
- exploreSkill
- hand-overSkill
- improve-codeSkill
- lessonSkill
- memorySkill
- paste-this-into-your-aiSkill
- planSkill
- saveSkill
- scheduleSkill
- servicesSkill
- shopSkill
- update-dependenciesSkill
- verifySkill
- wong-setupSkill
- wong-syncSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
0
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 25
Check preconditions, then run prepare.
“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
Invoking /ship authorizes every step below unprompted: archive, checkpoint, walk, merge, remote-branch deletion, sync, the pull-in with any save a task needs, and safe picks. Confirm anything else (a force push, --no-verify, git reset --hard, checkout .) in the shared ask format.
The change loop owns the record, the pull-in, and the gate. main means the default branch.
Each command ends with a NEXT: line; follow it:
SHIP="$(git rev-parse --show-toplevel)/.claude/skills/ship/scripts/ship.mjs"
node "$SHIP" prepare --change "$CHANGE_NAME"
node "$SHIP" finishStep 1 — preflight
Attached review notes → apply them to the existing change first, then keep publishing.
Check preconditions, then run prepare. Uncommitted changes on the default branch go on in the same tree; Step 3's save cuts the feature branch.
The pull-in: nothing to ship yet
Invoke the apply skill, saying it runs inside /ship, then go to Step 2 in the same tree.
/ship <intent>→ pass the intent verbatim.- No argument → invoke
/applybare when its resolve order lands beforesole-active, or the session states clear intent with no change yet. - The cold stop. Landing on
sole-activeor nothing → say there is nothing to continue and/ship <intent>starts a new change, then stop: a cold/shipnever publishes the only open plan.
/plan pauses, tasks stay pending, or a task-driven /save fails or is unverifiable → report the blocker and stop before Step 2: no verb merges to stop.
Work that changes no repo file finishes in /apply: say so in one line and stop; no git change.
Step 2 — archive the change
Run node .claude/skills/explore/scripts/step-title.mjs set SHIP --task "<plan title>", again after each apply until finish merges, then set DONE. CHANGE_NAME is separate from BRANCH. Pass --change for a change the person or this chat named; without it prepare picks by the rungs. None selects → follow NEXT:; a new change comes from the new-plan fallback.
prepare archives by the CLI contract, which owns --skip-specs, after two stops:
- Other changes the branch adds → rerun with
--move-others;--allow-othersonly if the person asked to ship all. - Unchecked tasks → invoke
applyfor that change inside/ship, then rerun; still pending → report and stop.
Step 3 — delegate the checkpoint to /save
prepare numbers the ## Next changelog entry, merging main first when behind, then reruns the local checks: allow 15 minutes. NEXT: carries any repair.
Invoke the save skill once (plus one after Step 4's fix) as ordinary /save inside /ship and follow it verbatim, with prepare's CHANGE and ARCHIVE if any. Proceed only on SUCCESS or NONE. Any other result → stop before merge and report /save's reason; never repeat, bypass, or reinterpret the gate.
Step 4 — verify the preview (evidence, not a gate)
Invoke verify once with Step 3's exact checkpoint receipt, plus one with the fix's receipt, never for a better verdict. No verify skill → say so in one line and go on; never install it.
Any verdict but FAILURE → report it and merge. FAILURE after /verify's own fixes → one fix: apply inside /ship with ARCHIVE and the failures, then /save as in Step 3, and verify. Still FAILURE, or the fix must stop → say what fails and ask: fix more (Recommended), or publish anyway, recorded. If the walk's fixes, or its one /save of kept checks, advanced HEAD, merge that commit only when that /save returns SUCCESS or NONE.
Step 5 — merge and sync
Run finish once; allow 12 minutes. It merges the gated commit, promotes deferred secret edits, closes the plan's Inbox page, and looks at the live app. A skipped sync, a secrets error, or PLAN_PAGE=skipped is one report line, never a failed ship. Not merged → report the error and stop, unless NEXT: gives a recovery; then finish again only on SUCCESS or NONE.
Merge, not rebase, unless asked. Never check out, switch, stash, reset, or force a branch to make the sync succeed, or delete a local branch.
Look at the live app
LIVE_LOOK=ok/unknown → REASON as one report line. failed → say what fails, then invoke apply once with REASON and URL as the request; it ends at its preview and publish it?. No retry or revert.
Step 6 — report
Lead with the outcome in plain words: it is live, what changed for the person, the live link, then the plan's link to the archived review.html. Always add Checks loosened, each Check: bullet in the archived Decision log, and Choices I made, each Assumed line this ship added and each MOVED= plan, one plain line each; omit when none. Only when asked, add finish's and /save's lines, the archive path, the walk's verdict and evidence (a merged-anyway FAILURE says the person chose it), and the secret key names.
Then end by next work. A failed live look, or a /ship that /close invoked, does not close.
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.

