ship
Skill1 starsChanged 12 days agoMITView on GitHub
Use when the user wants to ship ONE branch of ONE repo right now — "/ship", "ship this worktree", "ship the branch I am on". Infers the worktree and branch from the current session (AskUserQuestion only when sitting on the default branch with unmerged branches, or outside any repo), derives the version and release title, then runs that repo''s bin/rtc-ship.sh end to end — gates, merge to the default branch, tag, release, refresh of the plugin, dogfood — and relays every phase verdict. For a whole queue unattended use autopilot; for editing a repo''s rtc-ship.json use ship-config.
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
- 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
- caidanw/skillstheir 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 repository8 other files it gives its agents.
- autopilotSkill
- close-out-the-runSkill
- execute-unattendedSkill
- run-to-completionSkill
- ship-configSkill
- triage-for-autonomySkill
- ungate-queueSkill
- writing-execution-plansSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
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 21
Not inside any repo at all → AskUserQuestion for the repo path (header "Repo", free-text Other), then pick the worktree from git -C <path> …
- Very specific: line 25
Version and title — derived, not asked: Read the target repo's declared manifest (rtc-ship.json manifest, default …
- Distinctive: line 52
Never force-push; a published tag that is wrong moves only with the user's explicit approval (delete + recreate), otherwise fix forward in …
- Distinctive: line 54
Ask the depth question every time — an earlier "you may push" does not cover merge, tag or release.
- Distinctive: line 67
When you begin working under this skill, lead your first substantive reply with "🏃 ship:" so the user can see which plugin just became …
“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 — one branch, one repo, shipped all the way out
rtc-ship.sh owns the loop; this skill owns the conversation around it: infer what can
be inferred from the session, ask only what genuinely needs a human, run the loop, relay
the verdicts. It does not re-implement any loop step.
The flow
- Which worktree/branch — inferred first, asked only when ambiguous. Resolve the
session's own location:
git rev-parse --show-toplevelandgit branch --show-current.- Inside a repo on a NON-default branch → that worktree and branch are the ship
target. State them ("shipping
<branch>in<toplevel>") and move on — no question. - Inside a repo ON the default branch → list the unmerged branches
(
git branch --no-merged <default>plusgit worktree list) and AskUserQuestion which one to ship (header "Branch", option labels<branch> — <worktree path>). - Not inside any repo at all → AskUserQuestion for the repo path (header "Repo",
free-text Other), then pick the worktree from
git -C <path> worktree list. The default branch is resolved, never assumed (bin/rtc-ship.sh --which-config), and a worktree is the only safe ship target — never the canonical checkout.
- Inside a repo on a NON-default branch → that worktree and branch are the ship
target. State them ("shipping
- Version and title — derived, not asked. Read the target repo's declared manifest
(rtc-ship.json
manifest, default.claude-plugin/plugin.json) and its top CHANGELOG entry: version =X.Y.(Z+1); title = the CHANGELOG entry's text after the date, else the first line ofgit log <default>..HEAD. Print both. AskUserQuestion only when the derivation is genuinely ambiguous (header "Version/title", first option "use the derived<version>/<title>"). - How far may it go — always asked once. AskUserQuestion, header "Depth", with the full loop as the
first option: gates → merge to the default branch → tag → release → refresh → dogfood.
Other options: "through the merge only" and "gates only (
--test-only)". A ship that stops short of the default branch is not yet obtainable by installers — say so when the user picks a shorter depth. - Run it. From the target repo's root:
bash bin/rtc-ship.sh <worktree-dir> <version> "<title>"(append--no-reaponly if the user asks to keep the worktree). Stream the phase output to the user as it goes. On a non-zero exit, report the failing phase and the tail the script already printed, and STOP — do not retry blindly; say what has to be fixed first (a red gate, a dirty canonical checkout, a version-surface split). - Inspection modes first, when asked:
--which-config(what the repo resolves today),--versions-only/--check-versions(the gate alone, writes nothing),--bump-versions <dir> <version>(rewrite only the declared surfaces). Offer these as a first AskUserQuestion choice when the user says "check" rather than "ship".
Rules that still apply
- The canonical checkout must be clean on the default branch when the config sets
require_default_branch_checkout— back up any foreign dirt byte-identically, never discard it. - Never force-push; a published tag that is wrong moves only with the user's explicit approval (delete + recreate), otherwise fix forward in the next version.
- Ask the depth question every time — an earlier "you may push" does not cover merge, tag or release.
When NOT to use
- A whole standing queue to clear unattended — that is
autopilot. - Editing or inspecting a repo's
rtc-ship.json— that isship-config. - A repo with no
bin/rtc-ship.sh— say so and stop; do not improvise a loop by hand. - The user only wants to read state (no ship intended) — use the inspection modes in step 5 and stop there.
Branding (🏃)
When you begin working under this skill, lead your first substantive reply with "🏃 ship:" so the user can see which plugin just became active.
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.

