ship
Skill4 starsChanged 18 days agoMITView on GitHub
Quality gate before committing, graded by what the diff touches: classify the change to know which gates apply, confirm the affected tests are green, read the full diff, review correctness, look for the simplest implementation, run the whole suite, validate in the real environment only if the change touches an observable surface, check whether any documentation has drifted and commit. Use when you finish a piece of work and are about to commit, or when you want a serious review of what you have done so far.
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 repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-repo-to-docsSkill
- adrSkill
- auth-bypass-localSkill
- before-afterSkill
- bug-huntSkill
- carry-envSkill
- code-healthSkill
- crux-doctorSkill
- crux-initSkill
- css-to-componentsSkill
- deploy-fallbackSkill
- deploy-watchSkill
- device-loopSkill
- drive-browserSkill
- e2eSkill
- end-sessionSkill
- eval-fixturesSkill
- explain-planSkill
- flowSkill
- grillSkill
- merge-conflictsSkill
- motion-videoSkill
- oauth-reauthorizeSkill
- prod-signalsSkill
- promote-to-docsSkill
- prose-checkSkill
- read-documentSkill
- render-loopSkill
- repo-mapSkill
- review-prSkill
- root-causeSkill
- runbookSkill
- security-auditSkill
- share-localSkill
- skill-auditSkill
- skill-creatorSkill
- teachSkill
- ui-behaviourSkill
- ui-tellsSkill
- visual-diffSkill
- visual-testSkill
- wizardSkill
- workspaceSkill
- write-testsSkill
- x-postsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
4
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
- Very specific: line 31
Run the affected tests (the classifier's tests: line), not the whole suite, before looking at anything.
- Very specific: line 35
If the report has artifacts: (screenshots, dumps, stray temporaries in the root), take them out of the stage or add them to .gitignore.
- Distinctive: line 41
All of it. Check that it does exactly what was intended.
- Distinctive: line 62
Only now: is there a simpler way?
- Distinctive: line 70
Stop and say so. It is only changed if whoever decides confirms that behaviour is no longer wanted.
- Distinctive: line 86
If the change invalidates any documentation, it is updated in the same turn.
“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
A chain of gates before committing. It stops as soon as one fails. The reason
behind each rule is in <this-skill-directory>/references/why.md; read it
if you doubt one or are about to propose an exception.
0. Which gates are needed
First of all:
crux ship scopeIt says which gates apply, which tests to run in gate 1 and whether the environment has to be brought up. The classifier decides, not your judgement.
| What the diff touches | Gates |
Text only (documentation, licences, .gitignore) | 2, 8, 9 |
| Code not visible from outside | 1 to 6, 8, 9 |
| Observable surface: UI, API, data, dependencies, integration | all |
1. Sanity
Run the affected tests (the classifier's tests: line), not the whole suite,
before looking at anything. If they were already red, it is not your diff: say
so and stop.
If the report has artifacts: (screenshots, dumps, stray temporaries in the
root), take them out of the stage or add them to .gitignore. They are never
committed.
2. Read the diff
All of it. Check that it does exactly what was intended. Stop and ask if there are files that were beside the point, formatting mixed with logic, dead code or debugging leftovers.
3. Correctness
Edge cases, nulls, unhandled errors, inverted conditions, concurrency. If there is an automatic review, it goes here.
4. Conventions
crux ship conventionsIt lists the convention documents that apply and concrete signals (repeated literals, types in constants files, redeclared catalogues). The signals are heuristics; opening the documents it lists is not optional.
5. Quality
Only now: is there a simpler way? Reuse what exists, abstraction at the right level, names that say what they do.
6. Regression
The whole suite, after the fixes from 3 to 5.
A test that already existed and turns red is not edited to make it pass. Stop and say so. It is only changed if whoever decides confirms that behaviour is no longer wanted.
7. Reality, only if gate 0 asks for it
| What the diff touches | What to validate |
| UI | See it in the viewports that matter; then /before-after so whoever decides approves it |
| API | Call the affected endpoints, not just their tests |
| Data | That the migration applies and rolls back |
| Dependencies | That it starts from scratch, not from your cache |
Bring up the environment in the task's workspace.
8. Documentation drift
If the change invalidates any documentation, it is updated in the same turn. The classifier's warning is a signal, not a verdict.
9. Commit
Conventional commit, imperative and lowercase, with a body that explains the why. One type of change per commit.
Leaving a record
The checks run through crux, which records the real result:
crux ship gate # what quality.gate in the contract declares
crux ship run -- <command> # a single check
crux ship seal # after the commitseal refuses if anything is left red and closes the receipt against HEAD.
A long suite goes in the background once the commit is made: work elsewhere
until it reports, and do not touch the tree it is testing.
crux workspace finish does not open the proposal without that receipt.
finish --skip-gate exists only to obey whoever decides, never to save
yourself a step.
.crux-ship goes in the repo's .gitignore.
Before publishing the proposal
crux ship body <file with the body>It looks for the tool's signature and, in client-repo profile, any mention of
our tooling.
Anti-patterns
- Deciding the gates by eye instead of with gate 0.
- Running all nine on a documentation change.
- Starting at 3: without 1 you do not know whether the red is yours.
- Closing 4 without opening the document.
- Simplifying (5) before verifying (3).
- Skipping 6 because the change was small.
- Considering 7 passed without having seen the screen or called the endpoint.
- Committing with a gate red.
Related
/workspace— the isolated environment for gate 7/visual-test— the visual review for gate 7/end-session— closing the session
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.

