agentleFS
jocarrdjocarrd/crux-agents/skills/ship/SKILL.md

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

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-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • seek888Skill

    open-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

  • ayudaySkill

    setup-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

  • ShreyRaviSkill

    landing-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

  • zebbernSkill

    debug-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

  • ramybarsoumSkill

    document-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

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
  1. Very specific:

    Run the affected tests (the classifier's tests: line), not the whole suite, before looking at anything.

    line 31
  2. Very specific:

    If the report has artifacts: (screenshots, dumps, stray temporaries in the root), take them out of the stage or add them to .gitignore.

    line 35
  3. Distinctive:

    All of it. Check that it does exactly what was intended.

    line 41
  4. Distinctive:

    Only now: is there a simpler way?

    line 62
  5. Distinctive:

    Stop and say so. It is only changed if whoever decides confirms that behaviour is no longer wanted.

    line 70
  6. Distinctive:

    If the change invalidates any documentation, it is updated in the same turn.

    line 86

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 scope

It 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 touchesGates
Text only (documentation, licences, .gitignore)2, 8, 9
Code not visible from outside1 to 6, 8, 9
Observable surface: UI, API, data, dependencies, integrationall

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 conventions

It 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 touchesWhat to validate
UISee it in the viewports that matter; then /before-after so whoever decides approves it
APICall the affected endpoints, not just their tests
DataThat the migration applies and rolls back
DependenciesThat 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 commit

seal 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

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.