agentleFS
taecontroltaecontrol/skills/skills/engineering/ship/SKILL.md

ship

Skill1 starsChanged 2 months agoMITView on GitHub

Publish finished work as a pull request and drive its CI checks to green. Use when work is ready for review, or when asked to open a PR, make its checks pass, or answer its review.

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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a failure needs something you cannot get, such as a secret, infrastructure access, or a human decision, stop and name it.

    line 24

“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.

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

Ship

A pull request is ready when the human can merge it without asking anything. Green checks in CI, not on this machine, are the bar.

Prepare

The branch holds only durable work: temporary artifacts such as specs, prototypes, and reports stay out of it. When the work came from a spec, check that what must outlive it is in the change, not only in the spec. Bring the branch up to date with its base, and rerun the project's gates when that changed anything.

Open

Push the branch and open the pull request as a draft against its base, with the title and description written by pr-description, whatever the size of the change. It stays a draft: the human marks it ready for review once they have looked at it.

Drive checks to green

Watch every CI check until it finishes. For each failure, find why it fails in CI when it passed locally, such as a different platform, browser, path, timeout, or concurrency, fix the cause, and push again. A check that passes only on a retry is flaky, not green: diagnose it with diagnosing-bugs. Make checks pass by fixing code, tests, or configuration; disabling a check or weakening a test to get green does not count. When a failure is outside the change, show that it fails on the base too, say so in the pull request, and find or open its issue so the next delivery inherits the diagnosis. When a fix changes what the description says, update the description with pr-description.

A review bot that runs on the pull request counts as a check. Before anyone is asked for review, its review of the head is in, and each finding it marks blocking is fixed, or answered on the pull request: with the evidence that refutes it, or as improbable with what happens when it occurs. When the bot reviews only pull requests marked ready, say so in your report: the human marks it ready, waits for the bot, and brings its blocking findings back here before asking a teammate.

When a failure needs something you cannot get, such as a secret, infrastructure access, or a human decision, stop and name it.

Answer a review

A review round adds only what closes its blocking items, whether a person or a review bot raised them. Give each one in a live case the smallest fix that closes it at every site of the same mechanism, and answer an improbable one with its line, as strategic-programming defines both. Choose the fix as refine's Improve section chooses one, with each option the reviewer proposed among the options the second opinion compares. A note the reviewer marked as not blocking, or a change the review did not ask for, stays out unless the human asks for it. Tell the human which notes you left out. Before the human asks for another review, run pr-review again on the new head, close its blocking findings the same way, drive the checks to green again, and bring the description up to date.

Done

Every CI check is green, each blocking finding a review bot left on the head is fixed or answered, or your report names the bot review still to come, the description matches the final state, and the draft pull request is ready to merge once the human marks it ready for review. The human marks it ready and merges.

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.