agentleFS
librosdeialibrosdeia/builder-method-claude-plugin/skills/ship/SKILL.md

ship

Skill0 starsChanged 5 days agoMITView on GitHub

Phase 6 of the Builder Method — audit security and privacy, save the work, choose a host from the plugin's recipes, deploy, connect the user's domain, and record how to redeploy and roll back in builder/06-ship.md. Use when the product is validated and the user wants to put it online, or runs /builder:ship.

  • Deletes or force-pushes
  • Commits and pushes

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

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    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
  1. Distinctive:

    Goal: check security, save the work, and put the product on the internet with the user's own domain.

    line 8
  2. Very specific:

    If you have no shell tool, say that shipping needs a terminal: open this same folder in Claude Code and run /builder:next.

    line 17
  3. Very specific:

    Never print, log or write secret values (API keys, passwords, tokens), not even in 06-ship.md.

    line 22
  4. Distinctive:

    Never git push --force, and never git reset --hard.

    line 23
  5. Distinctive:

    Ask before anything that publishes or costs money: creating a remote repository, pushing, deploying, adding a domain.

    line 24
  6. Very specific:

    Write the findings in the "Audit" table of 06-ship.md, ordered by priority (critical → low), in plain words, without secret values.

    line 30
  7. Distinctive:

    If the user asked for the audit only, stop after recording it.

    line 35
  8. Very specific:

    Follow the recipe's "Deploy" section.

    line 47
  9. Distinctive:

    If the user has a domain, follow the recipe's "Domain" section.

    line 51

“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

Phase 6 · Ship

Goal: check security, save the work, and put the product on the internet with the user's own domain. Input: the validated product (builder/05-validation.md). Output: a public URL, and builder/06-ship.md.

Read and follow:

  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/tone.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/state-rules.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/gates.md: apply the Ship gate, mentioning any flow not pass, pending decision or debt.

If you have no shell tool, say that shipping needs a terminal: open this same folder in Claude Code and run /builder:next. Then stop.

Set phases.ship.status to in_progress and currentPhase to ship. Create builder/06-ship.md from ${CLAUDE_PLUGIN_ROOT}/skills/ship/templates/06-ship.md (translate the headings to the user's language, but keep "Audit" recognisable, e.g. "Audit / Auditoría").

Safety rules for the whole phase:

  • Never print, log or write secret values (API keys, passwords, tokens), not even in 06-ship.md. Use names only.
  • Never git push --force, and never git reset --hard.
  • Ask before anything that publishes or costs money: creating a remote repository, pushing, deploying, adding a domain. If the user said to proceed without questions, still stop before publishing anything new, unless they explicitly asked you to deploy.

Step 1 · audit

Delegate to the security-auditor subagent (Agent tool, subagent_type: "builder:security-auditor"). Give it the project root and builder/02-prd.md (its "Data & privacy" section says how sensitive the data is). If the subagent tool isn't available, audit yourself following ${CLAUDE_PLUGIN_ROOT}/agents/security-auditor.md.

Write the findings in the "Audit" table of 06-ship.md, ordered by priority (critical → low), in plain words, without secret values.

  • Critical findings are fixed before the remote step and before deploying (one checkpoint commit per fix: builder: fix <short title>).
  • A secret found in the code or in the git history is always critical. A fix commit doesn't remove it from history, so the user must create a new key (rotate it) in that provider and revoke the old one. Put the new key only in environment variables. Don't push anything (the remote step) until the user confirms the old key is revoked.
  • Others need the user's explicit approval to defer (Status: deferred (approved)).

If the user asked for the audit only, stop after recording it.

Step 2 · remote

Offer to keep a copy of the code online. If they agree and use GitHub: gh repo create <name> --private --source . --push. Otherwise give them the steps for their host. Explain in two lines why it matters (a backup, and automatic deploys). The user may skip this step (skipped).

Step 3 · prepare

Read every recipe in ${CLAUDE_PLUGIN_ROOT}/skills/ship/recipes/ (except _template.md), and use their "Fits when" sections to recommend one for this stack and data. Explain the trade-off in two or three lines, and link the pricing page. Don't quote prices. Then follow the chosen recipe's "Prepare" section, and give the user a clear split: what you do in the provider's dashboard and what Claude does.

Step 4 · deploy

Follow the recipe's "Deploy" section. When it's live, open the public URL and smoke-test every flow once. Record it under "Deploy" in 06-ship.md.

Step 5 · domain (optional)

If the user has a domain, follow the recipe's "Domain" section. Give exact DNS records, step by step, for their registrar, and explain that DNS can take a while. Record it.

Step 6 · record

Complete 06-ship.md:

  • the public URL and the domain;
  • environment variable names and what each is for;
  • how to redeploy;
  • how to roll back (from the recipe).

Set review: reviewed, mark the steps and the phase done, and update the progress page.

Close by congratulating the user, briefly. Then say what to do next: share the URL, collect feedback, and run /builder:iterate to start a new improvement cycle.

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.