agentleFS
LucfaceLucface/claude-skills/skills/ship/SKILL.md

ship

Skill1 starsChanged 3 days agoMITView on GitHub

Fix-until-clean loop then commit and push. Use when ready to ship code — runs tests, lint, typecheck, fixes any issues, commits, and pushes.

  • Reads credentials
  • Commits and pushes

195 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, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 7

    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. Distinctive:

    Before running anything, detect what's available:

    line 36
  2. Very specific:

    Only run checks that exist.

    line 46
  3. Distinctive:

    Run all available checks. Max 5 fix iterations (hard stop: same error 3 times).

    line 60
  4. Distinctive:

    Read the error output

    line 63
  5. Distinctive:

    If fixed → continue to next check

    line 67
  6. Distinctive:

    If still failing after 3 attempts on same issue → STOP and report

    line 68
  7. Distinctive:

    If push is rejected (remote has new commits):

    line 94
  8. Very specific:

    Run /sv to save session state

    line 107
  9. Distinctive:

    Update changelog if applicable

    line 108

“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 — Fix Until Clean, Then Push

Automated loop that ensures code is clean before shipping.

When to Use

  • Done coding and ready to commit + push
  • Want to make sure everything passes before pushing
  • Replace manual "run tests, fix, run again" cycle

Arguments

/ship [optional commit message]

Examples:
/ship add user validation endpoint
/ship fix dashboard performance regression
/ship                              # auto-generates commit message from diff

Parse $ARGUMENTS as the commit message. If empty, auto-generate from git diff --staged.

Time Budget

  • Quality checks: 2 min max per suite run
  • Fix loop: 3 min max per fix attempt, 10 min total
  • Hard stop: 15 min total. If not shipped by then → STOP, report status

Step 0: Detect Project Type

Before running anything, detect what's available:

# Check for package.json scripts
# Node/Bun project: use bun test, bun run lint, bun run typecheck
# Python project (pyproject.toml or setup.py): use uv run pytest, uv run ruff check
# Ruby project (Gemfile): use bundle exec rake test, bundle exec rubocop
# If no recognizable project → warn and skip quality checks, just commit

Only run checks that exist. If package.json has no lint script, skip lint. Don't fail on missing scripts.

Step 1: Detect Branch Context

# Check current branch
BRANCH=$(git branch --show-current)

# Branch detection: check your project's CLAUDE.md for branch conventions
# If your project uses a staging/dev branch instead of main, warn before pushing to main

Step 2: Quality Check Loop

Run all available checks. Max 5 fix iterations (hard stop: same error 3 times).

For each failure:

  1. Read the error output
  2. Identify root cause
  3. Fix it (max 2 attempts same approach, then try alternative)
  4. Re-run the failing check
  5. If fixed → continue to next check
  6. If still failing after 3 attempts on same issue → STOP and report

Step 3: Commit + Push

Once all checks pass:

# Stage changes — use specific files, NOT git add -A
# Review what changed with git status first
# NEVER stage .env, credentials, or secrets files
git add [specific files]

# Commit with message (from $ARGUMENTS or auto-generated from diff)
git commit -m "$(cat <<'EOF'
[commit message]

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
EOF
)"

# Push
git push

Step 4: Handle Push Failures

If push is rejected (remote has new commits):

git pull --rebase
# Re-run quality suite (rebase might introduce conflicts)
# If clean → push again
git push
# If merge conflicts → STOP, ask user

Step 5: Post-Ship

After successful push:

  • Run /sv to save session state
  • Update changelog if applicable
  • Report: SUCCESS: Shipped. [N] files changed, all checks passing.

Safety Rails

ConditionAction
5+ fix iterationsSTOP, report remaining issues
Same error 3 timesSTOP, needs different approach
Merge conflictsSTOP, ask for help
No changes to commitSkip, notify user
.env or secrets in diffWARN, exclude from staging
On wrong branch (per project convention)WARN before pushing

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.