ship
Skill1 starsChanged 15 days agoApache-2.0View on GitHub
Verify a change, then deliver it by opening a pull request and watching its CI pass, or by pushing straight to main when the repository says so. Use it whenever the user says ship it, send it, open a PR, push to main, deploy, or release, or asks to get finished work delivered, even if they do not name a mode.
- Commits and pushes
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 repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-chatSkill
- argocdSkill
- code-reviewSkill
- commitSkill
- dependency-trackSkill
- financeSkill
- handoffSkill
- java-21-to-25-migrationSkill
- jenkinsSkill
- jiraSkill
- perplexitySkill
- pr-readySkill
- researchSkill
- skanetrafikenSkill
- sonarqubeSkill
- tddSkill
- to-tasksSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Run the verify skill on the candidate revision.
- Distinctive: line 56
If the push is rejected, fetch and reconcile.
- Distinctive: line 64
If the repository deploys on push, confirm the deployed version serves the new behavior with a read-only check before calling it shipped.
“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
Deliver verified work. Nothing should reach the base branch or production on unverified
evidence, so verification comes first and delivery second. The mode is a pull request unless
the repository says to push straight to main; look in AGENTS.md, the README, and whether
pull requests are enabled on the remote. If they are silent, use a pull request.
End with SHIPPED or one concrete blocker. Invoking this skill authorizes the delivery below
and nothing else. It never merges a pull request.
1. Scope
git status --porcelain and git diff --stat. Identify the files this task changed; leave
everything else alone and never stage with -A, ., or -u. Follow the commit skill for
staging and the message. Work in an isolated worktree when other sessions may be active.
Fetch and rebase onto the current base (origin/main) so the evidence is about what will
land. Force-pushing can destroy remote work, so do it only with explicit approval.
2. Verify
Run the verify skill on the candidate revision. Deliver only on PASS. FAIL and BLOCKED both stop here: fix the cause or report
the blocker, never weaken a check to get PASS. Any later commit or rebase needs the
affected checks rerun.
3. Deliver
The staged diff holds only this task's files, with no secrets and no machine or account data. Re-fetch; if the base moved, rebase and rerun step 2 for what changed.
Pull request mode (default)
Push the branch with upstream tracking and open a non-draft pull request with an explicit title and body: why the change exists, the verification result and how to reproduce it, and remaining risks. Then watch the checks for the head SHA until each is terminal:
gh pr checks <number> --watchOn every poll confirm the head SHA has not changed. Address review comments that are valid and reply with evidence to those that are not. Stop at a green, mergeable pull request and report it; the merge is the user's.
Direct mode (repository ships to main)
git push origin HEAD:mainIf the push is rejected, fetch and reconcile. Do not overwrite remote work. Then watch the CI and deploy runs for the pushed SHA until each is terminal:
gh run list --commit <sha> --json databaseId,name,status,conclusion
gh run watch <run-id> --exit-statusIf the repository deploys on push, confirm the deployed version serves the new behavior with a read-only check before calling it shipped.
4. When a check fails
Open gh run view <run-id> --log-failed, find the failing command and cause, and whether the
base already fixes it. Reproduce narrowly, fix, verify again, and push once. In direct mode a
failure in production that is not quickly fixable is reverted with a new commit, never a
history rewrite. Do not rerun unchanged failed runs hoping for green unless the log proves an
infrastructure failure, and say so.
Final report
Mode: pull request | direct to main
Delivered: <PR URL or pushed sha>
Verification: <PASS | FAIL | BLOCKED, with the verify result and how to reproduce it>
Checks: <runs for this head and their conclusions>
Not run: <skipped checks and why>
Risk: <what is still unverified>
VERDICT: SHIPPED | BLOCKED <reason>Report SHIPPED only when the checks for the delivered head are green. Never report a step
that was not run in this 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.

