ship
Skill2 starsChanged 5 months agoMITView on GitHub
Final phase — push branch, open PR, wait for CI, merge, deploy. Phase 8 of the eight-phase workflow. Delegates to release agent. Refuses to proceed if any quality gate fails.
- Commits and pushes
194 other projects use a version of this.
Adopted by
Most recently taken up by
- claudialnathan/skillstheir own version, first seen Nov 15, 2026
- saleem-hadad/skillstheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- felipeam86/pipe-skillstheir own version, first seen Nov 15, 2026
- ShipfoxHQ/shipfoxtheir own version, first seen Nov 15, 2026
- nightly-labs/openbottheir own version, first seen Nov 14, 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★ 142ksame name
- rtk-ai/rtk★ 87ksame name
- simstudioai/sim★ 30ksame name
- millionco/react-doctor★ 15ksame name
- nightly-labs/openbot★ 7.9ksame name
- BuilderIO/agent-native★ 7.7ksame name
- fallow-rs/fallow★ 5.3ksame name
- puncsky/system-design-and-architecture★ 3.6ksame name
- plugin87/ux-ui-agent-skills★ 3.2ksame name
- ShenSeanChen/waku-agent★ 2.2ksame 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 repository60 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- animation-disciplineSkill
- api-versioningSkill
- autopilotSkill
- browser-e2eSkill
- characterizeSkill
- clarifySkill
- codemodSkill
- constitution-compactSkill
- constitutionSkill
- context-budgetSkill
- creative-webSkill
- db-migrationSkill
- debugSkill
- detect-stackSkill
- dispatch-criteriaSkill
- dreamSkill
- experimentSkill
- fastapiSkill
- flag-cleanupSkill
- flag-rolloutSkill
- flask-realtimeSkill
- framework-detectorSkill
- front-end-designSkill
- grill-meSkill
- handoffSkill
- image-generationSkill
- implementSkill
- initiativeSkill
- instinctSkill
- loopSkill
- nextjsSkill
- observabilitySkill
- okr-alignSkill
- parallel-swarmSkill
- pivotSkill
- planSkill
- pr-bodySkill
- prime-disciplineSkill
- prod-observabilitySkill
- react-nodeSkill
- react-viteSkill
- release-trainSkill
- researchSkill
- reviewSkill
- security-guardSkill
- self-healSkill
- skill-creatorSkill
- specifySkill
- tailwind-disciplineSkill
- tasksSkill
- tdd-loopSkill
- token-budgetSkill
- typographySkill
- verify-loopSkill
- verifySkill
- wip-checkpointSkill
- <kebab-case-skill-name>Skill
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
- Distinctive: line 96
After ship: "<feature> shipped.
“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.
Files
Ship
Push, PR, CI, merge, deploy. With gates.
Process
- Live-ruleset preflight (e2e-audit ci-gates-2) — the ruleset FILE is inert until applied server-side; without a live ruleset every "required" check is advisory and merge-on-red is possible.
If this fails (no active branch ruleset, or the API is unreadable): REFUSE to merge. Report to the operator with the apply command —live=$(gh api "repos/{owner}/{repo}/rulesets" 2>/dev/null || true) printf '%s' "$live" | jq -e '[.[] | select(.target=="branch" and .enforcement=="active")] | length > 0'gh api repos/{owner}/{repo}/rulesets --method POST --input .github/rulesets/main-protection.json— and stop after step 7 (PR open + CI watch are fine; merge is not).bash .claude/scripts/harness-doctor.shshows the same finding as "live branch ruleset". - Verify the quality bar from
.claude/CLAUDE.md §8. Every box must be checked. - Collect evidence (Round 10 C) —
bash .claude/scripts/collect-evidence.sh <spec-id>. ABORT if it exits non-zero (an AC is unproven or smoke is red). This producesverify/<date>-<feature>/pr-body.md. - Commit the lightweight evidence —
git add verify/<date>-<feature>/{EVIDENCE.md,pr-body.md,evidence.json,results.json,screenshots,traces}(heavy binaries are gitignored + ride as CI artifacts). - Stage and commit any final changes (CHANGELOG, version bump).
4b. Sync + commit living state (M-06 — network boundary, pre-merge on the PR branch). Ship is a network boundary: refresh the STATE.md so the merged branch carries the current answer, and commit it BEFORE the push so it rides the PR (not stranded in a post-merge tree). Grep-gated:
grep -ql 'initiative-state.sh sync' .claude/scripts/initiative-state.sh 2>/dev/null \ && bash .claude/scripts/initiative-state.sh sync || true git add initiatives/active/*.STATE.md .claude/state/current-* 2>/dev/null || true git diff --cached --quiet || git commit -m "chore(state): sync living STATE.md pre-merge (M-06)" - Push the branch (
git push -u origin <branch>). - Use pr-body to compose the complete PR body: include the problem/result summary, spec/plan links, every applicable evidence bundle, actual tests and remaining risks. Save it to a file and open with
gh pr create --body-file <complete-body-file>. Read back the published body before continuing. - Wait for CI (
gh pr checks --watch) —evidence-gateis now a required check; it blocks merge if any AC is unproven. - Merge confirmation — mode-dependent (e2e-audit release-deploy-2):
- Interactive session → ask the user to confirm merge. Their go is the gate.
- Auto mode (Cloud Routine,
--bg, overnight) → do NOT block on a human and do NOT run a baregh pr merge: defer to policy via the wrapper —bash .claude/scripts/autonomous-ship.sh <pr>. It runs the green-gate (arms nativegh pr merge --autoONLY when every required check is green, refuses otherwise), applies theauto-merge-oklabel after its own preflight, and leaves the live ruleset's required checks as the real gate. If checks can't go green, it refuses — stop at "PR open + CI red" and surface it in the morning report; never improvise a merge.
- Squash-merge.
- Interactive:
gh pr merge --auto --squash --delete-branch(after the user's go). - Auto mode:
autonomous-ship.sh(step 8) already armed the squash-merge; do not re-run merge by hand. Once GitHub reports the PR merged, runbash .claude/scripts/reconcile-shipped.shto flip spec/initiative status → shipped and append the merged PR + its proof pointers to the ship-log.
- Interactive:
- Release via release-please (e2e-audit release-deploy-6) — release-please is the
SINGLE tag/changelog authority. Never
git tagorgh release createby hand: after the feature PR merges, release-please opens/updates its release PR from the Conventional Commits; merging the release-please PR is what tags + publishes the CHANGELOG. If no release PR appears, check release-please-config.json for the placeholder package-name (harness-doctor flags it). - Trigger deploy (or watch auto-deploy).
- Update memory with any non-obvious learnings.
Hard rules
- No bypass. Required checks must be green.
- No merge without a live ruleset. "Required" checks only block when a server-side active branch ruleset exists — preflight step 0 is non-negotiable.
- No
--force. Ever, on main/master. - Interactive: user confirms merge. Auto mode: policy confirms merge via
autonomous-ship.sh— the wrapper green-gates + labels + armsgh pr merge --auto; a baregh pr mergein auto mode is forbidden. Green required checks on a LIVE ruleset (step 0) remain the real gate. Auto mode never merges outside that policy. - User confirms deploy. Production always requires explicit go — in auto mode the deploy environment's required reviewers are that gate (merge ≠ deploy).
- ADR check (gap-audit G39/G40). If the diff touches architectural surfaces (migrations, settings, auth, API contracts) and no
.claude/memory/decisions/file is added/updated or cited in the plan's References, STOP and warn loudly — create the missing ADR viaadr-new.shbefore shipping. CI's adr-gate enforces the same rule.
Quality bar (from CLAUDE.md §8)
- Spec approved
- Plan approved
- All tasks complete (each with red→green ledger — Round 10 A)
- Unit tests pass + assertion-density gate clean
- Integration tests pass
- E2E verified — every AC proven via spec-match (Round 10 B)
- Evidence bundle generated (
collect-evidence.shexit 0) and embedded in PR body - Code review approved
- Security review clean
- Lint + typecheck clean
- Docs updated
Output
PR opened: <url>
Checks: <green/red>
Merged: <yes/no>
Tagged: v<version>
Deployed: <yes/no/scheduled>After ship: "<feature> shipped. PR <url>. Tag v<version>. Deploy <status>."
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.

