메뉴
The pre-deploy gate. Triggers on "deploy", "ship it", "release", "cut a release", "push to prod", "roll it out", or editing a CI or deploy config. Produces a deploy brief with five required slots and a tagged release — or it refuses to call the deploy ready.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Restructure frontend code so it's testable, predictable, and correctly layered — without changing behavior. Pull pure logic out of framework glue, fix reactivity anti-patterns (derived state synced by a watcher/effect, logic in the view, effects with no cleanup, unstable list keys), name and place extractions right (util vs helper vs colocated), and keep the base ← common ← feature dependency one-way. Triggers on "refactor this component", "logic in the template/JSX", "this is hard to test", "watch/useEffect misused", "component does too much", "where does this helper go". Vue & React.
Find and fix hardcoded design values that bypass the design system — raw hex/rgb/hsl colors, arbitrary Tailwind classes like `bg-[#1f2432]`, inline-style colors, and magic spacing/radius/shadow — and route each through a token. Triggers on "remove hardcoded colors", "use our design tokens", "enforce the design system", "why isn't dark mode working here", or a linter flagging arbitrary values. Complements `fe-design-system` (which defines the tokens); this enforces their use.
Test frontend UI code the way it should be tested — risk-scored per file (P0–P3), behavior-not-implementation, boundary-only mocking, and the minimum valuable set. Covers components, composables/hooks, stores, forms, and SSR/hydration safety using the project's own runner (Vitest/Jest + Testing Library / Vue Test Utils, Playwright for E2E). Triggers on "test this component/page", "frontend/Vue/React/Nuxt tests", "component/composable/store tests", "why is this test flaky", "should this be an E2E?". Not for non-UI logic (use test-code) or outside-in black-box QA (use test-blackbox).
Capture the *why* after a change — the non-obvious knowledge a future developer or agent can't recover by reading the code: hidden constraints, business rules, rejected alternatives, edge-case guards, invisible API contracts, and what silently breaks if the code changes. Triggers on "document this", "write docs for what we built", "capture why this exists", "document the constraints/decisions", "preserve this for future devs" — after a feature, refactor, or bug fix. NOT for README, API docs, code comments, or CHANGELOG — only the knowledge the code can't tell you.
The SKULL leader/conductor. Triggers on "skull", "set up skull", "mc setup", "onboard me", "build my team", "what's new", or when starting work in a new/unfamiliar project. It interviews you (grill-me), maps the project, then assembles a tailored team from the installed skills and agents — Sentinel the project cartographer plus planning, review, understanding, guardrail and security specialists — and runs it on your work. It builds the best `.claude/` workspace per project, delegates to parallel subagents (choosing the right model per agent), brainstorms hard and decides fast, keeps a complete view of every installed capability, keeps itself and you current with the newest Claude Code features, and proactively offers the right tool the moment a need shows up.
Drive a full QA pass on any project as a SKULL-led tester team — user-end, black-box, code, and stress/load — then emit a charted skull.html status dashboard. Triggers on "test everything", "QA this", "full test pass", "is it ready to ship", "pre-release check", "the app has no tests", "test this app end to end". Not for a single unit test (use cap-tdd) or a security audit (use wf-security-audit).
| name | ops-ship |
| description | The pre-deploy gate. Triggers on "deploy", "ship it", "release", "cut a release", "push to prod", "roll it out", or editing a CI or deploy config. Produces a deploy brief with five required slots and a tagged release — or it refuses to call the deploy ready. |
| allowed-tools | Read, Grep, Glob, Bash, Write, Edit |
A deploy is a change to a running system other people depend on. The gate is not "be careful" — it's a deploy brief whose five slots are structurally required. An empty slot means the brief is INCOMPLETE and the deploy is not ready. Not "proceed with caution" — not ready.
First, confirm where this is going: read .skull/env (run ops-env-map if it's stale). If the target is
production, you assemble the brief for a human to execute — you do not run the deploy yourself.
| # | Slot | What fills it — and what an empty slot means |
|---|---|---|
| 1 | Verify evidence | The command you ran and its actual output: tests, build, typecheck, lint green. No output = unverified = not ready. |
| 2 | Migration dry-run result | The migration run against a copy, with its output — or the literal words "no schema change". Never blank. |
| 3 | Rollback plan | The exact revert commands and the direction you tested. "We'd figure it out" is not a plan (see ops-rollback). |
| 4 | Blast radius | Who and what breaks if this is wrong — which users, which services, which data. Name them. |
| 5 | Flag / canary strategy | Behind a flag, or canaried to N% with a rollback trigger — or one sentence on why neither fits. |
Write the brief to .skull/deploy-<date>.md. A reviewer should green-light it without re-deriving any slot.
git tag -a v1.4.2 -m "release notes" && git push origin v1.4.2
The tag is what ops-rollback redeploys and what ops-incident points at. An untagged deploy is one you
can't cleanly name later — which means one you can't cleanly revert.
A slot filled with "should be fine" / "N/A" where a real answer belongs · "we'll test in prod" · a rollback plan nobody has ever run · a migration that only goes forward · deploying Friday afternoon with no one watching the graphs. Each is an incomplete brief wearing a checkmark.
Pairs with ops-env-map (prove the target first) and ops-rollback (the plan slot 3 demands). Credits:
change-management and canary / progressive-delivery discipline from standard SRE practice.