From ship
Defines a /code workflow with quality gates (tests, lint, types, coverage, test quality) and review gates for RGRC cycles. Useful for enforcing code quality standards.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ship:use-workflow-codeWhen to use
/code ワークフロー, quality gates, 品質ゲート, RGRC サイクル
This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Command | Workflow Reference |
| Command | Workflow Reference |
|---|---|
/code | ${CLAUDE_SKILL_DIR}/references/code-workflow.md |
| Pattern | Reference |
|---|---|
| TDD | ${CLAUDE_SKILL_DIR}/../use-workflow-tdd-cycle/SKILL.md |
| Gate | Target | Verification |
|---|---|---|
| Tests | All passing | npm test exit code 0 |
| Lint | 0 errors | npm run lint exit code 0 |
| Types | No errors | tsc --noEmit exit code 0 |
| Coverage | C0 ≥90%, C1 ≥80% | Coverage report |
| Test Quality | per-metric thresholds | evaluator-test (skip if no Spec) |
When a Spec with Test Scenarios exists, spawn evaluator-test as a background agent using this invocation.
Agent(subagent_type: "evaluator-test",
prompt: "spec_path: <path>\ntest_paths: <paths>",
run_in_background: true)
Pass when all 5 metrics meet thresholds. On any fail, report findings (uncovered T-NNN, excess tests, duplicates, granularity issues, intent issues) and fix before proceeding. Skip when no Spec exists (e.g., /fix, ad-hoc changes).
| Metric | Threshold |
|---|---|
| coverage | ≥0.8 |
| excess | ≤0.1 |
| duplication | ≤0.2 |
| granularity | ≥0.7 |
| intent | ≥0.7 |
After RGRC cycles, spawn reviewer-readability as a background agent:
Agent(subagent_type: "reviewer-readability",
prompt: "Review files changed in this session: <paths>",
run_in_background: true)
High severity → fix before Quality Gates. Medium/low → advisory.
Skip for /fix and single-file changes.
Tests: pass | fail (detail)
Lint: pass | fail (detail)
Types: pass | fail (detail)
Coverage: C0 XX% / C1 XX% - pass | fail
Test Quality: cov=X.X exc=X.X dup=X.X gran=X.X int=X.X | pass | fail | skip (no Spec)
All 5 lines required. Empty lines indicate a skipped gate - investigate before proceeding.
| Excuse | Counter |
|---|---|
| "Tests pass, lint can wait" | Lint errors are tech debt. Zero errors before commit |
| "Type errors are just warnings" | tsc --noEmit exit 0 or no ship. Type warnings are errors |
| "Coverage is close enough" | "Close enough" is failure with extra steps. Meet the threshold |
| "This gate doesn't apply to this change" | All 4 gates apply to every change. No exceptions |
npx claudepluginhub thkt/dotclaude --plugin toolkitProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.