소스 정보
- 저장소
- InugamiDev/ultrathink-oss
- 최근 소스 활동
- 2026년 3월 28일 09:40
- 감지된 SKILL.md 언어
- 영어
- 스타
- 43
- 포크
- 10
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/InugamiDev/ultrathink-oss --skill verify명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | verify |
| description | Full pre-PR verification pipeline — build, typecheck, lint, test, secrets, git status |
| layer | utility |
| category | quality |
| triggers | ["verify","verification","ready for pr","pre-pr check","is it ready","check everything","run all checks"] |
| inputs | [{"mode":"quick | full (default) | pre-commit | pre-pr"},{"path":"Project root or specific directory"}] |
| outputs | [{"report":"Structured pass/fail per check"},{"verdict":"Ready for PR: YES | NO"}] |
| linksTo | ["quality-gate","test","code-review","security-scanner","build-resolver"] |
| linkedFrom | ["cook","ship","plan-validate"] |
| preferredNextSkills | ["pr-writer","code-review"] |
| fallbackSkills | ["quality-gate","fix"] |
| riskLevel | low |
| memoryReadPolicy | none |
| memoryWritePolicy | selective |
| sideEffects | ["Runs test suite (may create test artifacts)"] |
Run a comprehensive verification pipeline to determine if code is ready for PR or deployment. Unlike quality-gate (which checks changed files), verify checks the entire project state.
Use this when:
Checks run in order. Each produces a PASS/FAIL/SKIP status:
| # | Check | Command | Blocks PR |
|---|---|---|---|
| 1 | Build | npm run build / next build | YES |
| 2 | Typecheck | tsc --noEmit | YES |
| 3 | Lint | biome lint / eslint . | On errors |
| 4 | Tests | vitest run / jest / pytest | YES |
| 5 | Console.log | grep -rn in src/ | WARNING |
| 6 | Secrets | Pattern grep | YES |
| 7 | Git Status | git status / git diff --stat | INFO |
| Mode | Checks | Use When |
|---|---|---|
| quick | Typecheck + Lint | Mid-development sanity check |
| full | All 7 checks | Default, before PR |
| pre-commit | Format + Type + Lint + Secrets | Git pre-commit hook |
| pre-pr | All 7 + coverage threshold + branch check | Final PR readiness |
In pre-pr mode, also verify:
git merge-base --is-ancestor)# Detect project type and available tools
[[ -f package.json ]] && PROJECT_TYPE="node"
[[ -f pyproject.toml ]] && PROJECT_TYPE="python"
[[ -f go.mod ]] && PROJECT_TYPE="go"
[[ -f Cargo.toml ]] && PROJECT_TYPE="rust"
# Detect available runners
[[ -f biome.json ]] && LINTER="biome"
[[ -f .eslintrc* ]] && LINTER="eslint"
command -v vitest && TEST_RUNNER="vitest"
command -v jest && TEST_RUNNER="jest"
command -v pytest && TEST_RUNNER="pytest"
Run each check, capture output, determine status:
# 1. Build
BUILD_OUT=$(npm run build 2>&1)
BUILD_STATUS=$?
# 2. Typecheck
TSC_OUT=$(npx tsc --noEmit 2>&1)
TSC_STATUS=$?
# 3. Lint
LINT_OUT=$(npx biome lint ./src 2>&1)
LINT_STATUS=$?
# 4. Tests
TEST_OUT=$(npx vitest run --reporter=verbose 2>&1)
TEST_STATUS=$?
# 5. Console.log
LOG_OUT=$(grep -rn 'console\.log' src/ --include='*.ts' --include='*.tsx' \
| grep -v '\.test\.' | grep -v '\.spec\.' | grep -v 'node_modules')
# 6. Secrets
SECRET_PATTERNS='(sk-[a-zA-Z0-9]{20,}|AKIA[A-Z0-9]{16}|ghp_[a-zA-Z0-9]{36}|password\s*=\s*["\x27][^"\x27]+)'
SECRET_OUT=$(grep -rn -E "$SECRET_PATTERNS" src/ --include='*.ts' --include='*.tsx' \
| grep -v '\.test\.' | grep -v '\.env\.example')
# 7. Git Status
GIT_OUT=$(git status --porcelain)
GIT_DIFF=$(git diff --stat HEAD)
VERIFICATION: [PASS|FAIL]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Build ✅ Success (12.3s)
Typecheck ✅ Clean
Lint ⚠️ 3 warnings
Tests ✅ 47/47 passed (94% coverage)
Logs ⚠️ 2 console.log found
Secrets ✅ Clean
Git 📋 3 files changed, 1 untracked
Ready for PR: YES (with minor warnings)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
For each failing check, output:
| Pitfall | Impact | Fix |
|---|---|---|
| Running full build every time | Slow feedback loop | Use quick mode for typecheck-only |
| Ignoring lint warnings | Accumulate technical debt | Address warnings or configure rules |
| Not checking git status | Commit unintended files | Always review what's staged |
| Skipping test step | Ship broken functionality | Tests are non-negotiable in full mode |
| Secret false positives fatigue | Real secrets slip through | Refine patterns, add allowlists |
| Not checking branch freshness | Merge conflicts after PR | In pre-pr mode, check merge-base |
> /verify --quick
VERIFICATION: PASS
Typecheck ✅ Clean
Lint ✅ Clean
Ready: YES (quick mode — run full before PR)
> /verify
VERIFICATION: FAIL
Build ❌ Failed (exit code 1)
Error: src/app/page.tsx: Cannot find module './components/Header'
Typecheck ❌ 3 errors
src/lib/auth.ts(12,5): TS2322 Type 'null' not assignable to 'User'
src/api/route.ts(8,1): TS2305 Module has no exported member 'handler'
src/api/route.ts(15,3): TS2345 Argument type mismatch
Lint SKIP (blocked by build failure)
Tests SKIP (blocked by build failure)
Logs ✅ Clean
Secrets ✅ Clean
Git 📋 5 files changed
Ready for PR: NO
Recommendation: Run build-resolver to fix 3 type errors, then re-verify
Verify integrates with the skill mesh:
verify FAIL → build-resolver (fix types) → verify PASS → pr-writer (create PR)
verify FAIL → fix (complex logic errors) → test (add missing tests) → verify PASS
cook → implement → verify → code-review → ship
Unified design foundations — design system architecture, tokens, component specs, visual principles, creative vision, figma integration, plus brand design system loader (66 real brands via DESIGN.md). Absorbs design, design-system, design-systems, design-principles, design-router, creative-vision, figma, design-md.
Render, summarize, and present markdown documents and structured content in multiple output modes
Ultra UI skill - combines Google's DESIGN.md spec (machine-readable design tokens) with the ui-ux-pro-max knowledge base (91 styles, 161 palettes, 73 font pairings, 161 products, 104 UX guidelines, 25 chart types). Generates lint-clean DESIGN.md files, validates token references and WCAG contrast, exports Tailwind/DTCG tokens, and diffs design systems version-over-version.
SOC 직업 분류 기준
