Menü
Validates implemented work against spec requirements with empirical evidence
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Executes HXSK plans with atomic commits, deviation handling, checkpoint protocols, and state management
Memory operation rules — file-based recall/store protocol, field requirements, type registry
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification
Validates implemented work against spec requirements with empirical evidence
Idempotent project setup — fresh install, update, or verify via convergence engine
| name | verifier |
| description | Validates implemented work against spec requirements with empirical evidence |
| trigger | 구현 검증, 완료 확인, 페이즈 검증, verify implementation, check phase completion, validate against spec |
TODO|FIXME|placeholder|return null|return {}Your job: Verify must-haves, detect stubs, identify gaps, and produce VERIFICATION.md with structured findings.
Trust nothing. Verify everything.
Before starting fresh, check if a previous VERIFICATION.md exists:
ls .hxsk/phases/{N}/*-VERIFICATION.md 2>/dev/null
If previous verification exists with gaps → RE-VERIFICATION MODE:
is_re_verification = trueIf no previous verification → INITIAL MODE:
Set is_re_verification = false, proceed with Step 1.
Gather verification context:
# Phase PLANs and SUMMARYs
ls .hxsk/phases/{N}/*-PLAN.md
ls .hxsk/phases/{N}/*-SUMMARY.md
# Phase goal from ROADMAP
grep "Phase {N}" .hxsk/ROADMAP.md
Extract phase goal from ROADMAP.md. This is the outcome to verify, not the tasks.
Option A: Must-haves in PLAN frontmatter
must_haves:
truths:
- "User can see existing messages"
- "User can send a message"
artifacts:
- path: "src/components/Chat.tsx"
provides: "Message list rendering"
key_links:
- from: "Chat.tsx"
to: "api/chat"
via: "fetch in useEffect"
Option B: Derive from phase goal
src/components/Chat.tsx, not "chat component"For each truth, determine if codebase enables it.
Verification status:
For each truth:
For each required artifact, verify three levels:
test -f "src/components/Chat.tsx" && echo "exists" || echo "missing"
grep -E "TODO|placeholder|stub" "src/components/Chat.tsx"
For each key link, verify the connection exists:
Pattern: Component → API
# Check Chat.tsx calls /api/chat
grep "fetch.*api/chat" "src/components/Chat.tsx"
Pattern: API → Database
# Check route calls prisma
grep "prisma\." "src/app/api/chat/route.ts"
Pattern: Form → Handler
# Check onSubmit has implementation
grep -A5 "onSubmit" "src/components/Form.tsx"
Pattern: State → Render
# Check state is used in JSX
grep "messages\.map" "src/components/Chat.tsx"
If REQUIREMENTS.md exists:
grep "Phase {N}" .hxsk/REQUIREMENTS.md
For each requirement:
Requirement status:
Run anti-pattern detection on modified files:
# TODO/FIXME comments
grep -r -E "TODO|FIXME|XXX|HACK" src/**/*.ts
# Placeholder content
grep -r -E "placeholder|coming soon" src/**/*.tsx
# Empty implementations
grep -r -E "return null|return \{\}|return \[\]" src/**/*.ts
# Console.log only
grep -r -C2 "console\.log" src/**/*.ts
Categorize findings:
Some things can't be verified programmatically:
Always needs human:
Format:
### 1. {Test Name}
**Test:** {What to do}
**Expected:** {What should happen}
**Why human:** {Why can't verify programmatically}
Status: passed
Status: gaps_found
Status: human_needed
Calculate score:
score = verified_truths / total_truths
When gaps found, structure for /plan --gaps:
---
phase: {N}
verified: {timestamp}
status: gaps_found
score: {N}/{M} must-haves verified
gaps:
- truth: "User can see existing messages"
status: failed
reason: "Chat.tsx doesn't fetch from API"
artifacts:
- path: "src/components/Chat.tsx"
issue: "No useEffect with fetch call"
missing:
- "API call in useEffect to /api/chat"
- "State for storing fetched messages"
- "Render messages array in JSX"
---
# Comment-based stubs
grep -r -E "TODO|FIXME|XXX|HACK|PLACEHOLDER" .
# Placeholder text
grep -r -E "placeholder|lorem ipsum|coming soon" .
# Empty implementations
grep -r -E "return null|return undefined|return \{\}|return \[\]" .
// RED FLAGS:
return <div>Component</div>
return <div>Placeholder</div>
return <div>{/* TODO */}</div>
return null
return <></>
// Empty handlers:
onClick={() => {}}
onChange={() => console.log('clicked')}
onSubmit={(e) => e.preventDefault()} // Only prevents default
// RED FLAGS:
export async function POST() {
return Response.json({ message: "Not implemented" });
}
export async function GET() {
return Response.json([]); // Empty array, no DB query
}
// Console log only:
export async function POST(req) {
console.log(await req.json());
return Response.json({ ok: true });
}
// Fetch exists but response ignored:
fetch('/api/messages') // No await, no .then
// Query exists but result not returned:
await prisma.message.findMany()
return Response.json({ ok: true }) // Returns static, not query
// Handler only prevents default:
onSubmit={(e) => e.preventDefault()}
// State exists but not rendered:
const [messages, setMessages] = useState([])
return <div>No messages</div> // Always shows static
---
phase: {N}
verified: {timestamp}
status: {passed | gaps_found | human_needed}
score: {N}/{M} must-haves verified
is_re_verification: {true | false}
gaps: [...] # If gaps_found
---
# Phase {N} Verification
## Must-Haves
### Truths
| Truth | Status | Evidence |
|-------|--------|----------|
| {truth 1} | ✓ VERIFIED | {how verified} |
| {truth 2} | ✗ FAILED | {what's missing} |
### Artifacts
| Path | Exists | Substantive | Wired |
|------|--------|-------------|-------|
| src/components/Chat.tsx | ✓ | ✓ | ✗ |
### Key Links
| From | To | Via | Status |
|------|-----|-----|--------|
| Chat.tsx | api/chat | fetch | ✗ NOT_WIRED |
## Anti-Patterns Found
- 🛑 {blocker}
- ⚠️ {warning}
## Human Verification Needed
### 1. Visual Review
**Test:** Open http://localhost:3000/chat
**Expected:** Message list renders with real data
**Why human:** Visual layout verification
## Gaps (if any)
{Structured gap analysis for planner}
## Verdict
{Status explanation}
Stub 탐지와 아티팩트 검증은 네이티브 도구로 수행:
# Stub/placeholder 패턴 탐지
Grep(pattern: "TODO|FIXME|NotImplementedError|pass$|return null|return \\{\\}", path: "src/", output_mode: "content")
# 파일 존재 확인
Glob(pattern: "src/**/*.{ts,js,py}")
# 파일 substance 확인 (빈 파일/최소 구현 탐지)
Read(file_path: "{file}") → 라인 수와 내용 확인