@su-record/vibe 3.1.0 → 3.2.1

package/skills/vibe.analyze/references/output-templates.md

@@ -0,0 +1,188 @@
+# Analyze Output Templates — Full Reference
+
+> Loaded by vibe.analyze SKILL.md for the Mode 1–4 output formats, the Mode 1 Next Steps decision tables, the Mode 1 stack directory mapping, and the Mode 2 document-type table.
+
+## Mode 1: Project Structure — Stack Directory Mapping
+
+**Backend:**
+- FastAPI/Django: `app/api/`, `app/services/`, `app/models/`
+- Express/NestJS: `src/controllers/`, `src/services/`, `src/models/`
+
+**Frontend:**
+- React/Next.js: `src/components/`, `src/pages/`, `src/hooks/`
+- Flutter: `lib/screens/`, `lib/services/`, `lib/providers/`
+
+## Mode 1: Scale for Large Projects (6+ related files) — Additional Agent Prompts
+
+```text
+Agent(subagent_type="Explore", model="haiku",
+  prompt="Find all test files related to [FEATURE]. Identify tested vs untested paths.")
+
+Agent(subagent_type="Explore", model="haiku",
+  prompt="Analyze [FEATURE] configuration, environment variables, and external integrations.")
+```
+
+## Mode 1: Feature/Module Analysis — Output
+
+```markdown
+## [feature-name] Analysis Results
+
+### Overview
+- **Feature**: [one-line summary]
+- **Status**: [Complete / In progress / Not implemented]
+- **Files**: N related files
+
+### Structure
+
+#### API Endpoints
+| Method | Path | Description | Auth |
+|--------|------|-------------|------|
+| POST | /api/v1/auth/login | User login | None |
+
+#### Core Services
+- `auth_service.py`: Authentication logic
+  - `login()`: Processes login
+  - `verify_token()`: Validates JWT
+
+#### Data Models
+- `User`: User table
+  - Key fields: id, email, password_hash
+  - Relationships: Session (1:N)
+
+### Reference Files
+- src/api/auth/router.py:L10-50
+- src/services/auth_service.py:L1-100
+```
+
+## Mode 1: Next Steps — Decision Tables
+
+After analysis, suggest mode-specific follow-up actions:
+
+**After code/feature analysis:**
+
+| Task Scope | Approach |
+|------------|----------|
+| Simple fix (1-2 files) | Plan Mode |
+| Complex feature (3+ files) | `/vibe.spec` |
+
+**After document analysis:**
+
+| Goal | Approach |
+|------|----------|
+| Apply findings to project | `/vibe.spec "feature-name"` |
+| Derive improvement direction | Plan Mode |
+| Compare with another source | `/vibe.analyze [other target]` |
+
+**After website analysis:**
+
+| Goal | Approach |
+|------|----------|
+| Build similar product | `/vibe.spec` |
+| Improve existing UI | `/vibe.figma` |
+| Compare with another site | `/vibe.analyze [other URL]` |
+
+## Mode 2: Classify Document Type
+
+| Type | Analysis Focus |
+|------|---------------|
+| Technical spec | API definitions, data models, sequence diagrams |
+| Presentation/slides | Key claims, frameworks, case studies |
+| PRD/requirements | User stories, acceptance criteria, scope |
+| Business document | Strategy, decision points, action items |
+| Research/academic | Methodology, conclusions, applicability |
+
+## Mode 2: Document Analysis — Output
+
+```markdown
+## [Document Name] Analysis
+
+### Overview
+- **Type**: [Presentation / Technical spec / PRD / ...]
+- **Topic**: [one-line summary]
+- **Pages/Sections**: N
+- **Audience**: [Developers / PMs / Executives / ...]
+
+### Key Content
+1. **[Concept 1]**: Description
+2. **[Concept 2]**: Description
+
+### Frameworks/Models (if any)
+- [Systematic structure presented in the document]
+
+### Project Relevance
+| Recommendation | Current State | Gap |
+|----------------|---------------|-----|
+| ... | ... | ... |
+
+### Key Insights
+- [Most important takeaway]
+
+### Suggested Actions
+1. ...
+```
+
+## Mode 3: Website Analysis — Output
+
+```markdown
+## [URL] Analysis
+
+### Overview
+- **Site type**: [SaaS / E-commerce / Portfolio / ...]
+- **Tech stack**: [Next.js, Tailwind, ...]
+- **Overall score**: N/100
+
+### Technical Analysis
+| Area | Detection | Details |
+|------|-----------|---------|
+| Framework | React/Next.js | SSR enabled |
+| CSS | Tailwind CSS | v3.4 |
+
+### UX/UI Analysis
+- **Navigation**: [assessment]
+- **CTA placement**: [assessment]
+- **Responsive design**: [assessment]
+
+### SEO Analysis (N/100)
+| Element | Status | Recommendation |
+|---------|--------|----------------|
+| Title | Present | Appropriate length |
+| Meta Description | Missing | Add description |
+
+### Accessibility (WCAG 2.1 AA)
+- **Semantic HTML**: [assessment]
+- **Keyboard navigation**: [assessment]
+- **Screen reader support**: [assessment]
+
+### Improvement Suggestions
+1. [highest priority]
+2. ...
+```
+
+## Mode 4: Project Quality Analysis — Report
+
+Save to `.vibe/reports/analysis-{date}.md`:
+
+```markdown
+# Project Analysis Report
+
+## Overview
+- Analysis date: YYYY-MM-DD HH:MM
+- Scope: Full / Code / Deps / Arch
+
+## Code Quality (N/100)
+- Average complexity: N (good/warning/critical)
+- High complexity files: N
+
+## Dependencies (N/100)
+- Total packages: N
+- Updates needed: N
+- Security issues: N
+
+## Architecture (N/100)
+- Circular dependencies: N found
+- Layer violations: N
+
+## Improvement Suggestions
+1. ...
+2. ...
+```

package/skills/vibe.analyze/references/quality-gate.md

@@ -0,0 +1,93 @@
+# Analyze Quality Gate — Full Reference
+
+> Loaded by vibe.analyze SKILL.md for the mode-specific weighted checklists, score calculation, depth levels, forbidden-patterns table, and quality thresholds.
+
+### Mode-Specific Checklists
+
+**Code/Feature Analysis:**
+
+| Category | Check Item | Weight |
+|----------|------------|--------|
+| Completeness | All related files identified | 20% |
+| Completeness | All API endpoints documented | 15% |
+| Completeness | All data models mapped | 15% |
+| Accuracy | File paths verified to exist | 10% |
+| Accuracy | Line numbers accurate | 10% |
+| Depth | Business logic explained | 10% |
+| Depth | Dependencies mapped | 10% |
+| Actionability | Next steps clearly defined | 10% |
+
+**Document Analysis:**
+
+| Category | Check Item | Weight |
+|----------|------------|--------|
+| Completeness | Full document read | 20% |
+| Completeness | All key concepts extracted | 20% |
+| Structure | Section structure identified | 15% |
+| Depth | Project relevance analyzed | 15% |
+| Depth | Gap analysis performed | 15% |
+| Actionability | Specific follow-up actions suggested | 15% |
+
+**Website Analysis:**
+
+| Category | Check Item | Weight |
+|----------|------------|--------|
+| Completeness | HTML fetched and parsed | 15% |
+| Tech | Tech stack identified | 15% |
+| UX | UX/UI patterns analyzed | 15% |
+| SEO | SEO elements inspected | 15% |
+| A11y | Accessibility checked | 15% |
+| Performance | Performance hints analyzed | 10% |
+| Actionability | Improvements suggested | 15% |
+
+### Score Calculation
+
+```
+Score = sum(checked items * weight) / 100
+
+Grades:
+- 95-100: EXCELLENT — comprehensive analysis
+- 90-94:  GOOD — minor gaps, additional exploration recommended
+- 80-89:  FAIR — needs deeper exploration
+- 0-79:   POOR — incomplete, re-analyze
+```
+
+### Depth Levels
+
+| Level | Scope | Output |
+|-------|-------|--------|
+| L1: Surface | File names, basic structure | File list |
+| L2: Structure | Functions, classes, imports | Structure map |
+| L3: Logic | Business logic, data flow | Flow analysis |
+| L4: Deep | Edge cases, dependencies, risks | Full analysis |
+
+**Minimum**: L3 for feature analysis, L2 for project overview.
+
+### Forbidden Patterns
+
+| Pattern | Problem | Fix |
+|---------|---------|-----|
+| "and more..." | Incomplete | List all items |
+| "etc." | Vague | Be specific |
+| "related files" without paths | Missing detail | Provide file paths |
+| Missing line numbers | Hard to navigate | Use `:L10-50` format |
+| No auth info on endpoints | Security gap | Always specify auth |
+
+### Quality Thresholds
+
+**Code (`--code`):**
+
+| Metric | Good | Warning | Critical |
+|--------|------|---------|----------|
+| Avg Complexity | ≤10 | 11-15 | >15 |
+| Max Function Length | ≤30 | 31-50 | >50 |
+| High Complexity Files | 0 | 1-3 | >3 |
+| Circular Dependencies | 0 | 1 | >1 |
+
+**Dependencies (`--deps`):**
+
+| Metric | Good | Warning | Critical |
+|--------|------|---------|----------|
+| Outdated Packages | 0-3 | 4-10 | >10 |
+| Security Vulnerabilities | 0 | 1-2 (low) | Any high/critical |
+| Major Version Behind | 0 | 1-2 | >2 |

package/skills/vibe.clone/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: vibe.clone
 description: URL → 마크업 레벨 픽셀 완벽 클론 — 헤드리스 브라우저로 라이브 사이트 캡처 후 현재 프로젝트 스택에 맞게 스캐폴딩
-argument-hint: "<url> [<url2>...] [--name=<feature>] [--mo-only] [--pc-only] [--ignore-robots] [--no-interact] [--real-content]"
+argument-hint: "<url> [<url2>...] [--name=<feature>] [--sub] [--mo-only] [--pc-only] [--ignore-robots] [--no-interact] [--real-content]"
 user-invocable: true
 ---
 
@@ -18,6 +18,7 @@ URL을 받아 **마크업 수준으로 정밀 복제**하고 현재 프로젝트
 /vibe.clone <url> --mo-only                    # 모바일(375×812)만 캡처
 /vibe.clone <url> --pc-only                    # 데스크탑(1440×900)만 캡처
 /vibe.clone <url> --name=stripe-clone          # 기능 이름 지정 (기본: 호스트명 kebab-case)
+/vibe.clone <url> --sub                        # 사이트맵/메가메뉴 하위 메뉴 URL까지 함께 클론
 /vibe.clone <url1> <url2> <url3>               # 다중 페이지 클론 (같은 사이트의 여러 경로)
 /vibe.clone <url> --ignore-robots              # robots.txt 무시 (사이트 소유자 허가 있을 때만)
 /vibe.clone <url> --no-interact                # 능동 인터랙션 스윕 끄기 (완전 결정론적·재현 가능 캡처)
@@ -31,12 +32,22 @@ Step 1) 인자 수집
   urls         = http(s):// 로 시작하는 모든 인자
   feature      = --name=<value> | URL host → kebab-case
   scope        = --mo-only | --pc-only | (기본: both)
+  sub          = --sub 플래그 유무
   ignoreRobots = --ignore-robots 플래그 유무
   realContent  = --real-content 플래그 유무 (소유/허가 확인 질문 1회 후 적용)
 
 Step 2) 인자 검증
   urls.length === 0  → 사용자에게 URL 입력 요청, 중단
   ! /^https?:\/\//.test(url) → "유효한 URL이 아닙니다" 에러, 중단
+  --sub && urls.length > 1 → "--sub는 기준 URL 1개와 함께 사용하세요" 에러, 중단
+
+Step 2.5) --sub URL 확장
+  - node {{VIBE_PATH}}/hooks/scripts/clone-extract.js suburls <url> \
+      --out=/tmp/{feature}/menu-urls.json [--ignore-robots]
+  - menu-urls.json.urls 를 urls 로 사용
+  - 수집 기준: /sitemap 우선, 없으면 header/nav/mega-menu
+  - 포함: 같은 origin + 같은 locale prefix의 하위 메뉴 URL
+  - 제외: 외부 링크, 언어 전환, 검색, TOP, 푸터 정책/문의/파트너/뉴스룸 링크
 
 Step 3) 스킬 진입
   → clone 스킬 Phase 0부터 순차 실행
@@ -51,6 +62,7 @@ Step 3) 스킬 진입
 Phase 0: Setup
   - .vibe/config.json + package.json → 스택 감지
   - feature 이름 결정, 디렉토리 생성
+  - --sub이면 /tmp/{feature}/menu-urls.json 생성 후 URL 목록 확장
 
 Phase 1: Capture (병렬 — scope에 따라 MO/PC 동시)
   - node {{VIBE_PATH}}/hooks/scripts/clone-extract.js capture <url> \
@@ -108,6 +120,7 @@ Phase 5: Pixel Verification (P1=0까지 루프 — clone SKILL.md 규칙; 병합
 
 ```
 /tmp/{feature}/                  # 작업 디렉토리 (산출물 원본)
+  ├── menu-urls.json             # --sub URL 확장 결과
   ├── mo/, pc/                   # rendered.html, computed.json, screenshot.png, states.json, behaviors.json, sections.json, assets/
   └── project-tokens.json        # 기존 프로젝트 토큰 인덱스
 

package/skills/vibe.continue/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: vibe.continue
+description: Restore previous session context for continuity — memory load, context restore, resume from last checkpoint.
+argument-hint: (no arguments)
+user-invocable: true
+---
+
+# /vibe.continue
+
+Restore previous session context for continuity.
+
+## Usage
+
+```
+/vibe.continue
+```
+
+## Process
+
+1. Calls `core_start_session` to load project memories
+2. Restores previous conversation context
+3. Resumes work from last checkpoint
+
+## When to Use
+
+- At new session start, to pick up exactly where the previous session left off
+- At 85%+ context usage: `save_memory` → `/new` → `/vibe.continue` (컨텍스트 리셋 후 즉시 복원)
+- Combine with the `handoff` skill for detailed handover: Handoff writes a manual `HANDOFF.md` (work progress + notes + file list) before a session ends; `/vibe.continue` automatically restores memory + session state at the start of the next one.
+
+---
+
+ARGUMENTS: $ARGUMENTS

package/skills/vibe.design/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: vibe.design
 description: DESIGN.md(시각 품질 SSOT) 생성·검증·드리프트 검사·동기화. Figma 독립.
-argument-hint: "init [--from=interview|code|reference|figma] | lint | verify | sync"
+argument-hint: "init [--from=interview|code|reference|figma] | lint | verify | sync | preview"
 user-invocable: true
 ---
 
@@ -22,6 +22,7 @@ user-invocable: true
 /vibe.design lint                       # Stitch 9 섹션 완전성 검증
 /vibe.design verify [--files=<glob>]    # 구현 ↔ DESIGN.md hex 드리프트 (v1)
 /vibe.design sync                       # Figma 연결 시 양방향 동기화 (Should, Phase 2)
+/vibe.design preview "description"      # UI 프리뷰 (Antigravity 목업 또는 ASCII 폴백)
 ```
 
 ## Philosophy
@@ -152,6 +153,25 @@ user-invocable: true
 
 **v1 동작**: "Phase 2 에서 활성됩니다. 현재는 `/vibe.figma --emit-design-md` 를 사용하세요." 메시지 후 종료.
 
+### Subcommand: `preview`
+
+Generate the UI preview directly in the main session (native capability — no dedicated agent). DESIGN.md 와 독립적으로 동작 — 임시 프리뷰용.
+
+Generate UI preview from a text description, a design folder, or a single file.
+
+- **Antigravity enabled**: UI mockup image + component code generation
+- **Antigravity disabled**: ASCII art fallback
+
+**Input types:**
+
+| Input | Example |
+| ----- | ------- |
+| Text description | `"Login form with email, password"` |
+| Design folder | `./design/` |
+| Single file | `./mockups/login.html` |
+
+> Read `references/ui-preview.md` for the full supported file-format list and example invocations.
+
 ## Integration
 
 | Skill | 통합 지점 |
@@ -173,11 +193,13 @@ user-invocable: true
 |-----|---------|
 | `<root>/DESIGN.md` | `init` / `sync` |
 | 콘솔 리포트 | `lint` / `verify` |
+| ASCII 프리뷰 또는 목업 이미지 | `preview` |
 
 ## Heuristics & References
 
 - 코드 역추출 패턴: `heuristics/code-extract.md`
 - 시드 카탈로그: `references/README.md`
+- UI 프리뷰 포맷·예시: `references/ui-preview.md`
 - 템플릿: `templates/DESIGN.md.template`
 
 ARGUMENTS: $ARGUMENTS

package/skills/vibe.design/references/ui-preview.md

@@ -0,0 +1,20 @@
+# vibe.design — UI Preview: Supported Formats & Example
+
+> Loaded by vibe.design SKILL.md `preview` subcommand — full supported file-format list and example invocations.
+
+**Supported file formats in folder:**
+
+- `*.html` - HTML mockups
+- `*.png` / `*.jpg` / `*.webp` - UI screenshots (Claude reads images)
+- `*.json` - Design tokens
+- `*.css` / `*.scss` - Style variables
+- `*.md` - Style guides
+- `*.svg` - Vector graphics
+
+**Example:**
+
+```
+/vibe.design preview "Login form - email, password input + login button"
+/vibe.design preview ./design/dashboard/
+/vibe.design preview ./mockups/homepage.png
+```

package/skills/vibe.docs/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: vibe.docs
-description: Generate project documentation — README, architecture docs, user guide, release notes, agent instructions
-argument-hint: "readme, guide, arch, release, or agent"
+description: Generate project documentation — README, architecture docs, user guide, release notes, agent instructions, diagrams, codemaps
+argument-hint: "readme, guide, arch, release, agent, diagram, or codemaps"
 user-invocable: true
 ---
 
@@ -17,6 +17,8 @@ Generate or update project documentation by analyzing the actual codebase.
 /vibe.docs arch       # 아키텍처 문서 + Mermaid 다이어그램 (docs/ARCHITECTURE.md)
 /vibe.docs release    # 릴리즈 노트 (git history 기반)
 /vibe.docs agent      # CLAUDE.md / AGENTS.md 생성·동기화 (agents-md 검증 필수)
+/vibe.docs diagram    # Mermaid 다이어그램 (architecture/ER/flow/seq) → .vibe/diagrams/
+/vibe.docs codemaps   # 코드베이스 구조 자동 문서화 → docs/CODEMAPS/
 ```
 
 ## Pipeline Position