@su-record/vibe 2.9.40 → 2.10.0

package/skills/clone/SKILL.md

@@ -0,0 +1,361 @@
+---
+name: clone
+description: URL → markup 수준 pixel-perfect 클론 본체 — headless browser로 라이브 사이트 캡처 후 현재 스택으로 스캐폴드.
+when_to_use: /vibe.clone 진입점에서 체인 호출. 직접 호출 금지.
+user-invocable: false
+tier: standard
+---
+
+# vibe.clone — Markup-Level Website Clone
+
+## Core Principles
+
+```
+The rendered DOM is the source of truth for markup. Screenshots are for pixel verification only.
+
+✅ Puppeteer-rendered DOM (post-JS) → HTML structural mapping
+✅ Computed CSS → SCSS direct conversion (no guessing)
+✅ All remote assets (images, fonts) → downloaded locally and rewritten to project paths
+✅ Claude handles semantic decisions only: tag selection, component splitting, interactions
+✅ Screenshots are used for verification only, not generation
+```
+
+## Immutable Rules
+
+```
+1. Do NOT generate CSS values by guessing or eyeballing screenshots.
+   ✅ Use clone-extract.js computed CSS output as-is.
+   ❌ Do NOT write CSS values directly inside scoped <style> blocks.
+
+2. Do NOT hotlink remote assets. All images/fonts must be downloaded and rewritten.
+
+3. Do NOT skip the pixel verification loop (Phase 5). The clone is incomplete without it.
+
+4. Do NOT copy textual content verbatim from copyrighted sources for production use.
+   This skill is for layout/markup learning ("클론 코딩"). Replace text with placeholders
+   or user-provided copy when shipping a real product.
+```
+
+## Full Flow
+
+```
+Input: a URL (or multiple URLs for multi-page clones)
+
+→ Phase 0: Setup (stack detection, feature naming, working dir)
+→ Phase 1: Capture (Puppeteer → rendered HTML + computed CSS + screenshots + assets)
+→ Phase 2: Refine (DOM → sections.json per breakpoint)
+→ Phase 3: Scaffold (sections.json → SCSS auto-gen + Claude-authored HTML/components)
+→ Phase 4: Compile gate
+→ Phase 5: Pixel verification loop
+
+Working directory:
+  /tmp/{feature}/
+  ├── mo/ (375×812)  — rendered.html, computed.json, screenshot.png, assets/, sections.json
+  ├── pc/ (1440×900) — rendered.html, computed.json, screenshot.png, assets/, sections.json
+  └── tokens.json    — extracted design tokens (colors/fonts/spacing)
+
+Code output: placed directly in the project directory per detected stack
+  components/{feature}/, styles/{feature}/, public/images/{feature}/
+```
+
+---
+
+## Phase 0: Setup
+
+```
+1. Stack detection:
+   - .vibe/config.json → stack (react/vue/next/svelte/vanilla, scss/tailwind/css-modules)
+   - Fallback: package.json deps
+2. Feature name: URL hostname → kebab-case (e.g. stripe.com → stripe-clone)
+   - User may override with --name=<custom>
+3. Directories:
+   - components/{feature}/, styles/{feature}/, public/images/{feature}/
+4. Component indexing → /tmp/{feature}/component-index.json
+   (scan up to 50 existing components, extract props/slots/classes, within 2 minutes)
+5. Design token scan → /tmp/{feature}/project-tokens.json
+   (SCSS > CSS Variables > Tailwind > CSS-in-JS)
+```
+
+---
+
+## Phase 1: Capture ← Headless browser (parallel MO/PC)
+
+**Coordinator pattern: run MO/PC capture as parallel workers.**
+
+### BLOCKING Command — Use only clone-extract.js for capture
+
+```bash
+# [CLONE_SCRIPT] = {{VIBE_PATH}}/hooks/scripts/clone-extract.js
+
+# Mobile (375×812)
+node {{VIBE_PATH}}/hooks/scripts/clone-extract.js capture <URL> \
+  --out=/tmp/{feature}/mo/ \
+  --viewport=375x812 \
+  --bp=mo
+
+# Desktop (1440×900)
+node {{VIBE_PATH}}/hooks/scripts/clone-extract.js capture <URL> \
+  --out=/tmp/{feature}/pc/ \
+  --viewport=1440x900 \
+  --bp=pc
+```
+
+⛔ **Writing custom capture scripts (puppeteer-fetch.mjs, etc.) is forbidden.**
+⛔ **Do NOT use WebFetch or curl** — they cannot render JS-driven SPAs.
+✅ Use clone-extract.js. If output is unsatisfactory, modify the script.
+
+### Output per breakpoint
+
+```
+/tmp/{feature}/{bp}/
+  ├── rendered.html       — final DOM after JS execution
+  ├── computed.json       — per-element computed CSS + bounding box
+  ├── screenshot.png      — full-page screenshot
+  ├── assets/
+  │   ├── images/         — all <img>, background-image, <picture> sources
+  │   └── fonts/          — @font-face srcs
+  └── asset-map.json      — remote URL → local path mapping
+```
+
+### Capture rules
+
+```
+1. Wait for `networkidle2` (no in-flight requests for 500ms) before snapshot
+2. Scroll to bottom slowly to trigger lazy-loaded content
+3. Resolve all <img src>, srcset, and computed background-image URLs
+4. Resolve @font-face src() URLs from all stylesheets
+5. Download assets in parallel (concurrency=8), preserve original extensions
+6. Rewrite asset URLs in rendered.html and computed.json to local paths
+7. Strip inline analytics/tracking scripts before saving rendered.html
+```
+
+---
+
+## Phase 2: Refine ← DOM → sections.json (independent per BP)
+
+### BLOCKING Command — Writing custom refine scripts is forbidden
+
+```bash
+# MO
+node {{VIBE_PATH}}/hooks/scripts/clone-refine.js \
+  /tmp/{feature}/mo/rendered.html \
+  /tmp/{feature}/mo/computed.json \
+  --out=/tmp/{feature}/mo/sections.json \
+  --bp=mo
+
+# PC
+node {{VIBE_PATH}}/hooks/scripts/clone-refine.js \
+  /tmp/{feature}/pc/rendered.html \
+  /tmp/{feature}/pc/computed.json \
+  --out=/tmp/{feature}/pc/sections.json \
+  --bp=pc
+```
+
+⛔ **Phase 3 is blocked until refine completes for all required BPs.**
+⛔ **Do NOT parse rendered.html with custom Python/Node scripts.**
+✅ Use clone-refine.js output as-is. If unsatisfactory, modify the script.
+
+### Refinement rules
+
+```
+Refinement applied when converting rendered.html + computed.json → sections.json:
+  1. Strip <script>, <noscript>, <style>, tracking pixels
+  2. Strip nodes with display:none, visibility:hidden, opacity:0, size 0
+  3. Detect sections: <header>, <nav>, top-level <section>/<main> children, <footer>
+     Fallback: top-level children of <body> with height > 100px
+  4. Detect repeated patterns (sibling nodes with same tag+class signature, count >= 3)
+     → mark as component candidates
+  5. Extract design tokens:
+     - colors: unique color/background-color values, sorted by frequency
+     - typography: font-family/size/weight combinations
+     - spacing: padding/margin values (px), bucketed to nearest 4px
+  6. Background images (background-image: url) → images.bg
+  7. Inline <img> → images.content
+  8. Keep CSS subset: layout (display/flex/grid/position/inset/margin/padding/width/height/gap),
+     typography (font-*, line-height, letter-spacing, text-*, color),
+     decoration (background, border, border-radius, box-shadow, opacity),
+     transform/transition
+```
+
+### Output
+
+```
+/tmp/{feature}/{bp}/sections.json:
+  {
+    meta: { feature, url, viewport, bp },
+    tokens: { colors: [...], typography: [...], spacing: [...] },
+    sections: [
+      {
+        name: "Header" | "Hero" | "Features" | ...,
+        nodeRef, tag, size, css,
+        text,                 // text content (placeholder candidates)
+        components: [...],    // detected repeated patterns
+        children: [...],      // full recursive subtree
+        images: { bg, content: [...] }
+      }
+    ]
+  }
+```
+
+---
+
+## Phase 3: Scaffold ← stack-specific code generation
+
+**⛔ Implement MO fully first → pass verification → then PC. No responsive conversion in this phase.**
+**⛔ CSS values must use computed.json output as-is. No vw/clamp/@media in this phase.**
+
+### BLOCKING Command — SCSS must only use script output
+
+```bash
+# Step A: Auto-generate SCSS skeleton (run once per BP)
+node {{VIBE_PATH}}/hooks/scripts/clone-to-scss.js \
+  /tmp/{feature}/{bp}/sections.json \
+  --out=/path/to/project/styles/{feature}/ \
+  --token-file=/tmp/{feature}/project-tokens.json
+
+# Step B: Per-section validation (after writing each section's component code)
+node {{VIBE_PATH}}/hooks/scripts/clone-validate.js \
+  /path/to/project/styles/{feature}/ \
+  /tmp/{feature}/{bp}/sections.json \
+  --section={SectionName}
+```
+
+⛔ **Writing SCSS files directly without calling clone-to-scss.js invalidates Phase 3.**
+⛔ **Do NOT write custom SCSS generation scripts.**
+⛔ **Do NOT proceed to the next section without a clone-validate.js PASS.**
+✅ Use clone-to-scss.js output as-is. If unsatisfactory, modify the script.
+
+```
+Phase 3A: MO Scaffold
+  Input: /tmp/{feature}/mo/sections.json
+  ⛔ No parallelism. Process one section at a time:
+    1. Read the target section from sections.json
+    2. Map component candidates against component-index.json
+       ├─ Match → import existing
+       └─ No match → create new in components/{feature}/
+    3. clone-to-scss.js → auto-generate SCSS skeleton (computed values as-is) — Step A once
+    4. Claude: HTML structure + semantic tags + framework-specific component file
+       ⛔ No CSS written directly in <style> blocks — only @import/@use allowed
+       Framework mapping:
+         - React/Next → .tsx with CSS Modules or styled-components per stack
+         - Vue/Nuxt   → .vue with scoped <style lang="scss"> @import only
+         - Svelte     → .svelte with <style> @import only
+         - Vanilla    → .html + linked .scss
+    5. Asset references → public/images/{feature}/ (already populated in Phase 1)
+    6. clone-validate.js → compare SCSS vs sections.json — Step B
+       ├─ PASS → next section
+       └─ FAIL → fix discrepancies → re-run step 6 (loop until P1=0, no round cap)
+  → Phase 4 (MO compile) → Phase 5 (MO pixel verification)
+
+Phase 3B: PC Scaffold
+  Same process as MO, input /tmp/{feature}/pc/sections.json
+  → Phase 4 (PC compile) → Phase 5 (PC pixel verification)
+
+Phase 3C: Responsive Integration (after both MO+PC pass verification)
+  → Merge MO+PC styles into @media-based responsive layout (separate flow, TODO)
+
+Claude's role (restricted):
+  ✅ Component candidates: decide which patterns become reusable components
+  ✅ HTML semantics: section/h1/p/button/nav tag selection
+  ✅ Text replacement: substitute copyrighted copy with placeholders or user-supplied text
+  ✅ Interactions: hover/focus states, click handlers, conditional rendering
+  ❌ Do NOT modify SCSS CSS values (use clone-to-scss.js output as-is)
+  ❌ Do NOT write CSS directly in <style> blocks
+  ❌ Do NOT use vw/clamp/@media or create custom mixins in Phase 3A/3B
+  ❌ Do NOT hotlink remote URLs — all assets must use local public/images/ paths
+```
+
+---
+
+## Phase 4: Compile Gate
+
+```
+No round cap. Loop until compile succeeds (or stuck → ask user).
+
+0. Capture baseline (before Phase 3): record existing tsc + build errors
+   → Phase 4 only fixes NEW errors
+
+1. TypeScript: vue-tsc / svelte-check / tsc --noEmit
+2. Build: npm run build (120s timeout)
+3. Dev server: npm run dev → detect port → polling
+
+On error: parse → auto-fix → re-check
+Termination:
+  ✅ Success: all checks pass → enter Phase 5
+  ⚠️ Stuck: same errors as previous round → ask user
+     1. Direct fix instructions → retry
+     2. "proceed" — record remaining errors as TODO, proceed to Phase 5
+     3. "abort" — halt
+  ultrawork mode: on stuck, record TODO without prompting and proceed
+
+⛔ Must enter Phase 5 after Phase 4 passes. Do NOT output a "completion summary".
+```
+
+---
+
+## Phase 5: Pixel Verification Loop ← MANDATORY
+
+**⛔ Phase 5 is mandatory, not optional. Enter automatically after Phase 4.**
+**⛔ Skipping Phase 5 makes the entire clone "incomplete".**
+
+```
+No round cap. Loop until P1=0 (or stuck → ask user).
+Infrastructure: src/infra/lib/browser/ (Puppeteer + CDP) — same as figma Phase 6.
+
+1. Render scaffolded page in dev server at matching viewport
+2. Capture screenshot → pixelmatch comparison against /tmp/{feature}/{bp}/screenshot.png
+   diffRatio > 0.05 (clone target is tighter than figma) → P1
+3. CSS comparison: live computed CSS vs /tmp/{feature}/{bp}/computed.json
+   delta > 2px → P1, ≤ 2px → P2
+4. Asset audit: every <img>/background-image resolves to local public/images/ path → else P1
+5. Fix P1 first (refer to computed.json, no guessing) → revalidate compile → reload
+
+Narrowing scope:
+  Round 1: P1+P2+P3
+  Round 2: P1+P2
+  Round 3+: P1 only
+
+Termination:
+  ✅ P1=0 AND no new findings → complete
+  ⚠️ Stuck: same findings → ask user (resolve / proceed / abort)
+  ultrawork mode: on stuck, record TODO without prompting and complete
+
+Responsive: after MO verification → change viewport → repeat against PC screenshot
+Cleanup: shut down browser + dev server
+
+⛔ "Completion summary" output only allowed after Phase 5 completes.
+```
+
+---
+
+## Legal & Ethical Notes
+
+```
+This skill is intended for:
+  ✅ "Clone coding" learning exercises (markup/layout study)
+  ✅ Rebuilding the user's own previously-deployed sites
+  ✅ Authorized redesigns where the user has rights to the source
+
+NOT intended for:
+  ❌ Republishing copyrighted content (text, images, logos) without permission
+  ❌ Deceptive look-alike sites (phishing, brand impersonation)
+  ❌ Bypassing robots.txt or rate-limiting protections
+
+Claude must:
+  - Replace copyrighted text content with placeholders (e.g. "[Lorem ipsum]") by default
+  - Skip and warn when robots.txt disallows fetching the target path
+  - Refuse if the user's stated intent is brand impersonation or deception
+```
+
+---
+
+## Error Recovery
+
+| Failure | Recovery |
+|---------|----------|
+| clone-extract.js Puppeteer launch failure | Verify Node ≥18 and that Chromium is installed (`npx puppeteer browsers install chrome`). Retry once. |
+| Target site blocks headless (403/Cloudflare) | Retry with `--stealth` flag (uses puppeteer-extra stealth plugin). If still blocked, report to user. |
+| Asset download 404 | Log to asset-map.json with `status: missing`. Use a 1×1 transparent placeholder. Continue. |
+| robots.txt disallows path | Halt Phase 1. Inform user; require explicit `--ignore-robots` flag to proceed. |
+| clone-refine.js produces empty sections | Site likely uses Shadow DOM or canvas rendering. Report and ask whether to fall back to screenshot-only mode. |
+| Pixel diff stuck > 0.05 after 5 rounds | Likely font fallback or anti-aliasing. Report metric, allow user to accept threshold. |

package/skills/commerce-patterns/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: commerce-patterns
+invocation: [auto]
 tier: core
 description: "E-commerce domain patterns — cart management, payment processing (Toss/Stripe/PG), inventory tracking, and order state machines with transaction safety. Use when implementing any shopping cart, checkout flow, payment integration, stock management, or order lifecycle. Covers idempotency keys, double-charge prevention, stock reservation, and refund flows. Must use this skill when the codebase involves e-commerce — even for seemingly simple 'add to cart' features."
 triggers: [commerce, ecommerce, cart, payment, checkout, inventory, stock, order, pg, toss, stripe]

package/skills/commit-push-pr/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: commit-push-pr
+invocation: [auto, chain]
 tier: optional
 description: "Commit, push, and create PR in one go. Auto-activates on commit, PR, push keywords."
 triggers: [commit, push, PR, pull request, merge]

package/skills/context7-usage/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: context7-usage
+invocation: [auto]
 tier: optional
 description: "Context7 plugin for latest library documentation. Auto-activates when docs, documentation, latest version, official docs, API reference, or library help is needed."
 triggers: [docs, documentation, latest version, official docs, API reference, library help, context7]

package/skills/{vibe-contract → contract}/SKILL.md

@@ -1,10 +1,9 @@
 ---
-name: vibe-contract
+name: contract
+description: API contract drift 탐지 본체 — SPEC contract 추출 → 구현 비교 → breaking drift P1을 regress로 자동 등록.
+when_to_use: /vibe.contract 진입점 / /vibe.spec 완료 / /vibe.verify 통과 시 체인. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "API contract drift detection. Extracts HTTP/GraphQL/event/public-function contracts from SPEC into .vibe/contracts/<feature>.md, compares to implementation, and fails loudly on breaking drift (missing endpoints, removed required fields, type changes). P1 drifts auto-register as regressions via vibe-regress. Must use this skill when user runs /vibe.contract, when /vibe.spec completes, when /vibe.verify passes scenarios, or when the user says 'contract', 'API schema', 'breaking change', 'drift', '계약', '스키마 바뀜'."
-triggers: [contract, drift, "계약", "API 변경", "breaking change", "schema drift"]
-priority: 70
-chain-next: []
 ---
 
 # vibe.contract — API Contract Drift Detection
@@ -116,7 +115,7 @@ endpoints:
 
 Auto-invoke right after the SPEC is written:
 ```
-Load skill `vibe-contract` with: extract <feature>
+Load skill `contract` with: extract <feature>
 ```
 Failure does not stop `/vibe.spec` (extraction is optional). On success, `/vibe.run` references this contract.
 
@@ -124,7 +123,7 @@ Failure does not stop `/vibe.spec` (extraction is optional). On success, `/vibe.
 
 After all scenarios pass:
 ```
-Load skill `vibe-contract` with: check <feature>
+Load skill `contract` with: check <feature>
 ```
 - no drift → verify still passes
 - P1 drift → demote verify to fail; auto-register
@@ -134,7 +133,7 @@ Load skill `vibe-contract` with: check <feature>
 
 On P1 drift:
 ```
-Load skill `vibe-regress` with:
+Load skill `regress` with:
   subcommand: register --from-contract
   feature: <feature>
   symptom: "Contract drift: <endpoint-id> <drift-type>"

package/skills/create-prd/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: create-prd
+invocation: [auto, chain]
 tier: standard
 description: "Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning."
 triggers: [prd, product requirements, feature spec, requirements document]

package/skills/design-audit/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: design-audit
+invocation: [command, auto]
 tier: standard
 description: "Design technical quality audit — a11y, performance, responsive, theming, AI slop detection with 5-dimension scoring. Use when design-audit, ui-audit, a11y-check, design-check."
 triggers: [design-audit, ui-audit, a11y-check, design-check]

package/skills/design-critique/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: design-critique
+invocation: [auto]
 tier: standard
 description: "UX design review — Nielsen heuristics scoring, 5-persona red flag analysis. Use when design-critique, ux-review, design-review."
 triggers: [design-critique, ux-review, design-review]

package/skills/design-distill/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: design-distill
+invocation: [auto]
 tier: standard
 description: "Remove unnecessary visual complexity — strip decorative clutter, apply progressive disclosure, simplify UI to essentials. Use when design-distill, simplify-ui, ui-simplify, strip-ui."
 triggers: [design-distill, simplify-ui, ui-simplify, strip-ui]

package/skills/design-normalize/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: design-normalize
+invocation: [command, auto]
 tier: standard
 description: "Normalize hardcoded values to design system tokens — colors, typography, spacing, shadows aligned to MASTER.md. Use when design-normalize, design-system, token-align."
 triggers: [design-normalize, design-system, token-align]

package/skills/design-polish/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: design-polish
+invocation: [auto]
 tier: standard
 description: "Pre-ship final polish pass — pixel alignment, interaction states, micro-details check and auto-fix. Use when design-polish, ui-polish, final-pass, ship-ready."
 triggers: [design-polish, ui-polish, final-pass, ship-ready]

package/skills/design-teach/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: design-teach
+user-invocable: false
+invocation: [command, auto]
 tier: standard
 description: "Gather and store project design context — target audience, brand personality, aesthetic direction, constraints. Used by other design-* skills. Use when design-teach, design-setup, design-context."
 triggers: [design-teach, design-setup, design-context]

package/skills/devlog/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: devlog
+invocation: [auto]
 tier: standard
 description: "Auto-generate devlog posts from git commit history. Triggers every N commits, writes markdown to configured target repo."
 triggers: [devlog, 개발일지, dev log, devlog 작성, 개발일지 작성]

package/skills/{vibe-docs → docs}/SKILL.md

@@ -1,9 +1,9 @@
 ---
-name: vibe-docs
+name: docs
+description: 프로젝트 문서 생성 본체 — README / 아키텍처 / 사용자 가이드 / 릴리즈 노트.
+when_to_use: /vibe.docs 진입점에서 체인 호출. 직접 호출 금지.
+user-invocable: false
 tier: standard
-description: "Generate project documentation — README, architecture docs, user guide, release notes. Activates on docs, readme, documentation keywords."
-triggers: [vibe-docs, docs, documentation, readme, release notes, architecture doc]
-priority: 50
 ---
 
 # vibe.docs — Project Documentation Generator
@@ -112,7 +112,7 @@ Gemini CLI / Codex CLI / Cursor are not supported — do not generate or check `
 
 **Source of truth:**
 - **`CLAUDE.md` is the content SSOT.** Always edit it first; `AGENTS.md` is a regenerated derivative.
-- Behavioral block: `skills/vibe-docs/templates/behavioral-principles.md` (4 Karpathy principles, wrapped in `<!-- VIBE-BEHAVIORAL:START/END -->` markers).
+- Behavioral block: `skills/docs/templates/behavioral-principles.md` (4 Karpathy principles, wrapped in `<!-- VIBE-BEHAVIORAL:START/END -->` markers).
 
 **Procedure (applies to both creation and modification):**
 

package/skills/e2e-commerce/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: e2e-commerce
+invocation: [auto]
 tier: core
 description: "E2E test scenarios for commerce checkout and payment flows. Provides ready-made Playwright test templates for cart→checkout→payment→confirmation flows, including PG sandbox testing (Toss/Stripe), error scenarios (payment failure, timeout, stock exhaustion), and idempotency verification. Use when writing E2E tests for any e-commerce feature — checkout, payment, order status, or refund flows."
 triggers: [e2e commerce, checkout test, payment test, order flow test]

package/skills/event-comms/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: event-comms
+invocation: [auto]
 tier: standard
 description: "Event communication automation — SMS via Aligo, email via Gmail OAuth, SNS posts for LinkedIn/Threads. Handles templates, BCC rules, and confirmation protocol."
 triggers: [sms, aligo, gmail, event email, event sms, 문자 발송, 메일 발송, SNS 홍보]

package/skills/event-ops/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: event-ops
+invocation: [auto]
 tier: standard
 description: "Event operations — nametags, checklists, operational slides, Slido plans, image generation specs, settlement reports."
 triggers: [nametag, checklist, event slide, slido, 이름표, 체크리스트, 운영 슬라이드, 정산]

package/skills/event-planning/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: event-planning
+invocation: [auto]
 tier: standard
 description: "Community event automation — D-Day timeline, community patterns, proactive task execution. Auto-activates for event planning, meetup/webinar/conference management."
 triggers: [event planning, meetup, webinar, conference, 행사, 밋업, 웨비나, D-Day, 이벤트 준비]

package/skills/exec-plan/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: exec-plan
+user-invocable: false
+invocation: [auto, chain]
 tier: core
 description: "Convert SPEC into a self-contained execution plan that agents can run autonomously for hours. Use when a SPEC has 3+ phases, multiple files to change, or complex dependencies between tasks. Produces a plan with explicit file paths, interface extracts, and acceptance criteria so agents never need to 'figure out' context. Must use this skill when launching long-running autonomous work, parallelizing implementation across agents, or when user says 'execute this spec' or 'run this plan'."
 triggers: [exec plan, execution plan, autonomous plan, self-contained plan, long-running]

package/skills/{vibe-figma → figma}/SKILL.md

@@ -1,7 +1,8 @@
 ---
-name: vibe-figma
-description: Figma design to code — tree-based structural code generation
-triggers: []
+name: figma
+description: Figma → 코드 본체 — tree 기반 구조적 코드 생성.
+when_to_use: /vibe.figma 진입점에서 체인 호출. 직접 호출 금지.
+user-invocable: false
 tier: standard
 ---
 

package/skills/{vibe-figma-convert → figma-convert}/SKILL.md

@@ -1,7 +1,8 @@
 ---
-name: vibe-figma-convert
-description: Figma tree → structured code generation + screenshot validation
-triggers: []
+name: figma-convert
+description: Figma tree → 구조적 코드 변환 + 스크린샷 검증 본체.
+when_to_use: figma 체인에서 호출. 직접 호출 금지.
+user-invocable: false
 tier: standard
 ---
 

package/skills/{vibe-figma-extract → figma-extract}/SKILL.md

@@ -1,7 +1,8 @@
 ---
-name: vibe-figma-extract
-description: Acquire code generation data via Figma REST API — tree (primary), images, screenshots (for validation)
-triggers: []
+name: figma-extract
+description: Figma REST API로 코드 생성 데이터 수집 — tree(주) + 이미지 + 스크린샷(검증).
+when_to_use: figma 체인에서 호출. 직접 호출 금지.
+user-invocable: false
 tier: standard
 ---
 

package/skills/git-worktree/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: git-worktree
+invocation: [auto]
 tier: optional
 description: "Git Worktree for parallel branch work. Auto-activates for PR review, hotfix, parallel testing, or working on multiple branches simultaneously."
 triggers: [worktree, PR review, hotfix, parallel branch, multiple branches]

package/skills/handoff/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: handoff
+user-invocable: false
+invocation: [auto]
 tier: standard
 description: "Generate HANDOFF.md work handover document before session end. Auto-activates on handoff, handover, session cleanup keywords."
 triggers: [handoff, handover, session cleanup, session end, context save]