@su-record/vibe 2.9.40 → 2.10.2

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
@@ -106,13 +106,13 @@ graph TD
 | CLI | File | Support |
 |---|---|---|
 | Claude Code | `CLAUDE.md` | 100% (Primary) |
-| coco | `AGENTS.md` | 100% (Primary) |
+| Codex | `AGENTS.md` | 100% (Primary) |
 
-Gemini CLI / Codex CLI / Cursor are not supported — do not generate or check `GEMINI.md`.
+Gemini CLI / Cursor are not supported — do not generate or check `GEMINI.md`.
 
 **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):**
 
@@ -120,7 +120,7 @@ Gemini CLI / Codex CLI / Cursor are not supported — do not generate or check `
 2. **For `AGENTS.md`**:
    - **If missing** → create by cloning `CLAUDE.md` + applying CLI substitution (below).
    - **If exists** → regenerate from current `CLAUDE.md` + substitution, preserving user-specific additions outside the VIBE block.
-3. **CLI substitution for `AGENTS.md`** (coco): `Claude Code` → `coco` · `~/.claude/` → `~/.coco/` · `.claude/` → `.coco/` · `CLAUDE.md` → `AGENTS.md`. `CLAUDE.md` itself gets no substitution.
+3. **CLI substitution for `AGENTS.md`** (Codex): `Claude Code` → `Codex` · `~/.claude/` → `~/.codex/` · `.claude/` → `.codex/` · `CLAUDE.md` → `AGENTS.md`. `CLAUDE.md` itself gets no substitution.
 4. **Validate every touched file (whether newly created or modified)** via the `claude-md-guide` → `agents-md` skill chain — see validation block below. **Never write or save without running this step.**
 5. Report per file: created / updated / skipped / validation warnings.
 

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]

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

@@ -1,10 +1,10 @@
 ---
-name: vibe-interview
+name: interview
+description: 도메인 요구사항 인터뷰 본체 — type별 체크리스트(website/webapp/mobile/api/library/feature)로 사용자가 stop 할 때까지 루프.
+when_to_use: /vibe.spec orchestrator의 Phase 1에서 호출. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "Iteratively interview the user to gather ALL required and optional requirements for a new project or feature. Loops until the user explicitly stops. Uses type-specific domain checklists (website, webapp, mobile, api, library, feature) so nothing is missed. Must use this skill when the user says '만들자', '개발하자', '신규 기능', '무엇을 만들', 'let's build', 'new feature', or starts describing a product idea without a plan yet."
-triggers: [만들자, 개발하자, 기획하자, 신규 기능, 새 프로젝트, "무엇을 만들", "무엇을 개발", 아이디어, 인터뷰, interview, requirements, "let's build", "new feature", "new project"]
-priority: 95
-chain-next: [vibe-plan]
+chain-next: [plan]
 ---
 
 # vibe.interview — Domain Requirements Interview
@@ -20,7 +20,7 @@ chain-next: [vibe-plan]
 
 **Skip when**:
 - Small bug fix on an existing project
-- `.vibe/plans/{feature}.md` already exists (→ only update via `vibe-plan`)
+- `.vibe/plans/{feature}.md` already exists (→ only update via `plan`)
 
 ## Core Loop
 
@@ -53,7 +53,7 @@ chain-next: [vibe-plan]
 4. Save collected results
    .vibe/interviews/{feature}.md
      ↓
-5. chain-next: vibe-plan
+5. chain-next: plan
 ```
 
 ## Step 0: Git Branch (MANDATORY)
@@ -101,7 +101,7 @@ What kind of project is this?
 Read the checklist file for the detected type:
 
 ```
-Read skills/vibe-interview/checklists/{type}.md
+Read skills/interview/checklists/{type}.md
 ```
 
 The checklist is divided into a **Required** section and an **Optional** section. Each item has the following structure:
@@ -269,9 +269,9 @@ This pointer is used by /vibe.spec (no args) for Smart Resume.
 No-op if the value is already the same.
 ```
 
-## Step 5: Chain to vibe-plan
+## Step 5: Chain to plan
 
-After the interview is complete, the `vibe-plan` skill is automatically activated to refine the results into a structured plan.
+After the interview is complete, the `plan` skill is automatically activated to refine the results into a structured plan.
 
 ```
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -283,7 +283,7 @@ After the interview is complete, the `vibe-plan` skill is automatically activate
    Optional: 12/14
    Discovered: 3
 
-→ vibe-plan skill is starting plan creation...
+→ plan skill is starting plan creation...
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
 
@@ -293,7 +293,7 @@ After the interview is complete, the `vibe-plan` skill is automatically activate
 - Prompting the user to stop before Required items are complete
 - Ignoring a user's answer and moving on to the next question
 - Missing areas not in the checklist (use `discovered`)
-- Writing the plan in PTCF/EARS/Phase structure here (that is refined by vibe-plan; the actual spec is written by /vibe.spec)
+- Writing the plan in PTCF/EARS/Phase structure here (that is refined by plan; the actual spec is written by /vibe.spec)
 - Ending with 10 shallow questions (keep going until the user explicitly stops)
 - Providing only multiple-choice options without allowing free input
 
@@ -347,12 +347,12 @@ Claude: ⚠️ All required items complete. 10 optional items will be marked as
         ✅ Interview complete!
         📄 .vibe/interviews/parallax-website.md
 
-        → vibe-plan skill is starting plan creation...
+        → plan skill is starting plan creation...
 ```
 
 ## Related
 
-- **Next**: `vibe-plan` — refine interview results into a structured plan
-- **After plan**: `vibe-spec` (skill) → generates SPEC → then `/vibe.run` (logic) + `/vibe.figma` (UI track) in parallel
+- **Next**: `plan` — refine interview results into a structured plan
+- **After plan**: `spec` (skill) → generates SPEC → then `/vibe.run` (logic) + `/vibe.figma` (UI track) in parallel
 - **Templates**: `~/.claude/vibe/templates/plan-template.md`
-- **Checklists**: `skills/vibe-interview/checklists/{type}.md`
+- **Checklists**: `skills/interview/checklists/{type}.md`

package/skills/parallel-research/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: parallel-research
+user-invocable: false
+invocation: [auto]
 tier: standard
 description: "Parallel research with 4 specialized agents (best-practices, framework-docs, codebase-patterns, security-advisory) running simultaneously. Use when facing unfamiliar technology, choosing between libraries/frameworks, designing architecture for a new feature, or investigating security implications. Must use this skill when user asks 'how should we build X', 'which library for Y', or when starting work on a complex feature with unknown requirements. Not for simple lookups — use web search directly for those."
 triggers: [parallel research, complex feature, technology selection, architecture design, security critical]

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

@@ -1,10 +1,10 @@
 ---
-name: vibe-plan
+name: plan
+description: 인터뷰 결과 → 사람이 읽는 기획서(vision document) 정제 본체. /vibe.spec → 코드, /vibe.figma → UI 스토리보드의 입력.
+when_to_use: interview 완료 후 또는 /vibe.spec Phase 2에서 체인. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "Refine a vibe-interview result into a human-readable markdown 기획서 (planning document). The plan is a vision document that downstream skills/commands use: /vibe.spec consumes it for code implementation, /vibe.figma uses it for UI storyboards. Must use this skill after vibe-interview completes, or when the user has raw interview notes and wants a structured plan document."
-triggers: [기획서, 기획서 작성, plan document, 기획 정리, "interview 정리", refine plan]
-priority: 90
-chain-next: [vibe-spec, vibe-figma]
+chain-next: [spec, figma]
 ---
 
 # vibe.plan — Interview → Plan Document Refinement
@@ -13,12 +13,12 @@ chain-next: [vibe-spec, vibe-figma]
 
 ## When to Use
 
-- `vibe-interview` has just completed and `.vibe/interviews/{feature}.md` exists
+- `interview` has just completed and `.vibe/interviews/{feature}.md` exists
 - The user requests "write me a plan document" or "clean up the interview"
 - Need to convert an external PRD/wireframe into the vibe plan document format
 
 **Skip condition**:
-- If this skill is called directly without an interview → chain to `vibe-interview` first (no chain-prev; inform the user)
+- If this skill is called directly without an interview → chain to `interview` first (no chain-prev; inform the user)
 
 ## Core Flow
 
@@ -55,7 +55,7 @@ Read .vibe/interviews/{feature-name}.md
 Extract `type`, `status`, `requiredCollected`, `optionalCollected`, etc. from the frontmatter.
 
 **Validation**:
-- If the file does not exist → guide the user to run `vibe-interview` first.
+- If the file does not exist → guide the user to run `interview` first.
 - `status: partial` + Required items incomplete → apply **AI-Driven Gap Filling**:
 
 ### AI-Driven Gap Filling
@@ -249,6 +249,6 @@ Where would you like to start?
 
 ## Related
 
-- **Prev**: `vibe-interview` — requirements collection (implicit chain-prev)
+- **Prev**: `interview` — requirements collection (implicit chain-prev)
 - **Next**: `/vibe.spec` (code spec), `/vibe.figma` (UI design)
 - **Template**: `~/.claude/vibe/templates/plan-template.md`

package/skills/prioritization-frameworks/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: prioritization-frameworks
+invocation: [auto, chain]
 tier: standard
 description: "Reference guide to 9 prioritization frameworks with formulas, when-to-use guidance, and templates — RICE, ICE, Kano, MoSCoW, Opportunity Score, and more."
 triggers: [prioritize, prioritization, rice, ice, kano, moscow, opportunity score]

package/skills/priority-todos/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: priority-todos
+user-invocable: false
+invocation: [auto]
 tier: standard
 description: "Priority-based TODO management (P1/P2/P3). Auto-activates when managing tasks, reviewing issues, or organizing work by priority."
 triggers: [todo, priority, P1, P2, P3, task management, issue, organize]

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

@@ -1,10 +1,9 @@
 ---
-name: vibe-regress
+name: regress
+description: 회귀 테스트 자동 진화 본체 — 버그 등록 → 예방 테스트 생성 → 반복 패턴 클러스터 → git fix 커밋 import. 저장소 .vibe/regressions/.
+when_to_use: /vibe.regress 진입점 / /vibe.verify 실패 시 체인. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "Regression test auto-evolution. Registers bugs (auto from /vibe.verify failures or manual), generates preventive vitest/jest files from bug records, clusters repeated patterns (3+ same root-cause-tag) into shared tests, and imports historical `fix:` commits from git log. Storage: .vibe/regressions/<slug>.md. Must use this skill when user runs /vibe.regress, when /vibe.verify produces a failure, or when the user says 'don't let this happen again' / 'regression test' / '회귀 테스트'."
-triggers: [regress, regression, "회귀", "다시는", "반복 버그", "fix commit"]
-priority: 70
-chain-next: []
 ---
 
 # vibe.regress — Regression Auto-Evolution
@@ -134,7 +133,7 @@ cart-stock-race-double-deduct     cart      concurrency open             1d
 When `/vibe.verify` fails it calls:
 
 ```
-Load skill `vibe-regress` with: register --from-verify
+Load skill `regress` with: register --from-verify
   <feature>: {feature-name}
   <scenario>: {failed-scenario}
   <error>: {error-message}

package/skills/rob-pike/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: rob-pike
+user-invocable: false
+invocation: [auto]
 tier: core
 description: "Rob Pike's 5 Rules — block premature optimization. Auto-activates on optimize, slow, performance, cache, parallelize keywords."
 triggers: [optimize, slow, performance, cache, parallelize, bottleneck, speed up, faster, latency, benchmark]

package/skills/seo-checklist/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: seo-checklist
+invocation: [auto]
 tier: core
 description: "SEO gotchas for web development — easy-to-miss items that hurt search ranking. Covers meta tags, Open Graph, structured data (JSON-LD), sitemap, robots.txt, canonical URLs, and Naver/Google-specific requirements. Use when building or reviewing any public-facing web page, landing page, or marketing site. Must use this skill when user mentions SEO, search ranking, meta tags, or when deploying a web app that needs to be discoverable."
 triggers: [seo, search, meta, sitemap, schema, structured data, og, opengraph, google, naver]

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

@@ -1,10 +1,10 @@
 ---
-name: vibe-spec
+name: spec
+description: PTCF 구조 SPEC 한 문서 작성 — parallel research (GPT/Gemini/Claude agents), ambiguity scan, 100-point quality gate. plan 파일 입력 → .vibe/specs/{feature}.md + .vibe/features/{feature}.feature 생성.
+when_to_use: vibe.spec orchestrator의 Phase 3에서 호출. 직접 호출 금지 — /vibe.spec 사용.
+user-invocable: false
 tier: core
-description: "Create an AI-executable PTCF-structured SPEC document through conversational requirements gathering, parallel research (GPT/Gemini/Claude agents), PTCF writing, ambiguity scan, and 100-point quality gate (loops until perfect or stuck). Produces .vibe/specs/{feature}.md + matching .vibe/features/{feature}.feature (BDD). Must use this skill when the user says 'write spec', 'create spec', '/vibe.spec', or when a plan document exists and is ready for code specification."
-triggers: [spec, SPEC, 명세, "코드 명세", "구현 명세", "write spec", "create spec", PTCF]
-priority: 85
-chain-next: [vibe-spec-review]
+chain-next: [spec-review]
 ---
 
 # vibe.spec — Specification Agent
@@ -29,7 +29,7 @@ When `ultrawork` (or `ulw`) is included, automatically chains:
     ↓
 [1] SPEC Creation (this command)
     ↓
-[2] Auto: Load skill `vibe-spec-review` (chain-next from this skill)
+[2] Auto: Load skill `spec-review` (chain-next from this skill)
     ↓
 [3] Auto: /vibe.run "{feature}" ultrawork
 ```
@@ -483,10 +483,10 @@ node "[LLM_SCRIPT]" gemini orchestrate-json "Security advisories for passkey aut
 
 | Claude Agent | Role | Source |
 |--------------|------|--------|
-| `best-practices-agent` | Best practices for [feature] + [stack] | WebSearch |
-| `framework-docs-agent` | Latest docs via context7 | context7 MCP |
-| `codebase-patterns-agent` | Similar patterns in existing codebase | Glob, Grep |
-| `security-advisory-agent` | Security advisories for [feature] | WebSearch |
+| `best-practices` | Best practices for [feature] + [stack] | WebSearch |
+| `framework-docs` | Latest docs via context7 | context7 MCP |
+| `codebase-patterns` | Similar patterns in existing codebase | Glob, Grep |
+| `security-advisory` | Security advisories for [feature] | WebSearch |
 
 **Total: 4 GPT/Gemini calls (Bash) + 4 Claude agents (Task) = 8 parallel research tasks**
 
@@ -954,7 +954,7 @@ Stuck? (score == prev_score)
   ├─ Interactive: ask user → fill values OR "proceed" OR "abort"
   └─ ultrawork: record gaps as TODO → proceed
       ↓
-Score == 100 (or user-approved) → SPEC Draft Complete → Handoff to vibe-spec-review skill
+Score == 100 (or user-approved) → SPEC Draft Complete → Handoff to spec-review skill
 ```
 
 #### 7.4 Auto-Fix for Low Score
@@ -977,7 +977,7 @@ After SPEC draft is complete (score ≥ 95):
 **If `ultrawork` mode:**
 - ❌ DO NOT show handoff message
 - ❌ DO NOT ask for confirmation
-- ✅ Immediately load skill `vibe-spec-review` with feature `{feature-name}` (chain-next)
+- ✅ Immediately load skill `spec-review` with feature `{feature-name}` (chain-next)
 - ✅ After review passes, immediately proceed to `/vibe.run "{feature-name}" ultrawork`
 
 **If normal mode:**
@@ -995,10 +995,10 @@ Output the handoff message:
 ⏱️ Completed: {getCurrentTime result}
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-⚠️ NEXT STEP: Run SPEC review (vibe-spec-review skill)
+⚠️ NEXT STEP: Run SPEC review (spec-review skill)
 
 Option 1 (same session):
-  Load skill `vibe-spec-review` with feature `{feature-name}`
+  Load skill `spec-review` with feature `{feature-name}`
   (or natural language: "spec review")
 
 Option 2 (recommended for large context):

package/skills/{vibe-spec-review → spec-review}/SKILL.md

@@ -1,17 +1,16 @@
 ---
-name: vibe-spec-review
+name: spec-review
+description: SPEC 품질 리뷰 본체 — GPT/Gemini 크로스 검증, 100-point gate, Race Review(수렴 종료), Codex 적대 리뷰, 사용자 체크포인트.
+when_to_use: spec 완료 후 또는 /vibe.spec Phase 4에서 체인. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "Review and enhance an existing SPEC with GPT/Gemini cross-validation. Runs 100-point quality gate (loop until perfect or stuck), Race Review with convergence-based termination (no round cap), optional Codex adversarial review, Review Debate Team, and final user checkpoint. Must use this skill after vibe-spec completes, or when the user says 'review spec', '스펙 리뷰'."
-triggers: ["spec review", "review spec", "SPEC 리뷰", "명세 리뷰", race review]
-priority: 80
-chain-next: []
 ---
 
-# vibe-spec-review — SPEC Quality Review
+# spec-review — SPEC Quality Review
 
 Review and enhance SPEC with GPT/Gemini cross-validation.
 
-**Purpose:** Run this skill after `vibe-spec` to ensure accurate review execution. For large contexts, invoke in a new session.
+**Purpose:** Run this skill after `spec` to ensure accurate review execution. For large contexts, invoke in a new session.
 
 ---
 
@@ -20,7 +19,7 @@ Review and enhance SPEC with GPT/Gemini cross-validation.
 This skill is automatically called in Phase 4 of the `/vibe.spec` orchestrator. If direct invocation is needed:
 
 ```
-Load skill `vibe-spec-review` with feature: "feature-name"
+Load skill `spec-review` with feature: "feature-name"
 ```
 
 Or via natural language trigger: "스펙 리뷰", "review spec", "명세 리뷰".
@@ -57,7 +56,7 @@ If the value is already the same, no-op.
 ```
 /vibe.spec "feature" → SPEC created (Phase 3)
         ↓
-Phase 4: vibe-spec-review skill (this) → Quality validation + GPT/Gemini review
+Phase 4: spec-review skill (this) → Quality validation + GPT/Gemini review
         ↓
     /vibe.run "feature"
 ```

package/skills/systematic-debugging/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: systematic-debugging
+user-invocable: false
+invocation: [auto]
 tier: core
 description: "Enforce reproduce-first, root-cause-first, failing-test-first debugging. Auto-activates on bug, error, fail, broken, crash, flaky keywords."
 triggers: [bug, error, fail, broken, crash, flaky, not working, regression, unexpected, stack trace, exception, debug]

package/skills/techdebt/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: techdebt
+user-invocable: false
+invocation: [auto, chain]
 tier: core
 description: "Technical debt cleanup — detect and fix duplicate code, console.log, unused imports, any types, etc. Recommended before session end. Activates on techdebt, cleanup, debt keywords."
 triggers: [techdebt, cleanup, debt, unused imports, console.log, dead code]

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

@@ -1,19 +1,18 @@
 ---
-name: vibe-test
+name: test
+description: vibe 자가검진 본체 — 대상 harness(~/.claude/~/.codex)의 모든 command/skill/hook/agent 프로빙 → pass/fail 리포트 → ~/.vibe/test-reports/.
+when_to_use: /vibe.test 진입점에서 체인 호출. 직접 호출 금지.
+user-invocable: false
 tier: core
-description: "Self-test vibe by probing every command/skill/hook/agent in a target harness install dir (~/.claude or ~/.coco) and writing a pass/fail report to ~/.vibe/test-reports/. Takes an optional harness argument (cc|coco); empty = current harness. Must use this skill when user runs /vibe.test, when verifying a vibe install before release, or when the user says 'self-test', 'harness 점검', 'vibe 건강'."
-triggers: [test, self-test, "vibe 건강", "harness 점검", "자가검진"]
-priority: 70
-chain-next: []
 ---
 
-# vibe-test — Self-Test
+# test — Self-Test
 
 Probe every shipped vibe surface in one install dir and emit a pass/fail report.
 
 ## Why this exists
 
-When vibe ships new commands, skills, hooks, or agents, one side (CC or coco) can end up out of sync with the other, frontmatter can drift, and hook tests can silently break. `/vibe.test` is the single mechanical check: does every surface in the target install actually load and pass its own tests?
+When vibe ships new commands, skills, hooks, or agents, one side (CC or Codex) can end up out of sync with the other, frontmatter can drift, and hook tests can silently break. `/vibe.test` is the single mechanical check: does every surface in the target install actually load and pass its own tests?
 
 ## Target harness
 
@@ -21,15 +20,15 @@ The argument selects which install dir to probe:
 
 | Arg | Probed dir |
 |---|---|
-| (empty) | current harness — CC: `~/.claude/`, coco: `~/.coco/` |
+| (empty) | current harness — CC: `~/.claude/`, Codex: `~/.codex/` |
 | `cc` | `~/.claude/` |
-| `coco` | `~/.coco/` |
+| `codex` | `~/.codex/` |
 
 If the target dir does not exist, print a clear message and exit with guidance (not an error). Example:
 
 ```
-~/.coco/ not found — coco isn't installed on this machine.
-  To install: pnpm add -g @su-record/vibe-coco
+~/.codex/ not found — Codex isn't installed on this machine.
+  To install: npm i -g @openai/codex
 ```
 
 ## Probes
@@ -39,7 +38,7 @@ All probes are **structural or test-based** — no interactive command is ever a
 | Category | Source | Check |
 |---|---|---|
 | commands | `<install>/commands/*.md` | file readable · frontmatter parses · `description` present · body references a skill (`Load skill \`...\``) if it delegates |
-| skills | `<install>/skills/*/SKILL.md` | frontmatter parses · required fields (`name`, `description`) · `triggers` array non-empty · body non-empty |
+| skills | `<install>/skills/*/SKILL.md` | frontmatter parses · required fields (`name`, `description`, `invocation`) · `invocation` ⊆ `{command, auto, chain}` and non-empty · if `invocation` includes `auto` then `triggers` non-empty · if includes `command` then matching `commands/{vibe.X}.md` or `Load skill <name>` reference exists · if includes `chain` then another skill lists it in `chain-next` · body non-empty |
 | hooks | repo `hooks/scripts/*.js` | for each script with a matching `__tests__/<name>.test.js`, run `npx vitest run <test> --reporter=json` and parse pass/fail counts |
 | agents | `<install>/agents/*.md` | file readable · frontmatter parses · required fields (`name`, `description`) |
 
@@ -68,8 +67,8 @@ Written to `~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.{json,md}`. Exact sch
       { "name": "vibe.test", "status": "pass" }
     ],
     "skills": [
-      { "name": "vibe-test", "status": "pass" },
-      { "name": "vibe-spec", "status": "fail", "error": "frontmatter: triggers array is empty" }
+      { "name": "test", "status": "pass" },
+      { "name": "spec", "status": "fail", "error": "invocation includes `auto` but triggers array is empty" }
     ],
     "hooks": [
       { "name": "pre-tool-guard", "status": "pass", "tests": "38/38" },
@@ -82,7 +81,7 @@ Written to `~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.{json,md}`. Exact sch
   "failed": [
     {
       "category": "skills",
-      "name": "vibe-spec",
+      "name": "spec",
       "error": "frontmatter: triggers array is empty"
     }
   ]
@@ -111,7 +110,7 @@ Written to `~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.{json,md}`. Exact sch
 
 ## Failures
 
-- **skills / vibe-spec** — frontmatter: triggers array is empty
+- **skills / spec** — invocation includes `auto` but triggers array is empty
 - **agents / explorer** — agent file not found
 ```
 
@@ -119,15 +118,15 @@ If `failed` is empty, replace the Failures section with `_All probes passed._`.
 
 ## Steps
 
-1. **Resolve target**: argument (`cc` / `coco` / empty). Empty → detect current harness (`$CLAUDE_PROJECT_DIR` set → `cc`; else fall back to `cc`).
-2. **Resolve install dir**: `cc` → `~/.claude`, `coco` → `~/.coco`. If missing → print guidance + exit.
+1. **Resolve target**: argument (`cc` / `codex` / empty). Empty → detect current harness (`$CLAUDE_PROJECT_DIR` set → `cc`; else fall back to `cc`).
+2. **Resolve install dir**: `cc` → `~/.claude`, `codex` → `~/.codex`. If missing → print guidance + exit.
 3. **Read `vibe_version`** from `package.json` in the current repo.
 4. **Walk each category**, run its check, append `{ name, status, error? }` to `probes.<category>`.
 5. **Compute** `summary` counts and the flat `failed[]` list.
 6. **Ensure** `~/.vibe/test-reports/` exists (`mkdir -p`, dir mode `0o700` — consistent with `~/.vibe/config.json`).
 7. **Write** `<ts>-<harness>.json` and `<ts>-<harness>.md`.
 8. **Print** the Markdown summary to the console.
-9. **If `summary.failed > 0`**, load skill `vibe-regress` with `subcommand: register --from-test` and pass the failed entries. P1 = any probe with `status: fail`.
+9. **If `summary.failed > 0`**, load skill `regress` with `subcommand: register --from-test` and pass the failed entries. P1 = any probe with `status: fail`.
 
 ## Done Criteria
 
@@ -138,3 +137,4 @@ If `failed` is empty, replace the Failures section with `_All probes passed._`.
 - [ ] Markdown summary printed to console after the run
 - [ ] Reports land in `~/.vibe/test-reports/`, never in project-local `.vibe/`
 - [ ] `failed.length > 0` → auto-invokes `/vibe.regress register --from-test`
+- [ ] `invocation` field invariants enforced per skill (`command` / `auto` / `chain` validity)

package/skills/tool-fallback/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: tool-fallback
+invocation: [auto]
 tier: optional
 description: "Tool failure fallback strategies with circuit breaker. Auto-activates on API errors, search failures, timeouts, 429, 5xx, overloaded errors."
 triggers: [API error, search failure, timeout, 429, 5xx, overloaded, fallback, circuit breaker]