@su-record/vibe 3.2.6 → 3.2.8

package/skills/vibe.docs/references/readme.md

@@ -0,0 +1,45 @@
+# /vibe.docs readme — README Generation
+
+> vibe.docs SKILL.md 의 서브커맨드 표에서 **`readme` 가 선택됐을 때만** 로드한다.
+
+### `/vibe.docs readme` — README Generation
+
+Analyze the codebase and generate a complete README.md:
+
+1. **Detect project nature**: Read package.json, CLAUDE.md, existing README
+2. **Extract key info**: Tech stack, installation, usage, API surface
+3. **Generate sections**:
+
+```markdown
+# Project Name
+> One-line description from package.json
+
+## What is this?
+[2-3 sentences explaining the problem and solution]
+
+## Quick Start
+[Installation + minimal usage example]
+
+## Features
+[Auto-detected from codebase — exported functions, CLI commands, API endpoints]
+
+## Architecture
+[High-level module diagram if 5+ source directories]
+
+## Configuration
+[Detected config files and their purposes]
+
+## Development
+[Build, test, lint commands from package.json scripts]
+
+## License
+```
+
+**Analysis approach:**
+```
+Full-file reading: package.json → name, description, scripts, dependencies
+File-pattern search: src/**/*.ts → module structure
+Text search: pattern="export (function|class|const)" → public API surface
+Text search: pattern="(app|router)\.(get|post|put|delete)" → API endpoints
+Full-file reading: CLAUDE.md → project conventions
+```

package/skills/vibe.docs/references/release.md

@@ -0,0 +1,31 @@
+# /vibe.docs release — Release Notes
+
+> vibe.docs SKILL.md 의 서브커맨드 표에서 **`release` 가 선택됐을 때만** 로드한다.
+
+### `/vibe.docs release` — Release Notes
+
+Generate release notes from git history:
+
+1. **Collect**: `git log` since last tag
+2. **Classify**: feat/fix/refactor/docs/chore from commit messages
+3. **Group**: By category with breaking changes highlighted
+4. **Format**: Semantic versioning suggestion
+
+Output: `RELEASE_NOTES.md` or append to `CHANGELOG.md`
+
+**Output format:**
+```markdown
+## [x.y.z] - YYYY-MM-DD
+
+### Breaking Changes
+- ...
+
+### Features
+- feat: description (#PR)
+
+### Bug Fixes
+- fix: description (#PR)
+
+### Other
+- refactor/docs/chore items
+```

package/skills/vibe.documentation-provider/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: vibe.documentation-provider
+description: Fetch current, authoritative library and API documentation through the best available provider. Use for external API/SDK implementation, migrations, version differences, official references, or deprecated API checks; routes between chub, Context7, and official web documentation.
+user-invocable: true
+---
+
+# Documentation Provider
+
+## Done Criteria
+
+- [ ] 사용한 provider와 조회 대상 package/API가 기록되어 있다.
+- [ ] 답변 또는 구현 근거에 문서 버전이나 조회 날짜가 포함되어 있다.
+- [ ] fallback을 사용하면 앞선 provider 실패 이유가 기록되어 있다.
+
+Select one provider and return only the documentation needed by the caller.
+
+1. Prefer chub when curated API docs or reusable annotations are available. Read `references/chub.md`.
+2. Otherwise use Context7 when its library documentation provider is available. Read `references/context7.md`.
+3. Otherwise research the official vendor documentation on the web and cite the source.
+4. Delegate retrieval through native collaboration when the result would bloat the coordinator context. Claude Code maps the worker to Task/Agent; Codex maps it to native collaboration. Inherit the session model.
+
+Never implement from training data when current documentation is required. Preserve the caller's requested library, topic, language, and output shape.

package/skills/vibe.documentation-provider/references/chub.md

@@ -0,0 +1,141 @@
+---
+name: documentation-provider-chub-reference
+invocation: [auto]
+tier: optional
+description: "Context Hub (chub) — fetch vetted, up-to-date API documentation. Write accurate code based on the latest docs instead of training data when working with external APIs/SDKs."
+triggers: [chub, context hub, API docs, latest API, deprecated API, SDK documentation, api reference, 최신 문서]
+priority: 60
+---
+
+# Context Hub (chub) Usage
+
+A skill for fetching vetted, up-to-date documentation before writing external API/SDK code.
+Solves the knowledge cutoff problem inherent in training data.
+
+## Why?
+
+| Problem | Solution |
+|---------|----------|
+| Relying on training data → using deprecated APIs | chub get → code based on vetted latest docs |
+| Web search → noisy results | chub search → curated docs only |
+| Repeating the same mistakes every session | chub annotate → accumulated learnings |
+
+## When to Use
+
+| Situation | Example |
+|-----------|---------|
+| Writing external API code | "Integrate Stripe payments" |
+| Checking latest SDK version | "Call the latest OpenAI model" |
+| Need official documentation | "Set up Supabase auth" |
+| Preventing deprecated patterns | "Firebase v10 migration" |
+
+## Workflow
+
+```
+Request to write external API/SDK code
+    ↓
+Step 0: Check if chub is installed (auto-install if not)
+    ↓
+Step 1: chub search "<library name>"
+    ↓
+Step 2: chub get <id> --lang ts
+    ↓
+Step 3: Write code based on the docs
+    ↓
+Step 4: chub annotate when a gotcha is discovered
+```
+
+## Step 0 — Auto-install
+
+**Always perform this step before running the skill.**
+
+```bash
+# 1. Check if chub exists
+which chub || command -v chub
+```
+
+If chub is not found, attempt automatic installation:
+
+```bash
+npm install -g @aisuite/chub
+```
+
+If installation fails, fall back to running via `npx @aisuite/chub`:
+
+```bash
+# search example
+npx @aisuite/chub search "stripe"
+# get example
+npx @aisuite/chub get stripe/api --lang ts
+```
+
+If `npx` also fails, fall back to context7 or Web Search (see Fallback Chain).
+
+## Usage
+
+### Step 1 — Search for docs
+
+```bash
+chub search "stripe"
+chub search "openai"
+chub search ""           # View full list
+```
+
+### Step 2 — Fetch latest docs
+
+```bash
+chub get stripe/api --lang ts
+chub get openai/chat --lang py
+chub get supabase/auth --lang js
+```
+
+### Step 3 — Write code based on the docs
+
+Write accurate code based on the fetched documentation.
+**Never rely on training data. Docs first, code second.**
+
+### Step 4 — Record learnings
+
+Gotchas, workarounds, and version issues discovered during work:
+
+```bash
+chub annotate stripe/api "pg parameter is required for Korean payments"
+chub annotate openai/chat "tool_calls in streaming comes as delta"
+chub annotate firebase/auth "getAuth() import path changed in v10"
+```
+
+Annotations are stored locally and automatically included the next time you run `chub get`.
+
+## Implementation Pattern (Delegated Worker)
+
+Delegate through the harness's native collaboration capability to prevent
+context bloat. Claude Code maps the worker to Task/Agent; Codex maps it to
+native collaboration. Inherit the session model by default:
+
+```
+Worker goal: Run `chub search <library>` then `chub get <id> --lang <lang>` to
+fetch current API documentation for [topic]. Return only relevant usage
+examples, key changes, and annotations.
+```
+
+The worker handles the chub calls and returns only a summary — keeping the coordinator context clean.
+
+## Supported APIs (1,000+)
+
+OpenAI, Anthropic, Stripe, Firebase, Supabase, Vercel, AWS S3, Cloudflare Workers, Auth0, Clerk, and more.
+
+```bash
+chub search    # Run without arguments to view the full list
+```
+
+## Fallback Chain
+
+```
+which chub fails
+    ↓
+npm install -g @aisuite/chub (auto attempt)
+    ↓
+On failure: npx @aisuite/chub <command> (temporary execution)
+    ↓
+If npx also fails: context7 or Web Search fallback
+```

package/skills/vibe.documentation-provider/references/context7.md

@@ -0,0 +1,107 @@
+---
+name: documentation-provider-context7-reference
+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: [latest version, official docs, API reference, library help, context7]
+priority: 60
+---
+
+# Context7 Usage
+
+Guide for searching latest library/framework documentation using Context7 plugin with subagent isolation.
+
+## Why Subagent Approach?
+
+| Approach | Problem |
+|----------|---------|
+| Direct plugin call | Docs content fills main context, causing bloat |
+| Subagent isolation | Docs queried in separate context, only results returned |
+
+**Benefits:**
+
+- Prevents context bloat during long coding sessions
+- Solves knowledge cutoff problem with latest docs
+- Main context stays focused on implementation
+
+## When to Use
+
+| Situation | Example |
+|-----------|---------|
+| Latest API check | "React 19 use() hook usage" |
+| Version differences | "Next.js 15 changes" |
+| Official docs needed | "Prisma schema syntax" |
+| Migration guide | "Vue 2 → Vue 3 migration" |
+
+## How It Works
+
+```
+User asks library question
+    ↓
+Skill detects docs need
+    ↓
+Delegate an isolated docs-researcher worker using the inherited session model
+    ↓
+Worker calls context7 in isolated context
+    ↓
+Returns only relevant info to main context
+```
+
+## Usage
+
+### Automatic (Recommended)
+
+Just ask library/API questions naturally:
+
+```
+"How do I use React 19 use() hook?"
+"What's new in Next.js 15?"
+"Prisma many-to-many relation syntax"
+```
+
+The skill auto-detects and delegates a docs-researcher worker.
+
+### Manual Command
+
+```
+/context7:docs <library> [query]
+```
+
+Examples:
+
+```
+/context7:docs react hooks
+/context7:docs next.js app router
+/context7:docs prisma relations
+```
+
+## Implementation Pattern
+
+When you detect a library/API documentation need, delegate through the
+harness's native collaboration capability. Claude Code maps the worker to
+Task/Agent; Codex maps it to native collaboration. Inherit the session model:
+
+```
+Worker goal: Use context7 to find [library] documentation about [topic]. Return
+only the relevant API usage examples and key points.
+```
+
+The worker handles the context7 calls and returns a summary, keeping the coordinator context clean.
+
+## Fallback Chain
+
+```
+context7 plugin not installed
+    ↓
+Prompt user: /plugin install context7
+    ↓
+If still unavailable: Web Search for official docs
+```
+
+## Installation
+
+If context7 is not installed, guide user:
+
+```bash
+/plugin install context7
+```

package/skills/vibe.educational-content/SKILL.md

@@ -6,6 +6,13 @@ user-invocable: false
 
 # Create Educational Content
 
+## Done Criteria
+
+- [ ] 각 학습 목표가 관찰 가능한 행동으로 작성되어 있다.
+- [ ] 핵심 사실에 출처 또는 저장소 근거가 연결되어 있다.
+- [ ] 연습 과제와 정답 또는 평가 기준이 존재한다.
+- [ ] 최종 산출물이 요청된 형식과 경로에 존재한다.
+
 Turn a subject into a publishable learning experience whose outcome can be observed. Design the learning before polishing the presentation.
 
 ## Set the contract

package/skills/vibe.event/SKILL.md

@@ -1,165 +1,66 @@
 ---
 name: vibe.event
-description: Community event automation — D-Day based proactive task execution
-argument-hint: '"MDC 12차 3/30" or "webinar AI에이전트 4/15" or "DWK 5차 5/20"'
+description: 커뮤니티 행사 일정·홍보·운영을 준비하거나 D-Day 기준 자동화가 필요할 때 — event 유형을 판별하고 외부 발송 전 승인을 강제한다.
+argument-hint: '"event description" | status | dashboard'
 user-invocable: true
 ---
 
 # /vibe.event
 
-Automate community event planning with D-Day based proactive execution.
+## 완료 기준
+
+- [ ] event 유형, 날짜, D-Day가 상태 파일에 기록되어 있다.
+- [ ] 선택한 planning·communications·operations 단계의 산출물이 존재한다.
+- [ ] 외부 발송은 명시적 승인 기록 없이는 실행되지 않았다.
+- [ ] 완료된 task와 남은 task 상태가 저장되어 있다.
+
+Route one event request across planning, communications, and operations without loading unrelated detail.
 
 ## Usage
 
-```
-/vibe.event "MDC 12차 3/30"                    # Parse: type=MDC, edition=12, date=3/30
-/vibe.event "webinar AI에이전트 4/15"            # Parse: type=webinar, topic=AI에이전트, date=4/15
-/vibe.event "DWK 5차 5/20 오프라인"              # Parse: type=DWK, edition=5, date=5/20, format=offline
-/vibe.event status                              # Show current event status
-/vibe.event dashboard                           # Open dashboard (localhost:8080)
+```text
+/vibe.event "MDC 12차 3/30"
+/vibe.event "webinar AI에이전트 4/15"
+/vibe.event "DWK 5차 5/20 오프라인"
+/vibe.event status
+/vibe.event dashboard
 ```
 
-## Execution Flow
+## Routing
 
-```
-1. PARSE input
-   ├── Event type: MDC / webinar / DWK
-   ├── Edition number (optional)
-   ├── Date (required)
-   ├── Topic (optional, can be set later)
-   └── Format: offline/online (DWK only, default=offline)
-
-2. CALCULATE D-Day
-   └── today - event_date = D-{n}
-
-3. LOAD or CREATE state
-   ├── Check .event_state.json
-   └── Create if new event
-
-4. DETERMINE current phase
-   ├── MDC: 11 steps (D-60 → D+2)
-   ├── Webinar: 5 steps (planning → D+1)
-   └── DWK: 9 steps (D-30 → D+3)
-
-5. AUTO-EXECUTE pending deliverables
-   ├── Content drafts → event-planner agent
-   ├── Speaker research → event-planner agent
-   ├── Image generation → event-ops agent
-   ├── SMS/email drafts → event-ops agent
-   └── Ops materials → event-ops agent
-
-6. REQUEST confirmation for send actions
-   ├── SMS actual send
-   ├── Email actual send
-   └── Notion real registration
-
-7. SAVE state
-   └── Update .event_state.json
-```
+1. Parse event type (`MDC`, `webinar`, `DWK`), edition, date, topic, and format.
+2. Load `.event_state.json` when present; update it after each completed action.
+   For the complete phase tables, parsing examples, state schema, dashboard,
+   and legacy safety contract, read `references/orchestration-legacy.md`.
+3. Select only the required reference:
+   - timeline, speakers, outreach, intro/SNS/review content → `references/planning.md`
+   - SMS, email, invitations, reminders, SNS delivery copy → `references/comms.md`
+   - nametags, checklist, slides, Slido, images, settlement → `references/operations.md`
+4. When a request crosses modes, execute planning before communications and operations, sharing the same event state and output paths.
 
-## Input Parsing Rules
-
-| Input | Parsed Result |
-|-------|---------------|
-| `MDC 12차 3/30` | type=MDC, edition=12, date=2026-03-30 |
-| `webinar AI에이전트` | type=webinar, topic=AI에이전트, date=TBD (ask) |
-| `DWK 5차 5/20 오프라인` | type=DWK, edition=5, date=2026-05-20, format=offline |
-| `status` | Show .event_state.json summary |
-| `dashboard` | Run `python output/serve.py` |
-
-## Phase-by-Phase Agent Dispatch
-
-### MDC Phases
-
-| Phase | Agents Triggered | Outputs |
-|-------|-----------------|---------|
-| D-60 | event-planner | 3 topic suggestions + speaker research |
-| D-45 | event-planner | DM + email outreach drafts |
-| D-40 | event-ops | Topic confirmation request email |
-| D-28 | event-planner, event-ops | Intro + 2 images + 3 SMS + 1 email |
-| D-30 | event-planner, event-ops | LinkedIn/Threads promo + SMS send(✅) |
-| D-14 | event-planner | LinkedIn/Threads reminder |
-| D-3 | event-ops | BCC email + SMS send(✅) |
-| D-1 | event-ops | Nametags + checklist + PPTX + SMS(✅) |
-| D-Day | event-ops | Day-of SMS(✅) |
-| D+1 | event-planner, event-ops | Review posts + settlement |
-| D+2 | — | Site update (manual) |
-
-### Webinar Phases
-
-| Phase | Agents Triggered | Outputs |
-|-------|-----------------|---------|
-| Planning | event-planner, event-ops | Intro + 3 images + SMS + email |
-| Planning | event-planner | LinkedIn/Threads promo |
-| D-4 | event-ops | Zoom(manual) + BCC email + SMS(✅) |
-| D-Day | event-ops | SMS(✅) + slides |
-| D+1 | event-planner | Review posts |
-
-### DWK Phases
-
-| Phase | Agents Triggered | Outputs |
-|-------|-----------------|---------|
-| D-30 | event-planner | 3 topics + speaker research |
-| D-25 | event-planner | DM + email outreach |
-| D-20 | event-ops | Topic confirmation email |
-| D-16 | event-planner, event-ops | Intro + 2 images + SMS + email |
-| D-15 | event-planner | LinkedIn/Threads promo |
-| D-3 | event-ops | BCC email + SMS(✅) |
-| D-1 | event-ops | Slido plan + PPTX + SNS remind(✅) |
-| D-Day | event-ops | SMS(✅) + nametags(offline) |
-| D+3 | event-planner, event-ops | Review + settlement |
-
-## State File Format
-
-```json
-{
-  "event_id": "MDC-12",
-  "type": "MDC",
-  "edition": 12,
-  "date": "2026-03-30",
-  "title": "마케팅데이터커넥트 12회",
-  "topic": "마케팅 자동화",
-  "format": "offline",
-  "speakers": [
-    {
-      "name": "김영수",
-      "company": "Company X",
-      "topic": "마케팅 데이터 파이프라인"
-    }
-  ],
-  "current_step": "D-28",
-  "completed_steps": ["D-60", "D-45", "D-40"],
-  "outputs": {
-    "D-28": ["intro.md", "thumbnail_500x500.png", "sms_notification.txt"]
-  },
-  "confirmations_pending": []
-}
-```
+Claude Code maps named event workers to Task/Agent; Codex maps them to native
+collaboration. Inherit the session model and delegate independent work only
+when it does not race on `.event_state.json` or shared output files.
 
-## Dashboard
+## Safety Gate
 
-```bash
-# Start dashboard
-python output/serve.py
-# Opens http://localhost:8080
+- Drafts, previews, test sends, and local artifacts may be produced automatically.
+- Never send SMS/email/SNS, publish content, upload, or contact a real person without explicit confirmation in the current conversation.
+- Before confirmation show recipient count, exact preview, channel, and cost estimate where applicable. Email recipients use BCC.
+- Autonomous mode never bypasses this external-state confirmation.
 
-# Features:
-# - Timeline view with D-Day progress
-# - Generate buttons per step
-# - File preview links
-# - API status (Antigravity/Aligo key validity)
-# - Dark theme with community color coding
-```
+## State and Outputs
 
-## Safety Rules
+- State: `.event_state.json`
+- Speaker history: `data/speakers/{name}.json`
+- Reports and copy: `output/reports/`
+- Images and prompts: `output/images/`
 
-```
-CRITICAL — These are absolute prohibitions:
-1. NEVER send SMS/email without explicit user confirmation
-2. ALWAYS use BCC for email (never expose attendee emails)
-3. NEVER use emoji in SMS (EUC-KR incompatible)
-4. NEVER delete files (move only)
-5. ALWAYS test SMS with testmode_yn=Y before real send
-6. NEVER register to Notion without dry_run first
-7. NEVER commit .env files
-```
+## Done
+
+- Event identity and current D-Day phase are explicit.
+- Every requested artifact exists at its documented path.
+- State reflects completed, pending, and confirmation-blocked work.
+- No external send or publish occurred without explicit approval.
+
+ARGUMENTS: $ARGUMENTS