oh-my-customcode 0.1.0

package/templates/skills/infrastructure/docker-best-practices/SKILL.md

@@ -0,0 +1,274 @@
+# Docker Best Practices Skill
+
+> **Category**: Infrastructure
+> **Source**: Internal (based on Docker Official Documentation)
+
+## Purpose
+
+Apply Docker patterns for building optimized and secure container images.
+
+## Rules
+
+### 1. Layer Optimization
+
+```yaml
+principles:
+  - Combine related RUN commands
+  - Sort multi-line arguments alphabetically
+  - Clean up in same layer
+
+patterns: |
+  # GOOD: Single layer, clean cache
+  RUN apt-get update && apt-get install -y \
+      curl \
+      git \
+      vim \
+      && rm -rf /var/lib/apt/lists/*
+
+  # BAD: Multiple layers, cache remains
+  RUN apt-get update
+  RUN apt-get install -y curl
+  RUN apt-get install -y git
+```
+
+### 2. Multi-Stage Builds
+
+```yaml
+purpose:
+  - Reduce final image size
+  - Separate build and runtime dependencies
+  - Security (no build tools in production)
+
+pattern: |
+  # Build stage
+  FROM golang:1.21 AS builder
+  WORKDIR /app
+  COPY go.mod go.sum ./
+  RUN go mod download
+  COPY . .
+  RUN CGO_ENABLED=0 go build -o /app/server ./cmd/server
+
+  # Runtime stage
+  FROM gcr.io/distroless/static:nonroot
+  COPY --from=builder /app/server /server
+  USER nonroot:nonroot
+  ENTRYPOINT ["/server"]
+```
+
+### 3. Security
+
+```yaml
+principles:
+  - Run as non-root user
+  - Pin base image versions
+  - Use minimal base images
+  - Don't store secrets in images
+
+patterns: |
+  # Pin version with digest
+  FROM node:20-slim@sha256:abc123...
+
+  # Create non-root user
+  RUN groupadd -r appgroup && useradd -r -g appgroup appuser
+  USER appuser
+
+  # Use secrets mount (BuildKit)
+  RUN --mount=type=secret,id=npmrc,target=/root/.npmrc \
+      npm install
+
+  # .dockerignore for secrets
+  # .env
+  # *.pem
+  # credentials.json
+```
+
+### 4. Image Size Reduction
+
+```yaml
+strategies:
+  - Use slim/alpine base images
+  - Remove build dependencies
+  - Use .dockerignore
+  - Multi-stage builds
+
+minimal_bases:
+  distroless: "gcr.io/distroless/static"
+  alpine: "alpine:3.19"
+  slim: "debian:12-slim"
+
+patterns: |
+  # Alpine for size
+  FROM python:3.12-alpine
+  RUN apk add --no-cache gcc musl-dev
+
+  # Distroless for security
+  FROM gcr.io/distroless/python3
+  COPY --from=builder /app /app
+```
+
+### 5. Cache Optimization
+
+```yaml
+principles:
+  - Order from least to most frequently changing
+  - Copy dependency files first
+  - Use BuildKit cache mounts
+
+patterns: |
+  # Copy dependency files first
+  COPY package.json package-lock.json ./
+  RUN npm ci
+
+  # Then copy source (changes frequently)
+  COPY . .
+  RUN npm run build
+
+  # BuildKit cache mount
+  RUN --mount=type=cache,target=/root/.cache/pip \
+      pip install -r requirements.txt
+```
+
+### 6. ENTRYPOINT vs CMD
+
+```yaml
+entrypoint:
+  purpose: Main executable
+  form: exec form ["executable"]
+
+cmd:
+  purpose: Default arguments
+  form: exec form ["arg1", "arg2"]
+
+patterns: |
+  # Fixed command with variable args
+  ENTRYPOINT ["python", "app.py"]
+  CMD ["--port", "8080"]
+
+  # docker run myapp --port 3000
+  # Executes: python app.py --port 3000
+
+  # Flexible command
+  CMD ["python", "app.py"]
+
+  # docker run myapp bash
+  # Executes: bash
+```
+
+### 7. Health Checks
+
+```yaml
+purpose: Container health monitoring
+interval: how often to check
+timeout: max time for check
+retries: failures before unhealthy
+
+pattern: |
+  HEALTHCHECK --interval=30s --timeout=3s --retries=3 \
+      CMD curl -f http://localhost:8080/health || exit 1
+```
+
+### 8. Docker Compose
+
+```yaml
+best_practices:
+  - Use named volumes
+  - Define networks explicitly
+  - Use environment files
+  - Set resource limits
+
+pattern: |
+  version: "3.8"
+
+  services:
+    app:
+      build:
+        context: .
+        target: production
+      environment:
+        - DATABASE_URL
+      env_file:
+        - .env
+      ports:
+        - "8080:8080"
+      depends_on:
+        db:
+          condition: service_healthy
+      deploy:
+        resources:
+          limits:
+            cpus: "1"
+            memory: 512M
+      networks:
+        - backend
+
+    db:
+      image: postgres:16-alpine
+      volumes:
+        - postgres_data:/var/lib/postgresql/data
+      healthcheck:
+        test: ["CMD-SHELL", "pg_isready -U postgres"]
+        interval: 10s
+        timeout: 5s
+        retries: 5
+      networks:
+        - backend
+
+  volumes:
+    postgres_data:
+
+  networks:
+    backend:
+```
+
+### 9. Common Patterns by Language
+
+```yaml
+nodejs: |
+  FROM node:20-slim AS builder
+  WORKDIR /app
+  COPY package*.json ./
+  RUN npm ci --only=production
+
+  FROM gcr.io/distroless/nodejs20
+  WORKDIR /app
+  COPY --from=builder /app/node_modules ./node_modules
+  COPY . .
+  CMD ["server.js"]
+
+python: |
+  FROM python:3.12-slim AS builder
+  WORKDIR /app
+  RUN pip install --user -r requirements.txt
+
+  FROM python:3.12-slim
+  WORKDIR /app
+  COPY --from=builder /root/.local /root/.local
+  COPY . .
+  ENV PATH=/root/.local/bin:$PATH
+  CMD ["python", "app.py"]
+
+go: |
+  FROM golang:1.21 AS builder
+  WORKDIR /app
+  COPY go.* ./
+  RUN go mod download
+  COPY . .
+  RUN CGO_ENABLED=0 go build -o /server
+
+  FROM scratch
+  COPY --from=builder /server /server
+  ENTRYPOINT ["/server"]
+```
+
+## Application
+
+When writing Dockerfiles:
+
+1. **Always** use multi-stage builds
+2. **Always** run as non-root user
+3. **Always** pin base image versions
+4. **Prefer** minimal base images
+5. **Order** layers for cache efficiency
+6. **Clean** package caches in same layer
+7. **Use** .dockerignore
+8. **Add** health checks

package/templates/skills/infrastructure/docker-best-practices/index.yaml

@@ -0,0 +1,26 @@
+# Docker Best Practices Skill
+
+metadata:
+  name: docker-best-practices
+  category: infrastructure
+  description: Docker patterns for optimized containerization
+
+source:
+  type: internal
+  reference:
+    - https://docs.docker.com/
+    - https://docs.docker.com/develop/develop-images/dockerfile_best-practices/
+    - https://docs.docker.com/compose/compose-file/best-practices/
+
+provides:
+  - Layer optimization
+  - Multi-stage builds
+  - Security best practices
+  - Image size reduction
+  - Cache optimization
+  - ENTRYPOINT vs CMD
+  - Health checks
+  - Docker Compose patterns
+
+used_by:
+  - docker-expert

package/templates/skills/orchestration/intent-detection/SKILL.md

@@ -0,0 +1,214 @@
+# Intent Detection Skill
+
+> **Category**: Orchestration
+> **Source**: Internal
+
+## Purpose
+
+Automatically detect user intent and route to the appropriate agent with full transparency.
+
+## Detection Algorithm
+
+### 1. Input Analysis
+
+```
+User Input: "Go 코드 리뷰해줘"
+            │
+            ▼
+┌─────────────────────────────┐
+│  Tokenize & Extract         │
+├─────────────────────────────┤
+│  Keywords: ["Go"]           │
+│  Actions: ["리뷰"]          │
+│  File refs: []              │
+│  Context: []                │
+└─────────────────────────────┘
+```
+
+### 2. Pattern Matching
+
+Match extracted tokens against agent triggers:
+
+```yaml
+# For each agent in agent-triggers.yaml
+match_score = 0
+
+# Keyword match
+for keyword in user_keywords:
+  if keyword in agent.keywords:
+    match_score += agent.keyword_weight (default: 40)
+
+# Action match
+for action in user_actions:
+  if action in agent.actions:
+    match_score += agent.action_weight (default: 40)
+
+# File pattern match
+for pattern in user_file_refs:
+  if matches(pattern, agent.file_patterns):
+    match_score += agent.file_weight (default: 30)
+
+# Context bonus
+if agent == recent_agent:
+  match_score += context_bonus (default: 10)
+```
+
+### 3. Confidence Calculation
+
+```
+confidence = min(100, match_score)
+```
+
+### 4. Decision
+
+```
+if confidence >= 90:
+    auto_execute()
+elif confidence >= 70:
+    request_confirmation()
+else:
+    list_options()
+```
+
+## Detection Patterns
+
+### Keyword Patterns
+
+```yaml
+# Korean keywords
+korean:
+  - "고" → go
+  - "파이썬" → python
+  - "러스트" → rust
+  - "타입스크립트" → typescript
+
+# Action verbs (Korean)
+actions_kr:
+  - "리뷰" → review
+  - "분석" → analyze
+  - "수정" → fix
+  - "생성" → create
+  - "만들어" → create
+  - "확인" → check
+```
+
+### File Pattern Matching
+
+```yaml
+patterns:
+  go: ["*.go", "go.mod", "go.sum"]
+  python: ["*.py", "requirements.txt", "pyproject.toml", "setup.py"]
+  rust: ["*.rs", "Cargo.toml"]
+  typescript: ["*.ts", "*.tsx", "tsconfig.json"]
+  kotlin: ["*.kt", "*.kts", "build.gradle.kts"]
+```
+
+## Output Format
+
+### High Confidence
+
+```
+[Intent Detected]
+├── Input: "Go 코드 리뷰해줘"
+├── Agent: golang-expert
+├── Confidence: 95%
+└── Reason: "Go" keyword + "리뷰" action
+
+┌─ Agent: golang-expert (sw-engineer)
+└─ Task: Code review
+```
+
+### Medium Confidence
+
+```
+[Intent Detected]
+├── Input: "백엔드 API 확인해줘"
+├── Detected: go-backend-expert (?)
+├── Confidence: 78%
+└── Alternatives available
+
+Select agent:
+  1. go-backend-expert (78%)
+  2. fastapi-expert (72%)
+  3. springboot-expert (68%)
+
+Choice [1-3, or agent name]:
+```
+
+### Override
+
+```
+[Override Detected]
+├── Input: "@python-expert review api.py"
+├── Agent: python-expert (explicit)
+└── Bypassing intent detection
+
+┌─ Agent: python-expert (sw-engineer)
+└─ Task: Review api.py
+```
+
+## Integration
+
+### With Secretary
+
+```
+Secretary uses this skill to:
+1. Parse incoming user requests
+2. Detect intent and select agent
+3. Display reasoning
+4. Handle confirmations
+5. Route to selected agent
+```
+
+### With Agent Triggers
+
+```
+Load triggers from:
+skills/orchestration/intent-detection/patterns/agent-triggers.yaml
+
+Each agent defines:
+- keywords (language names, tech terms)
+- file_patterns (extensions, config files)
+- actions (supported actions)
+- weights (scoring factors)
+```
+
+## Error Handling
+
+### No Match
+
+```
+[Intent Unclear]
+├── Input: "도와줘"
+├── Confidence: < 30%
+└── Too generic to detect intent
+
+How can I help? Please be more specific:
+- What type of task? (review, create, fix, ...)
+- What language/technology? (Go, Python, ...)
+- What file or project?
+```
+
+### Ambiguous Match
+
+```
+[Intent Ambiguous]
+├── Input: "코드 리뷰"
+├── Top matches:
+│   └── All experts: ~50% each
+└── Need file context or language hint
+
+Specify the language or provide a file path.
+```
+
+## Configuration
+
+```yaml
+intent_detection:
+  enabled: true
+  auto_execute_threshold: 90
+  confirm_threshold: 70
+  show_reasoning: true
+  max_alternatives: 3
+  korean_support: true
+```

package/templates/skills/orchestration/intent-detection/index.yaml

@@ -0,0 +1,30 @@
+# Intent Detection Skill
+
+metadata:
+  name: intent-detection
+  category: orchestration
+  description: Automatically detect user intent and route to appropriate agent
+
+source:
+  type: internal
+
+provides:
+  - Keyword extraction from user input
+  - Action verb detection (Korean + English)
+  - File pattern matching
+  - Agent matching with confidence scores
+  - Transparent reasoning display
+  - Override support (@agent syntax)
+
+patterns:
+  location: ./patterns/agent-triggers.yaml
+
+thresholds:
+  auto_execute: 90
+  confirm: 70
+  unclear: 30
+
+used_by:
+  - secretary
+
+rule: R015