oh-my-customcode 0.8.0 → 0.9.0

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

@@ -0,0 +1,215 @@
+---
+name: intent-detection
+description: Automatically detect user intent and route to appropriate agent
+user-invocable: false
+---
+
+## 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: lang-golang-expert
+├── Confidence: 95%
+└── Reason: "Go" keyword + "리뷰" action
+
+┌─ Agent: lang-golang-expert (sw-engineer)
+└─ Task: Code review
+```
+
+### Medium Confidence
+
+```
+[Intent Detected]
+├── Input: "백엔드 API 확인해줘"
+├── Detected: be-go-backend-expert (?)
+├── Confidence: 78%
+└── Alternatives available
+
+Select agent:
+  1. be-go-backend-expert (78%)
+  2. be-fastapi-expert (72%)
+  3. be-springboot-expert (68%)
+
+Choice [1-3, or agent name]:
+```
+
+### Override
+
+```
+[Override Detected]
+├── Input: "@lang-python-expert review api.py"
+├── Agent: lang-python-expert (explicit)
+└── Bypassing intent detection
+
+┌─ Agent: lang-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:
+.codex/skills/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/.codex/skills/intent-detection/patterns/agent-triggers.yaml

@@ -0,0 +1,349 @@
+# Agent Triggers for Intent Detection
+# Used by intent-detection skill to match user input to agents
+
+# Score weights
+weights:
+  keyword: 40
+  file_pattern: 30
+  action: 20
+  context: 10
+
+# Action verbs (both Korean and English)
+action_verbs:
+  review:
+    korean: [리뷰, 검토, 확인, 체크]
+    english: [review, check, analyze, audit]
+  create:
+    korean: [생성, 만들어, 추가]
+    english: [create, make, add, new]
+  fix:
+    korean: [수정, 고쳐, 버그, 에러]
+    english: [fix, repair, debug, solve]
+  refactor:
+    korean: [리팩토링, 개선, 정리]
+    english: [refactor, improve, clean, optimize]
+  explain:
+    korean: [설명, 알려줘, 뭐야]
+    english: [explain, what, how, why]
+
+# Agent definitions
+agents:
+  # SW Engineers - Language
+  lang-golang-expert:
+    keywords:
+      korean: [고, 고랭, "go 언어"]
+      english: [go, golang]
+    file_patterns: ["*.go", "go.mod", "go.sum"]
+    supported_actions: [review, fix, refactor, explain]
+    base_confidence: 40
+
+  lang-python-expert:
+    keywords:
+      korean: [파이썬, 파이선]
+      english: [python, py]
+    file_patterns: ["*.py", "requirements.txt", "pyproject.toml", "setup.py", "Pipfile"]
+    supported_actions: [review, fix, refactor, explain]
+    base_confidence: 40
+
+  lang-rust-expert:
+    keywords:
+      korean: [러스트]
+      english: [rust, rs]
+    file_patterns: ["*.rs", "Cargo.toml", "Cargo.lock"]
+    supported_actions: [review, fix, refactor, explain]
+    base_confidence: 40
+
+  lang-kotlin-expert:
+    keywords:
+      korean: [코틀린]
+      english: [kotlin, kt]
+    file_patterns: ["*.kt", "*.kts", "build.gradle.kts"]
+    supported_actions: [review, fix, refactor, explain]
+    base_confidence: 40
+
+  lang-typescript-expert:
+    keywords:
+      korean: [타입스크립트]
+      english: [typescript, ts]
+    file_patterns: ["*.ts", "*.tsx", "tsconfig.json"]
+    supported_actions: [review, fix, refactor, explain]
+    base_confidence: 40
+
+  lang-java21-expert:
+    keywords:
+      korean: [자바, 자바21]
+      english: [java, java21, jdk21, jdk]
+    file_patterns: ["*.java", "pom.xml", "build.gradle"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  # SW Engineers - Frontend
+  fe-vercel-agent:
+    keywords:
+      korean: [리액트, 버셀, 넥스트]
+      english: [react, vercel, next, nextjs]
+    file_patterns: ["*.jsx", "*.tsx", "next.config.*", "vercel.json"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 40
+
+  fe-vuejs-agent:
+    keywords:
+      korean: [뷰, 뷰제이에스, 피니아]
+      english: [vue, vuejs, "vue.js", vue3, pinia, "vue router"]
+    file_patterns: ["*.vue", "vite.config.*", "vue.config.*"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 40
+
+  fe-svelte-agent:
+    keywords:
+      korean: [스벨트, 스벨트킷]
+      english: [svelte, sveltekit, "svelte kit"]
+    file_patterns: ["*.svelte", "svelte.config.*"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 40
+
+  # SW Engineers - Backend
+  be-fastapi-expert:
+    keywords:
+      korean: [패스트에이피아이, 패스트api]
+      english: [fastapi, starlette]
+    file_patterns: ["main.py", "app.py", "routers/*.py"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  be-springboot-expert:
+    keywords:
+      korean: [스프링, 스프링부트]
+      english: [spring, springboot, "spring boot", java]
+    file_patterns: ["*.java", "pom.xml", "build.gradle", "application.yml", "application.properties"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  be-go-backend-expert:
+    keywords:
+      korean: [고 백엔드, "go 백엔드", "go api"]
+      english: ["go backend", "go api", gin, echo, fiber]
+    file_patterns: ["*.go", "go.mod"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  # SW Engineers - Backend (continued)
+  be-express-expert:
+    keywords:
+      korean: [익스프레스, 노드]
+      english: [express, expressjs, "express.js", node]
+    file_patterns: ["*.js", "*.ts", "package.json", "app.js", "server.js"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  be-nestjs-expert:
+    keywords:
+      korean: [네스트, 네스트제이에스]
+      english: [nestjs, nest, "nest.js"]
+    file_patterns: ["*.ts", "nest-cli.json", "*.module.ts", "*.controller.ts"]
+    supported_actions: [review, create, fix, refactor]
+    base_confidence: 35
+
+  # SW Engineers - Tooling
+  tool-bun-expert:
+    keywords:
+      korean: [번, 번런타임]
+      english: [bun, bunx, "bun.js", bunfig]
+    file_patterns: ["bunfig.toml", "bun.lockb", "*.bun.ts"]
+    supported_actions: [build, test, run, migrate, review]
+    base_confidence: 40
+
+  tool-npm-expert:
+    keywords:
+      korean: [npm, 패키지, 배포, 퍼블리시]
+      english: [npm, publish, package, registry, version]
+    file_patterns: ["package.json", ".npmrc", ".npmignore"]
+    supported_actions: [publish, version, audit, pack]
+    base_confidence: 40
+
+  tool-optimizer:
+    keywords:
+      korean: [최적화, 번들, 성능, 트리쉐이킹]
+      english: [optimize, bundle, performance, "tree-shaking", "dead code"]
+    file_patterns: []
+    supported_actions: [analyze, optimize, report, bundle]
+    base_confidence: 40
+
+  # SW Engineers - Database
+  db-supabase-expert:
+    keywords:
+      korean: [수퍼베이스, 수파베이스]
+      english: [supabase, postgres, postgresql]
+    file_patterns: ["*.sql", "supabase/*"]
+    supported_actions: [review, create, fix, migrate]
+    base_confidence: 40
+
+  # SW Architects
+  arch-documenter:
+    keywords:
+      korean: [문서, 설명서, 리드미]
+      english: [document, docs, readme, documentation]
+    file_patterns: ["*.md", "README*", "CHANGELOG*"]
+    supported_actions: [create, review]
+    base_confidence: 35
+
+  arch-speckit-agent:
+    keywords:
+      korean: [스펙, 명세, 스펙키트]
+      english: [spec, specification, speckit, design]
+    file_patterns: ["*.spec.md", "*.spec.yaml", "specs/*"]
+    supported_actions: [spec, design, document]
+    base_confidence: 40
+
+  # Infra Engineers
+  infra-docker-expert:
+    keywords:
+      korean: [도커, 컨테이너]
+      english: [docker, container, dockerfile]
+    file_patterns: ["Dockerfile", "docker-compose.yml", "docker-compose.yaml", ".dockerignore"]
+    supported_actions: [review, create, fix, explain]
+    base_confidence: 40
+
+  infra-aws-expert:
+    keywords:
+      korean: [에이더블유에스, 아마존, 클라우드]
+      english: [aws, amazon, cloud, s3, ec2, lambda, ecs, eks]
+    file_patterns: ["*.tf", "serverless.yml", "template.yaml", "cloudformation.*"]
+    supported_actions: [review, create, fix, explain]
+    base_confidence: 40
+
+  # Managers
+  mgr-creator:
+    keywords:
+      korean: [에이전트 생성, 에이전트 만들어]
+      english: ["create agent", "new agent"]
+    file_patterns: []
+    supported_actions: [create]
+    base_confidence: 50
+
+  mgr-updater:
+    keywords:
+      korean: [업데이트, 동기화]
+      english: [update, sync]
+    file_patterns: []
+    supported_actions: [review, fix]
+    base_confidence: 50
+
+  mgr-supplier:
+    keywords:
+      korean: [검사, 의존성, 감사]
+      english: [audit, check, dependency, validate]
+    file_patterns: []
+    supported_actions: [review]
+    base_confidence: 50
+
+  # QA Team
+  qa-planner:
+    keywords:
+      korean: [테스트 계획, QA 계획, 테스트 전략]
+      english: ["test plan", "qa plan", "test strategy", "test scenarios"]
+    file_patterns: []
+    supported_actions: [plan, scenarios, criteria]
+    base_confidence: 40
+
+  qa-writer:
+    keywords:
+      korean: [테스트 케이스, 테스트 문서, 테스트 리포트]
+      english: ["test case", "test documentation", "test report", "qa documentation"]
+    file_patterns: []
+    supported_actions: [write, report, template]
+    base_confidence: 40
+
+  qa-engineer:
+    keywords:
+      korean: [테스트 실행, 테스트 수행, 회귀 테스트, 자동화 테스트]
+      english: ["run tests", "execute tests", "regression", "automate test", "verify fix"]
+    file_patterns: ["*_test.*", "*.spec.*", "test_*.*"]
+    supported_actions: [execute, verify, automate, regress]
+    base_confidence: 40
+
+  # QA Lead (Orchestrator)
+  qa-lead:
+    keywords:
+      korean: [품질 리드, QA 리드, 테스트 조율]
+      english: ["qa lead", "quality lead", "test coordination"]
+    file_patterns: []
+    supported_actions: [coordinate, review, lead]
+    base_confidence: 40
+
+  # System Agents
+  sys-naggy:
+    keywords:
+      korean: [할일, 태스크, 리마인드, 알림]
+      english: [todo, task, remind, reminder]
+    file_patterns: []
+    supported_actions: [list, add, done, complete, priority, remind]
+    base_confidence: 40
+
+  sys-memory-keeper:
+    keywords:
+      korean: [메모리, 기억, 저장, 회상]
+      english: [memory, remember, recall, save]
+    file_patterns: []
+    supported_actions: [save, recall, remember]
+    base_confidence: 40
+
+  # Managers (continued)
+  mgr-gitnerd:
+    keywords:
+      korean: [커밋, 브랜치, 푸시, 풀, 머지, 리베이스]
+      english: [git, commit, branch, pr, push, pull, merge, rebase]
+    file_patterns: [".gitignore", ".gitattributes"]
+    supported_actions: [commit, branch, pr, sync, status, push, pull, merge]
+    base_confidence: 40
+
+  mgr-sync-checker:
+    keywords:
+      korean: [동기화, 싱크, 검증]
+      english: [sync, synchronization, check, verify]
+    file_patterns: ["index.yaml", "AGENTS.md", "COMMANDS.md"]
+    supported_actions: [check, agents, commands, docs, fix]
+    base_confidence: 40
+
+  mgr-sauron:
+    keywords:
+      korean: [검증, 전체검증, 무결성, 사우론]
+      english: [verify, verification, sauron, "full check", "system integrity", "r017"]
+    file_patterns: []
+    supported_actions: [watch, quick, report, verify]
+    base_confidence: 40
+
+  mgr-claude-code-bible:
+    keywords:
+      korean: [공식문서, 바이블, 클로드코드 문서]
+      english: ["claude code docs", "official docs", bible, "code.codex.com", "native verification"]
+    file_patterns: []
+    supported_actions: [fetch, verify, check]
+    base_confidence: 40
+
+  # Master
+  planner:
+    keywords:
+      korean: [계획, 설계, 전략, 아키텍처]
+      english: [plan, architect, strategy, design]
+    file_patterns: []
+    supported_actions: [plan, design, architect]
+    base_confidence: 40
+
+  # Orchestrators
+  dev-lead:
+    keywords:
+      korean: [조율, 리뷰, 리드, 개발리드]
+      english: [lead, coordinate, review, "dev lead"]
+    file_patterns: []
+    supported_actions: [coordinate, review, lead]
+    base_confidence: 40
+
+  secretary:
+    keywords:
+      korean: [에이전트, 관리, 오케스트레이션]
+      english: [manage, agent, orchestrate]
+    file_patterns: []
+    supported_actions: [manage, create, coordinate]
+    base_confidence: 40
+

package/templates/.codex/skills/kafka-best-practices/SKILL.md

@@ -0,0 +1,52 @@
+---
+name: kafka-best-practices
+description: Apache Kafka best practices for event streaming, topic design, and producer-consumer patterns
+user-invocable: false
+---
+
+# Apache Kafka Best Practices
+
+## Producer Patterns
+
+### Idempotent Producer (CRITICAL)
+- Enable `enable.idempotence=true`
+- Prevents duplicate messages
+- Requires `acks=all`, `retries > 0`, `max.in.flight.requests.per.connection <= 5`
+
+### Exactly-Once Semantics
+- Use transactional API: `initTransactions()`, `beginTransaction()`, `commitTransaction()`
+- For exactly-once end-to-end processing
+
+### Performance
+- Batching: `linger.ms` (wait for batch to fill)
+- Compression: `compression.type=snappy` or `lz4`
+- `batch.size`: 16KB default, tune based on message size
+
+## Consumer Patterns
+
+### Offset Management
+- Auto-commit: `enable.auto.commit=true` (at-least-once)
+- Manual commit: `commitSync()` or `commitAsync()` (better control)
+
+### Rebalancing
+- Cooperative sticky assignor: minimal rebalancing disruption
+- `session.timeout.ms` and `heartbeat.interval.ms` tuning
+
+### At-Least-Once vs Exactly-Once
+- At-least-once: default, idempotent processing required
+- Exactly-once: transactional consumer + producer
+
+## Topic Design
+
+### Partitioning
+- Partition count: based on throughput (MB/s ÷ partition throughput)
+- Key-based partitioning for ordering guarantees
+- More partitions = higher throughput (but more overhead)
+
+### Retention
+- Time-based: `retention.ms`
+- Size-based: `retention.bytes`
+- Log compaction: for changelog topics (`cleanup.policy=compact`)
+
+## References
+- [Kafka Documentation](https://kafka.apache.org/documentation/)