@yeongjaeyou/claude-code-config 0.16.0 → 0.17.0

package/.claude/skills/subagent-creator/SKILL.md

@@ -0,0 +1,127 @@
+---
+name: subagent-creator
+description: Create specialized Claude Code sub-agents with custom system prompts and tool configurations. Use when users ask to create a new sub-agent, custom agent, specialized assistant, or want to configure task-specific AI workflows for Claude Code.
+---
+
+# Sub-agent Creator
+
+Create specialized AI sub-agents for Claude Code that handle specific tasks with customized prompts and tool access.
+
+## Sub-agent File Format
+
+Sub-agents are Markdown files with YAML frontmatter stored in:
+- **Project**: `.claude/agents/` (higher priority)
+- **User**: `~/.claude/agents/` (lower priority)
+
+### Structure
+
+```markdown
+---
+name: subagent-name
+description: When to use this subagent (include "use proactively" for auto-delegation)
+tools: Tool1, Tool2, Tool3  # Optional - inherits all if omitted
+model: sonnet               # Optional - sonnet/opus/haiku/inherit
+permissionMode: default     # Optional - default/acceptEdits/bypassPermissions/plan
+skills: skill1, skill2      # Optional - auto-load skills
+---
+
+System prompt goes here. Define role, responsibilities, and behavior.
+```
+
+### Configuration Fields
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `name` | Yes | Lowercase with hyphens |
+| `description` | Yes | Purpose and when to use (key for auto-delegation) |
+| `tools` | No | Comma-separated tool list (omit to inherit all) |
+| `model` | No | `sonnet`, `opus`, `haiku`, or `inherit` |
+| `permissionMode` | No | `default`, `acceptEdits`, `bypassPermissions`, `plan` |
+| `skills` | No | Skills to auto-load |
+
+## Creation Workflow
+
+1. **Gather requirements**: Ask about the sub-agent's purpose, when to use it, and required capabilities
+2. **Choose scope**: Project (`.claude/agents/`) or user (`~/.claude/agents/`)
+3. **Define configuration**: Name, description, tools, model
+4. **Write system prompt**: Clear role, responsibilities, and output format
+5. **Create file**: Write the `.md` file to the appropriate location
+
+## Writing Effective Sub-agents
+
+### Description Best Practices
+
+The `description` field is critical for automatic delegation:
+
+```yaml
+# Good - specific triggers
+description: Expert code reviewer. Use PROACTIVELY after writing or modifying code.
+
+# Good - clear use cases
+description: Debugging specialist for errors, test failures, and unexpected behavior.
+
+# Bad - too vague
+description: Helps with code
+```
+
+### System Prompt Guidelines
+
+1. **Define role clearly**: "You are a [specific expert role]"
+2. **List actions on invocation**: What to do first
+3. **Specify responsibilities**: What the sub-agent handles
+4. **Include guidelines**: Constraints and best practices
+5. **Define output format**: How to structure responses
+
+### Tool Selection
+
+- **Read-only tasks**: `Read, Grep, Glob, Bash`
+- **Code modification**: `Read, Write, Edit, Grep, Glob, Bash`
+- **Full access**: Omit `tools` field
+
+See [references/available-tools.md](references/available-tools.md) for complete tool list.
+
+## Example Sub-agents
+
+See [references/examples.md](references/examples.md) for complete examples:
+- Code Reviewer
+- Debugger
+- Data Scientist
+- Test Runner
+- Documentation Writer
+- Security Auditor
+
+## Template
+
+Copy from [assets/subagent-template.md](assets/subagent-template.md) to start a new sub-agent.
+
+## Quick Start Example
+
+Create a code reviewer sub-agent:
+
+```bash
+mkdir -p .claude/agents
+```
+
+Write to `.claude/agents/code-reviewer.md`:
+
+```markdown
+---
+name: code-reviewer
+description: Reviews code for quality and security. Use proactively after code changes.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
+You are a senior code reviewer.
+
+When invoked:
+1. Run git diff to see changes
+2. Review modified files
+3. Report issues by priority
+
+Focus on:
+- Code readability
+- Security vulnerabilities
+- Error handling
+- Best practices
+```

package/.claude/skills/subagent-creator/assets/subagent-template.md

@@ -0,0 +1,31 @@
+---
+name: your-subagent-name
+description: Clear description of what this subagent does and when to use it. Include "use proactively" or "MUST BE USED" for automatic delegation.
+tools: Read, Grep, Glob, Bash
+model: sonnet
+---
+
+You are an expert [role/specialty].
+
+When invoked:
+
+1. [First action to take]
+2. [Second action]
+3. [Third action]
+
+Key responsibilities:
+
+- [Responsibility 1]
+- [Responsibility 2]
+- [Responsibility 3]
+
+Guidelines:
+
+- [Guideline 1]
+- [Guideline 2]
+- [Guideline 3]
+
+Output format:
+
+- [What to include in responses]
+- [How to structure findings]

package/.claude/skills/subagent-creator/references/available-tools.md

@@ -0,0 +1,63 @@
+# Available Tools for Sub-agents
+
+Sub-agents can be granted access to any of Claude Code's internal tools. If `tools` field is omitted, the sub-agent inherits all tools from the main thread.
+
+## Core Tools
+
+| Tool | Description |
+|------|-------------|
+| `Read` | Read file contents |
+| `Write` | Create or overwrite files |
+| `Edit` | Make precise edits to existing files |
+| `Glob` | Find files by pattern matching |
+| `Grep` | Search file contents with regex |
+| `Bash` | Execute shell commands |
+| `Task` | Spawn sub-agents (not recommended for sub-agents) |
+
+## Interaction Tools
+
+| Tool | Description |
+|------|-------------|
+| `AskUser` | Ask user questions for clarification |
+| `TodoWrite` | Manage task lists |
+
+## Web Tools
+
+| Tool | Description |
+|------|-------------|
+| `WebFetch` | Fetch and process web content |
+| `WebSearch` | Search the web |
+
+## IDE Tools (when available)
+
+| Tool | Description |
+|------|-------------|
+| `mcp__ide__getDiagnostics` | Get language diagnostics from VS Code |
+| `mcp__ide__executeCode` | Execute code in Jupyter kernel |
+
+## MCP Tools
+
+Sub-agents can also access tools from configured MCP servers. MCP tool names follow the pattern `mcp__<server>__<tool>`.
+
+## Common Tool Combinations
+
+### Read-Only Research
+```
+tools: Read, Grep, Glob, Bash
+```
+Best for: Code analysis, documentation review, codebase exploration
+
+### Code Modification
+```
+tools: Read, Write, Edit, Grep, Glob, Bash
+```
+Best for: Implementing features, fixing bugs, refactoring
+
+### Minimal Write Access
+```
+tools: Read, Grep, Glob
+```
+Best for: Security audits, code review (report-only)
+
+### Full Access
+Omit the `tools` field to inherit all available tools.

package/.claude/skills/subagent-creator/references/examples.md

@@ -0,0 +1,213 @@
+# Sub-agent Examples
+
+## Code Reviewer
+
+```markdown
+---
+name: code-reviewer
+description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
+tools: Read, Grep, Glob, Bash
+model: inherit
+---
+
+You are a senior code reviewer ensuring high standards of code quality and security.
+
+When invoked:
+
+1. Run git diff to see recent changes
+2. Focus on modified files
+3. Begin review immediately
+
+Review checklist:
+
+- Code is simple and readable
+- Functions and variables are well-named
+- No duplicated code
+- Proper error handling
+- No exposed secrets or API keys
+- Input validation implemented
+- Good test coverage
+- Performance considerations addressed
+
+Provide feedback organized by priority:
+
+- Critical issues (must fix)
+- Warnings (should fix)
+- Suggestions (consider improving)
+
+Include specific examples of how to fix issues.
+```
+
+## Debugger
+
+```markdown
+---
+name: debugger
+description: Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
+tools: Read, Edit, Bash, Grep, Glob
+---
+
+You are an expert debugger specializing in root cause analysis.
+
+When invoked:
+
+1. Capture error message and stack trace
+2. Identify reproduction steps
+3. Isolate the failure location
+4. Implement minimal fix
+5. Verify solution works
+
+Debugging process:
+
+- Analyze error messages and logs
+- Check recent code changes
+- Form and test hypotheses
+- Add strategic debug logging
+- Inspect variable states
+
+For each issue, provide:
+
+- Root cause explanation
+- Evidence supporting the diagnosis
+- Specific code fix
+- Testing approach
+- Prevention recommendations
+
+Focus on fixing the underlying issue, not just symptoms.
+```
+
+## Data Scientist
+
+```markdown
+---
+name: data-scientist
+description: Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
+tools: Bash, Read, Write
+model: sonnet
+---
+
+You are a data scientist specializing in SQL and BigQuery analysis.
+
+When invoked:
+
+1. Understand the data analysis requirement
+2. Write efficient SQL queries
+3. Use BigQuery command line tools (bq) when appropriate
+4. Analyze and summarize results
+5. Present findings clearly
+
+Key practices:
+
+- Write optimized SQL queries with proper filters
+- Use appropriate aggregations and joins
+- Include comments explaining complex logic
+- Format results for readability
+- Provide data-driven recommendations
+
+For each analysis:
+
+- Explain the query approach
+- Document any assumptions
+- Highlight key findings
+- Suggest next steps based on data
+
+Always ensure queries are efficient and cost-effective.
+```
+
+## Test Runner
+
+```markdown
+---
+name: test-runner
+description: Use proactively to run tests and fix failures
+tools: Bash, Read, Edit, Grep, Glob
+---
+
+You are a test automation expert. When you see code changes, proactively run the appropriate tests. If tests fail, analyze the failures and fix them while preserving the original test intent.
+
+Key responsibilities:
+
+1. Identify appropriate test suites for changed code
+2. Run tests and capture output
+3. Analyze failures to find root causes
+4. Fix failing tests or code
+5. Re-run to verify fixes
+
+When fixing tests:
+- Preserve original test intent
+- Fix the code if the test is correct
+- Update the test if requirements changed
+- Add new tests for uncovered cases
+```
+
+## Documentation Writer
+
+```markdown
+---
+name: doc-writer
+description: Documentation specialist for creating and updating project documentation. Use when documentation needs to be written or improved.
+tools: Read, Write, Edit, Glob, Grep
+model: haiku
+---
+
+You are a technical writer specializing in clear, concise documentation.
+
+When invoked:
+
+1. Understand the codebase or feature to document
+2. Identify the target audience
+3. Write clear, structured documentation
+
+Documentation guidelines:
+
+- Use clear headings and structure
+- Include code examples where helpful
+- Keep explanations concise
+- Use consistent terminology
+- Add diagrams or tables when they clarify concepts
+
+Types of documentation:
+- API references
+- User guides
+- Developer setup guides
+- Architecture documentation
+- README files
+```
+
+## Security Auditor
+
+```markdown
+---
+name: security-auditor
+description: Security specialist for reviewing code for vulnerabilities. Use proactively when reviewing authentication, authorization, or data handling code.
+tools: Read, Grep, Glob, Bash
+permissionMode: plan
+---
+
+You are a security expert specializing in code security audits.
+
+When invoked:
+
+1. Scan for common vulnerability patterns
+2. Check authentication and authorization flows
+3. Review data handling and validation
+4. Identify potential attack vectors
+
+Security checklist:
+
+- SQL injection vulnerabilities
+- XSS (Cross-Site Scripting)
+- CSRF (Cross-Site Request Forgery)
+- Authentication bypasses
+- Insecure direct object references
+- Sensitive data exposure
+- Security misconfiguration
+- Broken access control
+
+Report format:
+- Severity (Critical/High/Medium/Low)
+- Location in code
+- Description of vulnerability
+- Recommended fix
+- References (CWE, OWASP)
+```

package/.claude/skills/youtube-collector/README.md

@@ -0,0 +1,107 @@
+# YouTube Collector Skill
+
+유튜브 채널을 등록하고, 새 컨텐츠를 수집하여 자막 기반 요약을 생성하는 Claude Code skill입니다.
+
+## 주요 기능
+
+- **채널 등록/관리**: 유튜브 채널을 등록하고 관리
+- **컨텐츠 수집**: 등록된 채널의 최신 영상 정보 수집
+- **자막 수집**: 영상의 자막(transcript) 자동 수집
+- **요약 생성**: 자막 또는 설명 기반 요약 생성
+- **중복 방지**: 이미 수집된 영상은 자동 스킵
+
+## 초기 설정
+
+### 1. 필수 패키지 설치
+```bash
+pip install google-api-python-client youtube-transcript-api pyyaml
+```
+
+### 2. API 키 설정
+```bash
+python3 .claude/skills/youtube-collector/scripts/setup_api_key.py
+```
+
+## 사용 프롬프트 예시
+
+### 채널 등록
+
+```
+유튜브 채널 @channelname 등록해줘
+```
+
+```
+이 유튜브 채널 등록해줘: https://youtube.com/@examplechannel
+```
+
+```
+다음 채널들을 등록해줘:
+- @channel1
+- @channel2
+- @channel3
+```
+
+### 컨텐츠 수집
+
+```
+등록된 유튜브 채널들의 새 영상 수집해줘
+```
+
+```
+유튜브 채널 @channelname의 최신 영상 5개 수집해줘
+```
+
+```
+모든 채널에서 새로운 컨텐츠 있는지 확인하고 수집해줘
+```
+
+### 수집된 데이터 조회
+
+```
+수집된 유튜브 컨텐츠 목록 보여줘
+```
+
+```
+@channelname 채널에서 수집된 영상들 보여줘
+```
+
+```
+최근 수집된 영상 요약 보여줘
+```
+
+### 채널 관리
+
+```
+등록된 유튜브 채널 목록 보여줘
+```
+
+```
+@channelname 채널 등록 해제해줘
+```
+
+### API 키 관리
+
+```
+유튜브 API 키 설정 상태 확인해줘
+```
+
+```
+유튜브 API 키 새로 설정해줘
+```
+
+## 데이터 저장 위치
+
+| 데이터 | 경로 |
+|--------|------|
+| API 키 | `~/.config/youtube-collector/config.yaml` |
+| 프로젝트 설정 | `.reference/youtube-config.yaml` |
+| 등록된 채널 | `.reference/channels.yaml` |
+| 수집된 컨텐츠 | `.reference/contents/{channel}/` |
+
+## 스크립트
+
+| 스크립트 | 설명 |
+|----------|------|
+| `setup_api_key.py` | API 키 설정 |
+| `fetch_videos.py` | 채널 영상 목록 조회 |
+| `fetch_transcript.py` | 영상 자막 수집 |

package/.claude/skills/youtube-collector/SKILL.md

@@ -0,0 +1,158 @@
+---
+name: youtube-collector
+description: 유튜브 채널을 등록하고 새 컨텐츠를 수집하여 자막 기반 요약을 생성하는 skill. 사용자가 (1) 유튜브 채널 등록/관리를 요청하거나, (2) 등록된 채널의 새 영상 수집을 요청하거나, (3) 유튜브 영상 요약을 요청할 때 사용. 데이터는 .reference/ 폴더에 YAML 형식으로 저장됨.
+---
+
+# YouTube Collector
+
+등록된 유튜브 채널의 새 컨텐츠를 수집하고 자막 기반 요약을 생성.
+
+## 사전 요구사항
+
+**필수 패키지:**
+```bash
+pip install google-api-python-client youtube-transcript-api pyyaml
+```
+
+**API 키 설정:** 보안을 위해 API 키는 사용자 홈 디렉토리에 저장됨.
+
+```bash
+# API 키 설정 (대화형)
+python3 scripts/setup_api_key.py
+
+# 또는 직접 지정
+python3 scripts/setup_api_key.py --api-key YOUR_API_KEY
+
+# 현재 설정 확인
+python3 scripts/setup_api_key.py --show
+```
+
+**설정 파일 경로:**
+- macOS/Linux: `~/.config/youtube-collector/config.yaml`
+- Windows: `%APPDATA%\youtube-collector\config.yaml`
+
+## 워크플로우
+
+### 1. 채널 등록
+
+채널 URL 또는 핸들로 등록:
+
+```bash
+# 핸들로 등록
+python3 scripts/register_channel.py --channel-handle @channelname --output-dir .reference/
+
+# URL로 등록
+python3 scripts/register_channel.py --channel-url "https://youtube.com/@channelname" --output-dir .reference/
+```
+
+**결과:** `.reference/channels.yaml`에 채널 정보가 추가됨.
+
+### 2. 컨텐츠 수집
+
+스크립트가 영상 목록 조회 + 자막 수집 + YAML 파일 저장을 자동으로 처리:
+
+```bash
+# 특정 채널 수집
+python3 scripts/collect_videos.py --channel-handle @channelname --output-dir .reference/ --max-results 10
+
+# 등록된 모든 채널 수집
+python3 scripts/collect_videos.py --all --output-dir .reference/
+```
+
+**결과:** `.reference/contents/{channel_handle}/{video_id}.yaml` 파일들이 생성됨.
+
+### 3. 요약 생성
+
+수집 결과 JSON에서 새로 추가된 영상 확인 후, 각 영상의 YAML 파일에 summary 필드 추가:
+
+```yaml
+summary:
+  source: "transcript"  # 또는 "description" (자막 없을 때)
+  content: |
+    ## 서론
+    - 문제 제기 또는 주제 소개
+    - 영상의 목적/배경
+
+    ## 본론
+    - 핵심 내용 상세 설명
+    - 해결책, 방법론, 예시 등
+    - 주요 포인트별 정리
+
+    ## 결론
+    - 핵심 요약
+    - 시사점 또는 다음 단계
+```
+
+**요약 생성 기준:**
+- `transcript.available: true` → 자막 기반 요약, `summary.source: "transcript"`
+- `transcript.available: false` → 설명 기반 요약, `summary.source: "description"`
+
+### 4. 데이터 조회
+
+수집된 컨텐츠 확인:
+- `.reference/contents/` 폴더 구조 확인
+- 특정 채널/영상의 YAML 파일 읽어서 정보 제공
+
+## 스크립트 옵션
+
+### register_channel.py
+
+| 옵션 | 설명 |
+|------|------|
+| `--channel-handle` | 채널 핸들 (@username) |
+| `--channel-url` | 채널 URL |
+| `--channel-id` | 채널 ID (UC...) |
+| `--output-dir` | 저장 디렉토리 (기본: .reference) |
+
+### collect_videos.py
+
+| 옵션 | 설명 |
+|------|------|
+| `--channel-handle` | 특정 채널 핸들 |
+| `--channel-id` | 특정 채널 ID |
+| `--all` | channels.yaml의 모든 채널 처리 |
+| `--output-dir` | 저장 디렉토리 (기본: .reference) |
+| `--max-results` | 채널당 최대 수집 개수 (기본: 10) |
+| `--language` | 자막 우선 언어 (기본: ko) |
+| `--no-skip-existing` | 기존 파일 덮어쓰기 |
+
+## 데이터 구조
+
+상세 스키마: [references/data-schema.md](references/data-schema.md)
+
+### 영상 데이터 예시
+```yaml
+video_id: "abc123"
+title: "영상 제목"
+published_at: "2025-12-10T10:00:00Z"
+url: "https://youtube.com/watch?v=abc123"
+thumbnail: "https://..."
+description: "영상 설명..."
+duration: "PT10M30S"
+collected_at: "2025-12-13T15:00:00Z"
+transcript:
+  available: true
+  language: "ko"
+  text: "자막 전체..."
+summary:
+  source: "transcript"
+  content: |
+    ## 서론
+    - 영상의 배경 및 목적
+
+    ## 본론
+    - 핵심 내용 1
+    - 핵심 내용 2
+
+    ## 결론
+    - 핵심 요약
+```
+
+## 에러 처리
+
+| 상황 | 안내 메시지 |
+|------|------------|
+| API 키 미설정 | "YouTube Data API 키가 필요합니다. `python3 scripts/setup_api_key.py`로 설정해주세요." |
+| 채널 미등록 | "등록된 채널이 없습니다. 먼저 채널을 등록해주세요." |
+| 패키지 미설치 | "필요한 패키지를 설치해주세요: `pip install google-api-python-client youtube-transcript-api pyyaml`" |
+| API 할당량 초과 | "YouTube API 할당량이 초과되었습니다. 내일 다시 시도해주세요." |