implementing-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel implementation in the background. Separates independent tasks from planning docs, each agent writes code directly. Context-safe with auto-save. Use for "백그라운드 구현", "bg impl", "병렬 구현", "Codex로 구현", "구현해줘", "코드 작성해줘" requests.
planning-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel planning in the background with auto-save. Agents continue running even when session hits context limits. Use for "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", "기획해줘", "N명이 기획", "계획", "플래닝", "plan", "설계" requests.
background-reviewer
Orchestrates multi-LLM parallel code review using Claude, Codex, and Gemini. Each agent reviews from a different perspective using agent personas (security, architecture, code quality, performance). Supports persona-based review via `agt persona review`. Use for "코드 리뷰", "리뷰해줘", "bg review", "멀티 리뷰", "background review", "페르소나 리뷰" requests.
review-fix-loop
Autonomous review-fix cycle that continuously reviews code using background-reviewer, fixes issues, and repeats until all findings are resolved. Use for "리뷰 루프", "자동 개선", "review fix loop", "리뷰 반복", "코드 개선 루프", "keep reviewing" requests.
analyzing-business-model
Analyzes the current repository's service from a business model perspective. Multiple BM expert agents (revenue strategist, market analyst, user value analyst, growth strategist) analyze in parallel and suggest monetization strategies. Use for "BM 분석", "수익화 분석", "비즈니스 모델 분석" requests.
processing-documents
Processes PDF, DOCX, XLSX, PPTX documents including analysis, summarization, and format conversion. Use for "문서 분석", "PDF 변환", "Excel 추출", "문서 요약" requests or when working with office documents.
analyzing-proposals
Analyzes business proposals and RFP documents, evaluating pricing, deadlines, and technical specifications for feasibility. Generates go/no-go reports. Use for proposal analysis, RFP review, bidding assessment, or business feasibility evaluation.
managing-context
Discovers and loads relevant project context from markdown documentation before each task. Matches context documents based on keywords, file paths, and task types. Use at task start to access project plans, architecture, and implementation status.
indexing-static-context
Provides an index of global static context files in ~/.agents/. Returns appropriate static file paths for natural language queries like "내 정보", "보안 규칙". Use when other skills or agents need to locate reference information.
managing-context-worktree
Evaluates context similarity between new and existing work, automatically creating git worktree on a new branch when tasks differ. Activates on task start, new feature implementation, or switching to different issues.
committing-and-creating-pr
Guides git commit and PR creation with security validation to prevent sensitive information leaks. Activates on "커밋", "commit", "PR", "pull request" requests. Enforces consistent commit style.
preparing-iac-deployment
Prepares IaC project deployment by analyzing the current project and generating K8s manifests, Dockerfiles, CI/CD workflows in standardized structure. Use for "배포 준비", "IaC 설정", "k8s 매니페스트", "deploy prep" requests.
reviewing-code-multi-ai
Orchestrates multiple AI tools (Claude, Codex, Gemini, Droid) for comprehensive code review from multiple perspectives. Use for "멀티 AI 리뷰", "코드 리뷰", "종합 리뷰" requests or when thorough multi-agent review is needed.
automating-browser
Provides Playwright-based browser automation and E2E testing. Supports screenshots, web scraping, and form automation. Use for "브라우저", "스크린샷", "E2E 테스트", "웹 스크래핑" requests.
looping-pr-reviews
Waits for PR reviews and automatically applies fixes in a loop. Analyzes review comments and commits corrections until approval. Use for "리뷰 대기", "리뷰 반영", "자동 리뷰 수정", "review loop" requests.
managing-tasks
Integrates with Task Master CLI (tm) for AI-powered project task management. Use for "다음 작업", "작업 목록", "tm", "task", "작업 상태" requests or when managing project tasks.
automating-appstore-connect
Automates App Store Connect via JWT API/Playwright hybrid. Supports app info, builds, TestFlight deployment, screenshot upload, and app submission. Use for "ASC", "TestFlight", "앱스토어", iOS deployment tasks.
managing-discord
Manages Discord servers/channels via REST API. Supports channel CRUD, permissions, messaging, and webhooks. Use for "Discord", "디스코드", "채널 관리", "discord bot" requests.
integrating-search-console
Integrates with Google Search Console API. Supports search performance analysis, URL inspection, sitemap management, and site verification. Use for "GSC", "서치콘솔", "검색 성과", "SEO 분석" requests.
managing-kubernetes
Manages Kubernetes clusters via kubectl. Supports pod/deployment/service management, log viewing, port-forwarding, and debugging. Use for "k8s", "kubectl", "파드", cluster management tasks.
uploading-to-notion
Uploads Claude session summaries or markdown reports to Notion. Use for "노션 업로드", "결과 저장", "notion 정리", "세션 요약", "리포트 업로드", "보고서 작성" requests.
managing-obsidian-tasks
Reads and manages tasks from Obsidian Vault's TaskManager. Supports Board.md (Kanban), Table.md (Dataview), Notes/*, with automatic workspace project sync. Use for "작업 목록", "할일 조회", "task 읽기", "obsidian 작업" requests.
writing-to-obsidian
Uploads documents to Obsidian Vault. Saves project context to workspace/{project}/context/, research/reports to articles/ with YYYY-MM-DD prefix. Use for "obsidian 업로드", "옵시디언 저장", "vault 업로드", "아티클 저장" requests.
managing-services
Centrally manages Docker containers and services. Supports service registration, listing, status updates, and port conflict detection. Use for "서비스 등록", "서비스 목록", "포트 확인", "컨테이너 관리", "docker 상태" requests.
developing-slack-apps
Develops Slack apps and API integrations. Supports Bolt framework, Block Kit UI, event handling, and slash commands. Use for "Slack", "슬랙", "봇", "webhook" requests or Slack app development.
managing-vault-secrets
Manages credentials and API keys from Vaultwarden. Auto-triggers when credentials are needed. Use for "vault 조회", "API 키 가져와", "비밀번호 저장", "secret 등록" requests.
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
managing-skills
Manages the skill ecosystem and maintains quality. Provides skill status overview, quality analysis, issue diagnosis, improvement suggestions, auto-fixes, and new skill creation guides. Use for "스킬 분석", "스킬 현황", "스킬 만들기", "스킬 개선" requests.
recommending-skills
Automatically recognizes and recommends suitable skills for user requests. Discovers helpful installed skills even without explicit skill requests. Implicitly activates on all user requests.
processing-audio
Converts and processes audio files using ffmpeg. Supports format conversion, sample rate changes, mono/stereo conversion, and segment splitting. Use for "오디오 변환", "wav 변환", "샘플레이트", "ffmpeg" requests.
benchmarking-ml-models
Runs ML model benchmarks and evaluations. Measures inference speed, memory usage, and accuracy metrics. Use for "벤치마크", "모델 평가", "성능 테스트", "inference 속도" requests.
syncing-ml-models
Synchronizes ML model files across servers. Supports rsync-based transfer with bandwidth control and checksum verification. Use for "모델 동기화", "모델 배포", "rsync 모델", "서버로 전송" requests.
deploying-triton
Deploys and manages NVIDIA Triton Inference Server containers. Automates model repository setup, config generation, and health checks. Use for "triton 서버", "triton 실행", "모델 서빙", "inference server" requests.
auditing-security
Audits repository security by analyzing current code and commit history for sensitive information leaks. Detects API keys, passwords, and credentials. Use for "보안 점검", "보안 감사", "security audit", "민감 정보 검사" requests.