session-reentry
|
opera-debrief
|
opendesign-concierge
|
debug-specialist
디버깅, 디버그, 버그, 에러, 오류, 버그 수정, 원인 분석, 로그 분석, 트러블슈팅, 문제 해결 - Identifies root causes of runtime bugs, analyzes error logs, and provides robust fixes. Use when user reports errors, unexpected behavior, or performance issues at runtime. Do NOT use for build/compilation errors (use build-error-resolver) or code quality issues (use code-reviewer).
review-claudemd
CLAUDE.md 리뷰, CLAUDE.md 개선, 대화 분석, 설정 개선, 프롬프트 최적화, 컨텍스트 최적화 - Analyzes recent conversation history to find improvements for global and local CLAUDE.md files. Use when reviewing CLAUDE.md settings, improving Claude Code context, or analyzing past conversations for patterns. Do NOT use for document writing (use doc-coauthoring) or project planning.
writing-plans
계획, 구현 계획, 플랜 작성, 작업 계획, 구현 플랜, 플랜 저장, TODO 저장, 계획 캡처, plan 저장, 플랜 캡처 - Creates detailed implementation plans with bite-sized tasks and TDD steps. Also captures Plan mode output to structured markdown. Use when planning multi-step implementations before coding, or saving Plan mode output. Do NOT use for brainstorming (use brainstorming) or PRD/product strategy (use prd-strategist).
sequential-thinking
순차적 사고, 분석, 문제 해결, 복잡한 문제, 단계별 분석, 의사결정, 트레이드오프, 가설 검증, 비판적 검토, 설계 검증, 약점 분석, 반대 의견, 편향 점검 - Systematic step-by-step thinking for complex multi-step analysis. Use when making architectural decisions, evaluating trade-offs, critically reviewing designs, or solving problems that need step-by-step decomposition. Also use for devil's advocate analysis, bias detection, and design validation. Do NOT use for simple questions that can be answered directly.
tdd-workflow
TDD, 테스트 주도 개발, 테스트 먼저, RED-GREEN-REFACTOR - Red-Green-Refactor TDD workflow. Writes failing tests first, then implements minimal code to pass. Use when implementing features test-first or when strict TDD process is needed. Do NOT use for test strategy planning (use testing-strategy) or E2E browser tests (use e2e-runner).
security-review
보안, 보안 리뷰, 보안 검토, 취약점, 보안 분석, OWASP, 인증, 인가, 취약점 점검 - Systematic security analysis based on OWASP Top 10. Reviews code for vulnerabilities, designs auth/authz systems, and produces severity-classified reports. Use when auditing security, designing authentication, or pre-deployment security checks. Do NOT use for general code quality reviews (use code-reviewer) or debugging (use debug-specialist).
ui-ux-design
UI, UX, 디자인, UI 디자인, UX 디자인, 사용자 경험, 화면, 인터랙션, 라이브 리뷰, 와이어프레임, 화면 설계 - Create and review UI/UX designs with live browser testing. Use for design implementation, interaction testing, visual inspection, and iterative refinement with Playwright. Also triggered when continuing from prd-strategist's Design Direction output.
testing-strategy
테스트 전략, 테스팅 계획, QA 전략, 품질 보증, 테스트 피라미드, 테스트 시나리오, 커버리지 목표 - Designs test strategies including test pyramid ratios, scenario categories, and coverage targets. Use when planning how to test a feature, designing QA approach, or creating test plans. Do NOT use for TDD implementation (use tdd-workflow) or E2E test execution (use e2e-runner).
build-error-resolver
빌드 에러, 빌드 오류, 컴파일 에러, 빌드 실패 해결, 의존성 에러 - Specialized in resolving build errors, compilation failures, and dependency issues. Use when build fails, compilation errors occur, or dependency conflicts arise. Do NOT use for runtime bugs or logic errors (use debug-specialist instead).
code-simpler
코드 단순화, 복잡도 감소, 심플리파이, 가독성, KISS, 중첩 제거 - Simplifies overly complex code by reducing nesting, cyclomatic complexity, and unnecessary abstractions. Use when code exceeds complexity limits (nesting >3, function >50 lines) or after insight/review reports flag complexity. Do NOT use for full code reviews (use code-reviewer) or dead code removal (use refactor-cleaner).
code-reviewer
코드 리뷰, PR 리뷰, 품질 리뷰, 성능 리뷰, code review - Expert at reviewing code for quality, adherence to architectural principles, security, and performance. Use when reviewing PRs, verifying code quality before merge, or auditing implemented features. Do NOT use for initial implementation or debugging.
architect
아키텍처, 설계, 시스템 설계, 구조 설계, 레이어 설계, 블루프린트, 컴포넌트 설계 - Design systems, layer structures, module boundaries, and feature architectures. Outputs actionable blueprints with file paths. Use when planning architecture for new features or restructuring existing systems. Do NOT use for code implementation (use feature-development) or code-level refactoring (use refactor-cleaner).
code-explorer
코드 탐색, 실행 흐름, 아키텍처 분석, 의존성 분석, 코드베이스 이해, 심볼 분석, 레퍼런스 추적 - Traces execution paths, maps architecture layers, and navigates symbols using LSP (Grep fallback). Use when exploring unfamiliar code, understanding feature implementations, or mapping dependencies. Do NOT use for making code changes (use feature-development or refactor-cleaner).
research
자료조사, 자료수집, 레퍼런스, 문헌조사, 기술조사, 논문, 사례조사, 비교분석, 리서치, 학술조사, 기술리서치, 정보수집, 자료정리, 배경조사 - 특정 주제에 대해 병렬 전문가 서브에이전트를 활용한 심층 자료 조사를 수행한다. 기술 문서, 논문, 사례, 통계, 비교 분석, 최신 동향을 복합적으로 수집·통합하여 종합 리포트를 생성한다. PRD 작성 전 기술 검토, 아키텍처 결정, 기술 스택 선택, 학술 배경 파악이 필요할 때 사용. 마켓 리서치(시장조사/경쟁분석)는 market-research 스킬을 사용할 것.
feature-development
기능 개발, 기능 구현, 신규 개발, 피처 개발, 개발 워크플로우 - Guided feature development with codebase understanding and architecture focus. Systematic 7-phase approach from discovery to implementation. Use when building new features or adding significant functionality. Do NOT use for simple bug fixes, config changes, or single-file edits.
e2e-runner
E2E 테스트, Playwright, 엔드투엔드, 통합 테스트, UI 테스트 - Generates, runs, and maintains E2E tests using Playwright. Use when creating browser-based tests, debugging flaky E2E tests, or maintaining Playwright test suites. Do NOT use for unit/integration tests (use tdd-workflow) or test strategy planning (use testing-strategy).
doc-coauthoring
문서 작성, 문서화, 문서, 스펙 작성, 기술 문서, 제안서, RFC, 설계 문서, 의사결정 문서 - Collaborative document co-authoring through 3 stages: context gathering, iterative refinement, and reader testing. Use when writing docs, proposals, tech specs, decision docs, or RFCs. Do NOT use for PRD/product requirements (use prd-strategist) or implementation plans (use writing-plans).
codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
code-conventions
코드 컨벤션, 코딩 스타일, 코드 스타일, 네이밍, 컨벤션, 타입스크립트, 파이썬, 자바, 함수 크기, 파일 크기 - Code style reference for TypeScript, Python, and Java. Provides naming rules, function/file size limits, and formatting conventions. Use when writing or reviewing code style. Do NOT use as primary skill for code reviews (use code-reviewer) or refactoring (use refactor-cleaner).
brainstorming
브레인스토밍, 아이디어, 기획, 구상, 아이디어회의, 설계, 요구사항 분석, 접근법 탐색 - Use before creating new features or significant changes to explore user intent, requirements, and design options. Collaborative brainstorming through step-by-step questioning. Do NOT use for simple bug fixes, config changes, or tasks with clear requirements already defined.
auto-documenter
자동 문서화, 문서 업데이트, 아키텍처 문서, memory, 변경 기록, ADR, 의사결정 기록 - 작업 완료 후 프로젝트 문서를 자동 생성/업데이트한다. architecture.md, memory.md, decisions/ ADR을 관리하며 memory.md 로테이션을 수행한다. Use when a development task is completed and documentation needs updating. Also use standalone to generate or refresh project documentation. Do NOT use for writing specs or proposals (use doc-coauthoring) or PRD (use prd-strategist).
github-operator
Git, GitHub, 커밋, 브랜치, 푸시, PR, 풀리퀘스트, commit, push, branch, pull request, 머지, merge, !pr - Git/GitHub 작업 전문가. 커밋, 브랜치 생성, 푸시, PR 생성을 수행한다. 브랜치 네이밍 규칙(feature/JH2-*)과 conventional commit 메시지를 강제한다. `!pr`로 원스텝 PR 플로우(브랜치→커밋→푸시→PR) 실행. 코드 구현이나 리뷰 작업에는 사용하지 않는다.
harness
하네스, 테스트 주도 팀, TDD 팀, 병렬 개발, 스펙 구현 - Spec/PRD-driven parallel development using Agent Teams. Generates tests first, then orchestrates teammates to make all tests pass. Use when implementing a feature or project from a spec with agent teams. Do NOT use for single-file changes or simple bug fixes.
learning-research
학습 리서치, 학습 자료, 공부 자료, 학습, 공부, 스터디, 개념 정리, 이해 - 특정 주제를 깊이 이해하기 위한 학습 자료를 수집·정리한다. 병렬 전문가 서브에이전트로 개념, 원리, 실습, 심화 자료를 수집하고 이해도별로 체계화된 학습 노트를 생성한다. Obsidian vault에 자동 저장. 의사결정용 자료 조사는 research 스킬을, 시장조사는 market-research 스킬을 사용할 것.
market-research
시장조사, 시장분석, 경쟁분석, 경쟁사, TAM, SAM, SOM, 시장규모, 트렌드, 니즈분석, 기회탐색, 사용자조사, 포지셔닝, 앱시장 - Conducts structured market research including market sizing, competitive landscape mapping, user needs discovery, and trend analysis. Use when exploring a new product idea, validating market opportunity, or analyzing competition before PRD creation. Do NOT use for PRD writing (use prd-strategist) or ideation (use brainstorming).
prd-strategist
PRD, 기획서, 요구사항, 제품 기획, MVP, 제품 전략 - Use when brainstorming product ideas, creating PRD documents, defining MVP scope, or planning new features. MUST BE USED for any product strategy or requirements documentation tasks.
refactor-cleaner
리팩토링, 데드 코드, 사용하지 않는 코드, 코드 정리, 클린업, 미사용 임포트 - Identifies and safely removes dead code, unused imports, and redundant code. Use when cleaning up codebases, removing unused functions, or reducing technical debt. Do NOT use for code simplification (use code-simpler) or full code reviews (use code-reviewer).
init
Initialize a new feature workflow with git worktree. Use when the user wants to start a new feature, create an isolated development branch, says "init worktree", or needs to set up a feature branch for compounder workflow.
ideate
Use when the user has an idea to brainstorm, wants to design a feature, needs help refining a concept, says "let's ideate", or describes a vague project needing structure. Guides structured brainstorming to produce a clear feature description ready for speckit.
execute
Use when the user wants to execute tasks autonomously, run compounder on a tasks.md file, start autonomous development, compound through a task list, or implement tasks iteratively. Guides autonomous task execution using compound loops.
plan-to-manifest
Translate a superpowers implementation plan into a parallel orchestration YAML manifest
remember
Save a learning to persistent memory with automatic scope inference
spawn
How to spawn subagents correctly under the router. Use when delegating work to a specialized agent.
pr-comment
PR review comment workflow - understand the concern before fixing
poll
Controlled polling for async operations at specified intervals
verify
Run code quality checks (ruff, black, mypy, pytest)
iterate
Autonomous TDD implementation workflow with phase gates.
teams-develop
Full PR-based development lifecycle using native Claude Code teams — PM coordinates specialized agents through intake, research, design, implement, review, integrate, and complete phases
parallel-orchestrate
Orchestrate N independent TDD subagents from a YAML task manifest with worktree isolation
agent-teams-workflow
Coordinate agent teams for multi-domain collaborative implementation from a design doc or plan
ctx
View and manage hierarchical context for the current directory
debug
Systematic debugging workflow with root cause verification before fixing
implement
Auto-started default workflow. Overridden by iterate, debug, or orchestrate when invoked.
pipeline
Full pipeline from design doc through plan, manifest, parallel orchestration, to branch completion
develop
PR-based development workflow with SE team simulation
distill
Distill session episodes into persistent memory patterns
experiment
Autonomous experiment workflow with eval gates, journal memory, and team support.
Page 1539 of 1700 · 84978 results
