Discover Development skills, compare source repositories and read the instructions for each workflow.
Capture user preferences as permanent directives. Activate when the user says "always", "never", "I prefer", "I like", "don't", "avoid", expresses a coding style preference, states a workflow requirement, or co...
Search your memory before solving problems. Activate when debugging errors, discussing architecture, answering "how do I...", fixing bugs, making technical decisions, or when you realize mid-response that past...
Create structured plans for complex tasks. Activate when the user asks to implement a feature, build something with multiple steps, needs a project roadmap, or when a task has 3 or more distinct steps. This ski...
Know the correct database field names. Activate when writing SQL queries, working with Supabase, using Prisma, accessing database tables, or when you need to reference column names. This skill prevents "column...
Resume session after /clear - instant restore from local cache (1ms) with Redis/Supabase fallback
Capture solutions as patterns for future use. Activate when you fix a bug, solve a non-trivial problem, get corrected by the user, discover something that works (or doesn't work), find a better approach, or com...
Literature research automation - search papers, code, and blogs, deduplicate, download PDFs, analyze and generate research reports. Supports incremental updates.
Browser automation skill for web testing, scraping, and interaction. Use for end-to-end testing, screenshots, and browser automation tasks.
Build multi-step LLM agents for the Continuum system. Use when creating agent definitions with nodes, edges, tools, and execution flows. Triggers on requests to "create an agent", "build a workflow", "design an...
Analyze Langfuse trace JSON exports using jq queries. Use when user provides a Langfuse trace file (.json) for analysis, debugging agent behavior, checking token usage, or investigating tool calls. Triggers on...
Expert prompt engineering for Claude 4.x models (Sonnet 4.5, Opus 4.5, Haiku 4.5). Use when creating system prompts, optimizing existing prompts, designing agentic workflows, or improving prompt effectiveness....
Execute Bruno .bru API requests via curl, or create new .bru files. Use when user asks to run, execute, or test an API request from a Bruno collection, references a .bru file, or wants to create a new Bruno req...
버전 릴리스 자동화. CHANGELOG.md 업데이트, 플러그인 버전 파일 수정, Git 커밋까지 일괄 처리한다. "릴리스", "release", "버전 업데이트", "version bump", "배포 준비" 요청 시 트리거된다.
Claude Code Hooks 생성 스킬. 도구 실행 전후 검증, 코드 품질 관리, 알림 전송을 자동화하는 훅을 생성한다. 사용자가 "훅 만들어줘", "hook 생성", "PreToolUse 훅", "PostToolUse 훅", "파일 보호 훅", "린트 훅", "알림...
AI 에이전트를 위한 고품질 프롬프트를 생성하는 스킬. 스킬/에이전트/MCP 서버/일반 코딩 작업을 위한 프롬프트를 한국어로 생성. 사용자가 "프롬프트 만들어줘", "프롬프트 생성", "프롬프팅 해줘", "~를 위한 프롬프트", "~...
AGENTS.md와 CLAUDE.md 파일 간 연결 및 충돌 해결. 프로젝트에 AGENTS.md가 존재할 때 CLAUDE.md가 이를 참조하도록 심볼릭 링크를 설정한다. 두 파일의 내용이 상충하면 사용자에게 확인하여 해결한다. "AGENTS.md 연결", "C...
LLM이 잘 설계된 도구를 통해 외부 서비스와 상호작용할 수 있게 하는 고품질 MCP(Model Context Protocol) 서버 생성 가이드. Python(FastMCP)이나 Node/TypeScript(MCP SDK)로 외부 API나 서비스를 통합하는 MCP 서버를 구축...
효과적인 스킬 생성 가이드. 사용자가 Claude의 기능을 전문 지식, 워크플로우, 도구 통합으로 확장하는 새 스킬을 만들거나 기존 스킬을 업데이트하려 할 때 사용한다.
Claude Code용 커스텀 서브에이전트 생성. .claude/agents 또는 ~/.claude/agents에 새 에이전트를 생성, 추가, 구성하려 할 때 사용한다. "에이전트 만들어줘", "에이전트 생성", "서브에이전트 추가", "~를 위한 에이전트 만...
Create and manage behavior specification wikis in Obsidian format. Use when creating specs, documenting features, or when user mentions "wiki", "spec", or "workstream". Specs are the source of truth - point an...
This skill should be used when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or architectural questions. The oracle excels at multi-source research combining codebase explor...
You MUST use this before any EXTENDED creative work (not simple execution) - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design be...
Create a PR for this branch. ALWAYS links related issues and uses closing keywords to auto-close them on merge.
Use when starting a session on a project, returning after time away, or before making significant changes. Essential for building comprehensive understanding of project state through total recall and oracle-dri...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.