Loading...
Loading...
Found 2,230 Skills
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: LiveKit Cloud + LiveKit Inference. REQUIRES writing tests for all implementations.
Day 2 보충 자료 - MCP 딥다이브. Claude Code에 외부 도구를 연결하는 MCP를 체계적으로 배운다. "MCP 배우기", "MCP 보충", "MCP 강의", "MCP 학습" 요청에 사용.
Persistent local memory for AI agents. Silently capture and retrieve context that survives beyond a single conversation: business requirements, API specs, integration quirks, technical decisions, user preferences, and domain knowledge. Use this skill proactively whenever you encounter information worth preserving or when context from past sessions would help the current task. Also triggered manually by "braindump this" (to store) or "use your brain" (to retrieve).
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
After an agentic task completes, perform a retrospective analysis across 6 dimensions (goal alignment, efficiency, decision quality, error handling, communication, reusability). Score performance, identify inefficiency patterns, evaluate skill usage, and produce actionable improvement recommendations. Triggers on "how did it go", "retrospective", "review performance", "what could be better", or after any long agentic task completes.
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.
Load groove workflow context into the conversation. Run at the start of every session.
Build AI agents and automate Claude Code programmatically using the Claude Agent SDK and headless CLI mode. Use this skill when you need to build an agent, create a Claude agent, make a bot, work with the agent SDK, run Claude in headless mode, write programmatic agent code, automate with Claude, create an MCP server builder, or query Claude programmatically. Covers the Python SDK, the claude -p headless interface, custom tool creation with SDK MCP servers, hooks for deterministic control, session management, and CLI flag reference. Authentication uses existing ~/.claude/ config — no API keys required.
Use this skill when auditing AI agent skills for security vulnerabilities, prompt injection, permission abuse, supply chain risks, or structural quality. Triggers on skill review, security audit, skill safety check, prompt injection detection, skill trust verification, skill quality gate, and any task requiring security analysis of AI agent skill files.
Non-interactive X11 desktop control for AI agents. Use when the task involves controlling a Linux desktop - clicking, typing, reading windows, waiting for UI state, or taking screenshots inside a sandbox or VM.
Checkpoint - Pre-publish review with multi-layer deep analysis. Triggers: Preparing to publish an npm package, requiring pre-release review, or checking code change quality. Review Layers: - Per-Change: In-depth analysis of each change group (up to 10 Agents) - Holistic: Parallel review by 5 roles (Architecture/Development/Testing/Security/Documentation) - Synthesis: 1 Agent summarizes review results Commands: - /把关 - Start pre-publish review - /把关 check - Check unpublished changes - /把关 version - Recommend version upgrade - /把关 report - Generate review report - /review - English command Capabilities: Unpublished change detection, in-depth per-change analysis, multi-role review, version recommendation, release risk assessment.
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction