Loading...
Loading...
Found 8,783 Skills
Repository understanding and hierarchical codemap generation
Home Assistant entity discovery, states, helpers, labels, groups, and services. Use when the user asks about entities or services, needs to rename/move/hide/label entities, or requires service calls via ha-mcp tools.
Automate Microsoft Teams tasks via Rube MCP (Composio): send messages, manage channels, create meetings, handle chats, and search messages. Always search tools first for current schemas.
Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools first for current schemas.
Display project status, active tracks, and next actions
Implement features using tracer bullet approach - build minimal end-to-end vertical slice first, then expand.
Build voice agents with the Cartesia Line SDK. Supports 100+ LLM providers via LiteLLM with tool calling, multi-agent handoffs, and real-time interruption handling.
Frontend structure worker: SCAFFOLD new React project or RESTRUCTURE existing monolith to component-based architecture
Structured thinking patterns for agent self-reflection. Includes think-about-collected-information (validate research), think-about-task-adherence (stay on track), and think-about-whether-you-are-done (completion validation).
Feishu Document Creation Orchestration Skill - Convert Markdown files to Feishu documents, orchestrate multiple sub-skills to collaborate on the task, and use file transfer for data to save Tokens.
Create structured change proposals and specification differences using an OpenSpec specification-driven approach. It is used for feature planning, proposal creation, specification writing, introducing new capabilities, or initiating development processes. Trigger words include "openspec proposal", "planning", "create proposal", "plan change", "specify feature", "new feature", "new characteristic", "new requirement", "add feature planning", "design specification"
Agent skill for neural-network - invoke with $agent-neural-network