Loading...
Loading...
Found 189 Skills
Integrate Claude Agent SDK with You.com HTTP MCP server for Python and TypeScript. Use when developer mentions Claude Agent SDK, Anthropic Agent SDK, or integrating Claude with MCP tools.
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describe_scene and get_canvas_screenshot to see its own work, (3) export/import .excalidraw files or PNG/SVG images, (4) save/restore canvas snapshots, (5) convert Mermaid to Excalidraw, or (6) perform element-level CRUD, alignment, distribution, grouping, duplication, and locking. Requires a running canvas server (EXPRESS_SERVER_URL, default http://localhost:3000).
This skill should be used when the user asks about "Claude Code plugins", "plugin development", "how to build a plugin", "what plugin components exist", "plugin architecture", "extending Claude Code", or needs an overview of plugin development capabilities. Acts as a guide to the 9 specialized plugin-dev skills, explaining when to activate each one. Load this skill first when the user is new to plugin development or unsure which specific skill they need.
Records workflows in authenticated browser sessions and generates annotated GIF tutorials without handling credentials. Use when you need to document authenticated processes, create tutorials from existing sessions, or capture workflows that require login. Triggers on "record my workflow", "document authenticated process", "create tutorial from session", "capture this workflow as GIF", or "show me how to do this". Works with Chrome browser via MCP integration and authenticated sessions.
MCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating json-render with the Model Context Protocol.
Use this skill when working with Mastra - the TypeScript AI framework for building agents, workflows, tools, and AI-powered applications. Triggers on creating agents, defining workflows, configuring memory, RAG pipelines, MCP client/server setup, voice integration, evals/scorers, deployment, and Mastra CLI commands. Also triggers on "mastra dev", "mastra build", "mastra init", Mastra Studio, or any Mastra package imports.
Manage your Dex personal CRM — search, create, and update contacts, log interaction notes, set follow-up reminders, organize contacts with tags and groups, and manage custom fields. Use this skill when the user wants to: (1) Find or look up a contact, (2) Add or edit contact details, (3) Log a meeting, call, or interaction note, (4) Set a reminder or follow-up task, (5) Organize contacts into groups or apply tags, (6) Track custom data with custom fields, (7) Merge duplicate contacts, (8) Review their relationship history or prepare for a meeting, (9) Authenticate with Dex via /dex-login, or any other personal CRM task involving their professional network.
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.
List tasks from One Horizon — planned, completed, blocked, initiatives, or bugs. Use when asked "what's on my plate", "what did I ship", "show blockers", "what initiatives are active", "show open bugs", "what should I pick up next", or "what is the team working on". Requires One Horizon MCP.
Single entry skill for open-websearch setup and focused live retrieval, preferring local CLI/daemon paths while remaining compatible with workspace-exposed MCP tools.
Expert guidance on AI Agent Harness architecture based on the comprehensive Claude Code analysis book
Create and manage chaos experiments using Harness Chaos Engineering via MCP. Run resilience tests like pod deletion, CPU stress, and network faults. Use when user says "chaos experiment", "chaos engineering", "resilience test", "chaos test", or wants to test system reliability.