Browse Skills

Agent Memory MCP provides a persistent, searchable memory bank for AI agents, exposing MCP tools to search, write, read, and analyze project knowledge. Use it when an agent needs long-term memory synced with project documentation.

Agent Memory Systems describes architectures for short-term, long-term, and working memory in AI agents, including vector store selection, chunking strategies, and retrieval patterns. Use it when designing or debugging agent memory to prevent retrieval failures that look like intelligence failures.

Agent Messaging sends and receives cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to send a message to an agent, check agent inbox, message another agent, reply to a message, notify an agent, or any inter-agent communication task.

Agent Tool Builder teaches how to design tools for AI agents, including JSON Schema, descriptions, validation, and MCP standards, so agents work reliably.

AI Agents Architect designs and builds autonomous AI agents, covering tool use, memory systems, planning strategies, and multi-agent orchestration. Use it when building or debugging AI agents that need function calling, planning loops, and controlled autonomy.

AutoGPT Agents provides a platform for building, deploying, and managing continuous autonomous AI agents through a visual workflow builder or development toolkit. Use it when creating visual workflow agents, deploying persistent agents with webhooks or schedules, or building complex multi-step AI automation systems.

Autonomous Agent Patterns describes design patterns for building autonomous coding agents, including tool/function calling APIs, permission systems, browser automation, and human-in-the-loop workflows. Use it when designing AI agents or autonomous coding assistants.

Autonomous Agents teaches patterns for building reliable AI agents that decompose goals, plan actions, execute tools, and self-correct without constant human guidance. Use it when designing agent loops like ReAct or Plan-Execute and adding guardrails and reliability measures for production.

Behavioral Modes defines distinct AI operating modes (brainstorm, implement, debug, review, teach, ship, orchestrate) that adapt Claude's behavior based on task type. Use it to switch modes automatically or manually for more effective responses.

Claude Code Guide provides templates and best practices for configuring Claude Code, prompting the agent, and debugging issues. The guide includes configuration templates, thinking keywords, and debugging techniques.

Computer Use Agents build AI agents that interact with computers like humans do — viewing screens, moving cursors, clicking buttons, and typing text. Use it when building desktop automation, vision-based control, or GUI agents with sandboxing and security.

Context Window Management provides strategies for managing LLM context windows, including summarization, trimming, routing, and avoiding context rot. Use it when hitting token limits, losing critical information mid-dialogue, or tuning long-context applications.