Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or...
Guide for designing and writing ap-* agent specifications. Use when creating a new agent, drafting agent frontmatter, defining agent workflows, or structuring agent collaborations. For...
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety...
Orchestrate parallel scientist agents for comprehensive research with AUTO mode
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than...
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Proactively analyzes the codebase and generates specialized subagents and skills to standardize agentic workflows.
No Polling for Background Agents
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA optimizer", "LLM...
Agent Orchestration Rules
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than...
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...