aeo-claude

Create well-crafted prompts for Claude agentic execution — fights the tendency to over-prescribe inputs and procedural steps

---

Review and improve an existing Claude prompt — identifies over-specification, procedural anti-patterns, and missed agentic potential

Build autonomous AI agents in Python using the Claude Agent SDK. Covers the GTVR execution pattern (gather, take action, verify, repeat), stateless query() and stateful ClaudeSDKClient APIs, streaming versus batch modes, custom tool creation with @tool decorator, MCP server integration, hook-based execution control, permission boundaries, API key and OAuth token management, multi-agent coordination, and production deployment strategies. Suited for programmatic agents, tool chains, and multi-agent systems. Not designed for basic chat interfaces.

Author high-quality Claude Code skills with proper frontmatter, trigger-optimized descriptions, progressive disclosure structure, and MCP tool integration. Includes file organization patterns, testing approaches, and performance tuning. Consult when building new skills, debugging activation issues, or refactoring existing skill content.

---

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Author custom Claude Code slash commands as reusable Markdown prompt templates. Covers frontmatter configuration, argument handling, variable substitution, and workflow automation patterns. Invoke when designing new commands, debugging command syntax, or converting repetitive prompts into reusable shortcuts.

2 hooks across 2 events