Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Implement OASIS features with patterns used in commit history. Use when modifying scanner flow, analysis, LangGraph agent (`oasis/agent/`), model integration, caching, CLI flags, or dashboard behavior.
Analyze Claude Code sessions via Braintrust
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.