lambda-run/builder-language-evals
Eval suite for the builder-language Claude Code skill — form-adherence across 4 models × 3 conditions, judged by Gemini 3.1 Pro.
Eval suite for the builder-language Claude Code skill — form-adherence across 4 models × 3 conditions, judged by Gemini 3.1 Pro.
npx add-skill lambda-run/builder-language-evalsEval suite for the builder-language Claude Code skill — form-adherence across 4 models × 3 conditions, judged by Gemini 3.1 Pro.
Got a toaster? Good! You could use it to run me, your very own useful AI Agent, for the normal folks! No need for data centers, or that four digit gaming rig when you got me! AI Agents are very useful and now you too can have one!
A centralized repository for personal skills and context definitions. > This project serves as a master library of technical competencies and AI personas, designed to be integrated into other environments via git submodules (e.g., as a .claude directory) to ensure consistent AI behavior and knowledge across projects.
Describe it or draw it. Kiln makes it real. — MCP tools for AI agents to design, generate, slice, and print 3D models. Supports OctoPrint, Moonraker/Klipper, Creality, Bambu Lab, Prusa Link, Elegoo, and Direct USB.
Build a minimal Python executive AI agent with fully commented code for learning, teaching, and junior developers
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 450+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
Meta-skill for designing multi-agent harnesses in Claude Code. Evidence-based iteration: 3 core principles + Context Economy + rolling Lessons capture. Distinct from claude-harness-blueprint/kit which are product templates.