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 skills add 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.
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.
智能备忘录 — Cloudflare Workers + D1 实战项目，用于学习 Claude Code 调用第三方 CLI / MCP / Skills
Build a persistent, structured wiki for your AI agent to store research and context across sessions using the LLM Wiki pattern.
Specialized Claude Code skills for spec review, design fidelity, feature completeness, and multi-layer testing. Complements the superpowers plugin.
Two reusable agent skills (simple-agent-comms, simple-agent-room) + Python CLI tools for inter-agent messaging on disk. JSON-Lines rooms, inotify-driven monitors, no broker dependency. Agent never needs to know the file paths.
A collection of Agent Skills for AI coding assistants (Claude, Cursor, Copilot). Following agentskills.io specification.