you-might-not-need-a-memo
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
这个技能目录把可安装的 AI Agent 技能集中在一起,方便你按搜索、分类、主题和官方来源快速筛选,并直接安装到 Claude Code、Cursor、Windsurf 等环境。
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
Open Source framework for voice and multimodal conversational AI
Tool for creating, maintaining and operating Kubernetes clusters with ease.
Prevent include cycles and platform-boundary leaks by enforcing header layering.
Load a 3D model from an OBJ file, create a textured mesh with mipmaps, and render with a fly-around camera. Use when someone needs to load geometry from a file, parse OBJ models, or render textured 3D meshes in SDL3 GPU.
Handle automated PR review feedback and merge when ready
Create new AI chat interface components for the ai-elements library following established composable patterns, shadcn/ui integration, and Vercel AI SDK conventions. Use when creating new components in packages/elements/src or when the user asks to add a new component to ai-elements.
Multi-tenant SaaS platform for token-gated onchain communities - wallet scoring, Discord/Telegram integration, and human-in-the-loop approval workflows
Backend budget tracking patterns for AI generation. Awareness-based tracking (not blocking), tool timeouts, per-tool rate limits, token estimates, context window management, truncation strategies, search quality detection. Triggers on budget, tool timeout, rate limit, token estimate, truncation, context window, search quality, diminishing returns.
Read the latest code review, plan fixes for all findings, then execute the fixes — all in one command. Produces a dated plan and execution log in .reviews/.