开发工具 Agent 技能
面向代码、仓库和工程流程的集成。
Process skills that give a Reasonix coding agent the disciplines of a careful engineer: write the test first, debug from evidence, plan before coding, verify before claiming done.
Codex-native harness with reusable agents, persistent multi-agent orchestration, and communication logs.
Audit accumulated AGENTS.md, CLAUDE.md, and generic SKILL.md instructions before stale workarounds keep consuming context.
Make Claude Code, Codex, Gemini CLI, or Qwen Code drive at full power on your own machine - generate images, video, and audio, build and run workflows, pick the model variant that fits your hardware,...
An open runtime that turns Codex, Claude Code, Gemini, Qwen, Kimi, Oh My Pi, Kilo Code, OpenCode, and Cursor into orchestrated fleets — same scripts as Claude Code's own Workflow tool, plus a live...
The definitive SEO + GEO skill for Claude. Full site audits with scored findings, AI search optimization (Google AI Overviews, ChatGPT, Perplexity), schema generation, E-E-A-T assessment, and 20...
Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content
An engineering control framework for automated AI coding. Its core assumption is that architecture, phase/work-unit boundaries, entry/exit criteria, and implementation control plans are prepared...
This repository is a curated collection of skills, plugins, and automation pipelines designed for Claude Code — Anthropic's CLI for AI-assisted software engineering.
Claude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20...
你以為的「中灰」，其實只反射了 的光。 CIELAB 裡 a* 乘 500、b* 乘 200 —— 那個 的比例是 **定下來的，八十年沒人動過。 1976 年 CIE 一口氣推出**色空間，不是因為需要兩個，是因為兩派人馬誰也說服不了誰。 色彩科學裡這種事很多。
iOS/macOS Research Swiss Army Knife
A local minimized harness, with simplified output and logs for self-evolve
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
You started with 50 clean lines. Three months later it's 200, and Claude ignores half of them. Adding more rules doesn't fix it.
Display your OpenClaw / Clawdbot / MoltBot AI assistant's activity on a portable e-ink display in real-time using a .
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
QuantManus 是一个基于大语言模型（LLM）的智能 Agent 框架，专注于**、**和**。
This project is in early stages and has been largely vibe-engineered with AI coding assistants. Expect bugs, missing features, and rough edges. — always work on a copy or use version control.
This repository contains the amalgamated C source code for Real Time Logic's embedded web and application server libraries:
Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.
Skill for Claude, Cursor & Copilot that automates the Karpathy LLM Wiki workflow: ingest web, GitHub, and YouTube URLs into a well-structured, citable, cross-referenced knowledge base with automatic...
Central marketplace for Claude Code plugins by xiaolai
Cross-platform and non-web GUI library for 🦀 Rust powered by 🎨 Skia.