技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: multi-step

英文目录

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

97K
Stars
77/100
信任
分类: ml-automation审计

TradingAgents: Multi-Agents LLM Financial Trading Framework

88K
Stars
80/100
信任
分类: finance审计

Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

73K
Stars
80/100
信任
分类: legal-compliance审计

Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.

26K
Stars
86/100
信任
分类: agent-skills审计

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

25K
Stars
88/100
信任
分类: agent-skills审计

Use multi-agent collaboration for software development

34K
Stars
77/100
信任
分类: development审计

Teams-first Multi-agent orchestration for Claude Code

37K
Stars
82/100
信任
分类: agent-frameworks审计

A comprehensive collection of ready-to-use scientific and research skills for AI agents.

31K
Stars
78/100
信任
分类: utility审计

The Single Sign-On Multi-Factor portal for web apps, now OpenID Certified™

28K
Stars
81/100
信任
分类: devops审计

Label Studio is a multi-type data labeling and annotation tool with standardized output format

28K
Stars
87/100
信任
分类: ml-automation审计

Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.

25K
Stars
73/100
信任
分类: browser-automation审计

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

23K
Stars
79/100
信任
分类: agent-frameworks审计