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: clear

英文目录

Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

171K
Stars
81/100
信任
分类: design-creative审计

A comprehensive library of over 1,273 agentic skills for various AI coding assistants, featuring clear documentation and installation instructions.

44K
Stars
76/100
信任
分类: development审计

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

13K
Stars
87/100
信任
分类: design-creative审计

Desktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, Microsoft Copilot Cowork, or Copilot Studio.

3.0K
Stars
83/100
信任
分类: utility审计

access to david ondrej's personal agent skills

2.7K
Stars
76/100
信任
分类: utility审计

AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.

1.8K
Stars
77/100
信任
分类: development审计

Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.

3.4K
Stars
70/100
信任
分类: design-creative审计

A local-first framework and skill collection for architecture firms to build and share AI-assisted workflows using Claude Code.

313
Stars
77/100
信任
分类: design-creative审计

A principles-first workflow for AI coding agents providing reusable phases and end-to-end workflows for software development tasks.

238
Stars
72/100
信任
分类: coding-agents审计

A collection of 34 installable agent skills for running computational-chemistry workflows in OpenClaw, with clear documentation and a DOI citation.

128
Stars
80/100
信任
分类: research审计

Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".

90K
Stars
80/100
信任
分类: security审计

Turn complex codebases into clear, navigable architecture diagrams with Claude Code.

1.7K
Stars
77/100
信任
分类: coding-agents审计