Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: downloads-organizer

英語版ディレクトリ

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

926
Stars
76/100
信頼
カテゴリ: utility監査

A Three.js agent skill pack for generating high-quality 3D graphics, scenes, and games, packaged for AI coding agents like Claude Code, Codex, and Cursor.

530
Stars
84/100
信頼
カテゴリ: design-creative監査
Cli71

🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.

38K
Stars
71/100
信頼
カテゴリ: coding-agents監査

Automatically downloads, installs, and deploys genuine Windows and Office with one click. This tool is completely free, ad-free, green, non-toxic, simple, efficient and safe.

2.7K
Stars
76/100
信頼
カテゴリ: productivity-automation監査

Local Twitter/X bookmark organizer with AI categorization and mindmap visualization

2.5K
Stars
83/100
信頼
カテゴリ: productivity-automation監査

CLI client for installing and managing verified AI agent skillsets from the Nori Skillsets registry, supporting multiple coding agents.

148
Stars
73/100
信頼
カテゴリ: coding-agents監査

A curated collection of modular agent skills for LLM-based agents, covering research, data analysis, and more.

146
Stars
76/100
信頼
カテゴリ: utility監査

Agent Skill for building evidence-backed Markdown knowledge bases with zero-cost setup, image-aware capture, automatic wiki maintenance, and an interactive knowledge graph—without requiring a RAG stack or Obsidian.

144
Stars
76/100
信頼
カテゴリ: utility監査

CLI tool to inject stored credentials into curl requests for AI agents interacting with public APIs.

120
Stars
70/100
信頼
カテゴリ: utility監査

Fizzy CLI and Agent Skills

205
Stars
71/100
信頼
カテゴリ: utility監査

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

34K
Stars
70/100
信頼
カテゴリ: research監査