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。

Lean Algorithmic Trading Engine by QuantConnect (Python, C#)

20K
Stars
80/100
信頼
カテゴリ: finance監査

A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".

90K
Stars
77/100
信頼
カテゴリ: design-creative監査

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
信頼
カテゴリ: security監査

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

791
Stars
69/100
信頼
カテゴリ: media-automation監査

Lean and powerful adblocking solution for OpenWrt

540
Stars
67/100
信頼
カテゴリ: legal-compliance監査

A collection of 70 agent skills for frontend, motion, accessibility, QA, and handoff workflows, designed for Codex and compatible with other AI coding tools.

117
Stars
72/100
信頼
カテゴリ: development監査

🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.

444
Stars
64/100
信頼
カテゴリ: agent-frameworks監査

Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

78
Stars
69/100
信頼
カテゴリ: utility監査

Composable Agent Skills for Claude and Codex that guide an idea from validation through sequenced build to shipping, with manual and autonomous tiers.

78
Stars
66/100
信頼
カテゴリ: coding-agents監査

Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)

42
Stars
69/100
信頼
カテゴリ: utility監査

Claude Code skill plugin for cleaning up and bringing Lean 4 code to mathlib standards.

27
Stars
66/100
信頼
カテゴリ: coding-agents監査

A lean, interconnected skill ecosystem for AI coding assistants like Claude Code, Cursor, and Windsurf.

80
Stars
68/100
信頼
カテゴリ: development監査