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: corpus

英語版ディレクトリ

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

1.6K
Stars
76/100
信頼
カテゴリ: rag-knowledge監査

用于训练中英文对话系统的语料库 Datasets for Training Chatbot System

2.1K
Stars
67/100
信頼
カテゴリ: support-automation監査

A multi-agent newsroom that transforms documents into a cross-linked wiki using local LLMs, designed for agent runtimes like Claude Code.

77
Stars
67/100
信頼
カテゴリ: research監査

A collection of 9 X/Twitter marketing skills for Claude Code and Codex that write tweets, threads, and replies in your voice, strip AI tells, and publish via Publora, with MIT license and clear installability.

42
Stars
70/100
信頼
カテゴリ: marketing-growth監査

Claude Code skill for automated RTL-to-GDS flow using open-source EDA tools.

41
Stars
67/100
信頼
カテゴリ: utility監査

A hand-curated, topic-organized library of the best ML education — 923 docs (391 arXiv papers, 474 Stanford/MIT/Karpathy/fast.ai lectures, 58 explainer articles), normalized to Markdown with full provenance. Open it in Obsidian or point your agent at it. A clean ML corpus for learning, RAG & fine-tuning.

141
Stars
67/100
信頼
カテゴリ: research監査

Codex skill for curating GitHub starred repositories into safe, meaningful GitHub Stars Lists.

15
Stars
66/100
信頼
カテゴリ: utility監査

Collection of 17 focused AI agent skills for tasks like brainstorming, research, and planning, compatible with skills.sh and installable via agent runtimes.

25
Stars
70/100
信頼
カテゴリ: productivity監査

Security audit skill for LLM agents - prompt injection scanner, attack catalog & defense checklist

10
Stars
66/100
信頼
カテゴリ: utility監査

A skill for AI coding assistants that converts folders of code, docs, papers, or images into a queryable, ontology-typed knowledge graph with entity reconciliation.

16
Stars
66/100
信頼
カテゴリ: data監査