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: haiku

英語版ディレクトリ

JAX-based neural network library

3.2K
Stars
77/100
信頼
カテゴリ: ml-automation監査

AI-powered skill auto-injection system for Claude Code that analyzes prompts and automatically loads relevant skills.

41
Stars
69/100
信頼
カテゴリ: coding-agents監査

Plugin de skills e agentes para Claude Code workflows de engenharia reais, do PRD ao PR

19
Stars
63/100
信頼
カテゴリ: utility監査

Full SDLC workflow for implementing features, fixing bugs, refactoring code, testing, releasing, publishing, and deploying. Use this skill when implementing, fixing, refactoring, testing, adding features, building new code, or releasing/publishing/deploying.

44
Stars
57/100
信頼
カテゴリ: design-creative監査

Validate SKILL.md files against the Agent Skills spec and Claude Code extensions. Run on new or modified skills before committing.

33
Stars
58/100
信頼
カテゴリ: research監査

외부 보안팀 코드 검사 전 자체 사전점검. security-audit 에이전트(+ 설정돼 있으면 SonarQube 보안 핫스팟)를 돌려 P0/P1/P2로 정리하고, 발견사항을 이슈로 쪼개 병렬 서브에이전트로 고친다. "보안 검사", "보안 점검", "코드 감사" 언급 시 사용.

20
Stars
58/100
信頼
カテゴリ: security監査

Design and build AI agents with persistent memory, tool use, and multi-turn conversation. Covers architecture selection, memory design, model selection, tool configuration, and implementation patterns across agent frameworks. Use when creating, debugging, or improving AI agents.

14
Stars
58/100
信頼
カテゴリ: design-creative監査