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。

.NET 10, Angular 21, Clean Architecture, Clean Code, SOLID, KISS, DRY, Mediator Pattern, Folder-by-Feature Structure

3.3K
Stars
85/100
信頼
カテゴリ: design-creative監査

👽 Terraform Orchestration Tool for DevOps. Keep environment configuration DRY with hierarchical imports of configurations, inheritance, and WAY more. Native support for Terraform and Helmfile.

1.3K
Stars
79/100
信頼
カテゴリ: devops監査

Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch with PR. Use when asked to prepare/create a release, bump version, or run `/prepare-release`.

51K
Stars
70/100
信頼
カテゴリ: automation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

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).

25K
Stars
83/100
信頼
カテゴリ: research監査

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

253
Stars
69/100
信頼
カテゴリ: coding-agents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

토스증권을 AI 에이전트·터미널에서 — 공식 Open API(예정)보다 넓은 조회·거래 범위(수급·AI시그널·스크리너·실시간 푸시·소수점 주문·dry-run preview)를 다루는 비공식 CLI

398
Stars
66/100
信頼
カテゴリ: agent-frameworks監査

Local Obsidian-backed dashboard for GitHub projects and AI agent skills

27
Stars
67/100
信頼
カテゴリ: utility監査

Collection of free, open-source AI skills for Google Ads practitioners, designed for use with Claude Code and other AI harnesses.

54
Stars
69/100
信頼
カテゴリ: marketing-growth監査

BenedictKing's Agent Skills collection for Claude Code and compatible agents

13
Stars
64/100
信頼
カテゴリ: utility監査

A collection of Claude Code skills for marketing operations including SEO, content, email, ads, and growth planning.

25
Stars
68/100
信頼
カテゴリ: marketing-growth監査