85630 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

test-health-check-setup

Get alerts in Slack when your A/B tests need attention. Use when you want daily health checks for your Intelligems tests, need to know when conversion drops or traffic is low, or want to monitor statistical significance progress. Sends one message per test with clear status indicators. Great for single-brand monitoring.

victorpay1
victorpay1
1

spec:test

Execute Tests - walks through test cases from the test plan, collects results, and updates the plan. Use when verifying a feature implementation.

ikatsuba
ikatsuba
1

dev:create-skill

Create New Skill - scaffolds a skill definition following Claude Code conventions and this repository's patterns. Use when adding a new skill.

ikatsuba
ikatsuba
1

project:init

Project Init - defines the overall system goals, stakeholders, constraints, and shared architectural decisions. Use when starting a new multi-spec project.

ikatsuba
ikatsuba
1

git:commit

Smart Commit - stages all changes and creates a conventional commit

ikatsuba
ikatsuba
1

git:changelog

Generate Changelog - analyzes git history and creates a human-readable changelog for non-technical teams

ikatsuba
ikatsuba
1

git:amend

Amend Commit - modifies the last commit with staged changes or new message

ikatsuba
ikatsuba
1

spec:review

Review Specification - validates documents for completeness, quality, and consistency against the codebase. Use when checking spec quality at any pipeline stage.

ikatsuba
ikatsuba
1

spec:requirements

Requirements Analysis - gathers requirements through structured questions and produces a requirements document with testable acceptance criteria. Use when starting a new feature spec or documenting requirements.

ikatsuba
ikatsuba
1

spec:research

Technical Research - investigates the codebase and builds a catalogue of solution variants per problem area. Iterative — can be re-run to widen the catalogue. Does not make decisions; selection happens in spec:design.

ikatsuba
ikatsuba
1

project:status

Project Status - dashboard showing progress across all specs with dependency tracking and next action suggestions.

ikatsuba
ikatsuba
1

project:plan

Project Plan - breaks the vision into individual specs with dependencies, execution order, and shared interfaces. Use when decomposing a project into features.

ikatsuba
ikatsuba
1

journal:search

Journal Search - searches entries in ~/journal by query, type, project, topic, tags, or date range. Use when the user wants to find past thoughts, decisions, problems, or ideas they captured.

ikatsuba
ikatsuba
1

review:diff

Diff Review - analyzes code changes and provides structured feedback before commit

ikatsuba
ikatsuba
1

journal:promote

Journal Promote - graduates a journal entry into a new spec by seeding .specs/<name>/ with the entry's content, then linking the journal entry back. Use when the user wants to turn a captured idea, problem, or decision into a full specification.

ikatsuba
ikatsuba
1

review:investigate

Investigate Problem - analyzes a problem in the codebase and proposes actionable solutions

ikatsuba
ikatsuba
1

review:ux

UX Review - analyzes feature for efficiency-first UX patterns, keyboard navigation, and pro-tool experience

ikatsuba
ikatsuba
1

spec:design

Technical Design - picks one variant per problem area from the research catalogue, then produces architecture diagrams, interfaces, and data flow. Decisions live here, not in research.

ikatsuba
ikatsuba
1

spec:test-plan

Test Plan - creates a manual test plan with traceable test cases from specification documents. Use when preparing to verify a feature implementation.

ikatsuba
ikatsuba
1

agent:developer

Designs and builds AI agents. Use when working on agent architecture, prompts, model selection, tool design, MCP, memory, context engineering, RAG, graph workflows, multi-agent systems, evaluation, or production reliability.

ikatsuba
ikatsuba
1

spec:status

Spec Status - displays pipeline progress dashboard for a single specification showing document statuses, blockers, and next action.

ikatsuba
ikatsuba
1

dev:claude-audit

Claude Code Setup Audit - reviews CLAUDE.md hierarchy, .claude/settings.json deny-list, per-directory commands, and extension layer against best practices for large codebases. Use periodically (every 3-6 months or after a major model release) or when onboarding a new repo.

ikatsuba
ikatsuba
1

spec:implement

Implement Tasks - executes tasks from the tasks document using subagents. Use when ready to start coding a feature.

ikatsuba
ikatsuba
1

agent:audit

Agent Audit - audits an existing AI agent against the 22 patterns from "Patterns for Building AI Agents" and the 12 factors of production-reliable agents, emitting a scored maturity report with a security gate. Use when reviewing, scoring, or assessing the production-readiness of an AI agent or agent design.

ikatsuba
ikatsuba
1

spec:tasks

Task Breakdown - generates an implementation plan with tracked tasks based on requirements and design documents. Use when breaking down a design into actionable work items.

ikatsuba
ikatsuba
1

journal:capture

Journal Capture - captures a thought, problem, edge case, idea, or decision into ~/journal and updates README indexes. Use when the user wants to write down a development thought or observation.

ikatsuba
ikatsuba
1

react-testing-library

Write production-grade React tests with Testing Library, MSW, and comprehensive coverage patterns

pluginagentmarketplace
pluginagentmarketplace
1

react-router

Master React Router v6 for production routing with error boundaries, lazy loading, and navigation guards

pluginagentmarketplace
pluginagentmarketplace
1

react-hooks-patterns

Master React Hooks including useState, useEffect, useContext, useReducer, and custom hooks with production-grade patterns

pluginagentmarketplace
pluginagentmarketplace
1

component-library

Build production-grade, accessible, and tested component libraries with Storybook, Chromatic, and design tokens

pluginagentmarketplace
pluginagentmarketplace
1

redux-state-management

Master Redux Toolkit for production state management including slices, async thunks, RTK Query, and error handling

pluginagentmarketplace
pluginagentmarketplace
1

react-performance

Master React performance optimization with memoization, code splitting, profiling, and Web Vitals monitoring

pluginagentmarketplace
pluginagentmarketplace
1

next-js-framework

Build production-grade React apps with Next.js 14 App Router, Server Components, and Edge Runtime

pluginagentmarketplace
pluginagentmarketplace
1

implementing-ddd-tactical-patterns-with-zod

Zod でドメイン層のモデルを実装する。値オブジェクト、エンティティ、集約、DTO と変換を書くときに使う。「値オブジェクトを作って」「エンティティを追加して」「ドメインモデルを実装して」「集約を設計して」といった依頼で起動する。既存モデルの修正やレビューにも使う。

donngi
donngi
1

adr

アーキテクチャ決定記録(ADR)を作成・更新するスキル。ユーザーが「ADRを書いて」「アーキテクチャ決定記録を作成」「/adr」などと言った場合に使用。依頼された内容をADRのフォーマットに整形し、コードベースから背景・影響を推論して埋める。既存ADRをsupersedeする際の相互リンク更新などステータス管理にも対応。

donngi
donngi
1

terraform-aws-annotated-blueprint

全プロパティに詳細な解説が付いたTerraform AWSテンプレートを作成する。ユーザーが「/terraform-annotated-aws-blueprint」コマンドで構築したいインフラの概要を入力すると、Terraform Providerスキーマに基づいた正確な属性一覧と、AWS公式ドキュメントに基づく解説を含むテンプレートを生成する。

donngi
donngi
1

diagramming-domain-models

DDD(ドメイン駆動設計)のドメインモデル図を生成・更新するスキル。エンティティ・バリューオブジェクト・集約(境界と集約ルート)・リポジトリ・ドメインサービス・ドメインイベントの関係を、JSON 中間ファイル → 機械検証 → 自己完結 HTML として決定論的に描画する。既存コードのドメイン層からの逆生成、対話でのゼロからのモデリング、既存 .model.json への集約追加・更新のすべてに対応。ユーザーがドメインモデル・集約・エンティティ・バリューオブジェクト・ユビキタス言語・境界づけられたコンテキストについて「図にして」「可視化して」「整理して」「一覧が見たい」「レビューしたい」「資料を作りたい」「全体像を把握したい」と求めたら、「ドメインモデル図」という言葉を使っていなくても必ずこのスキルを使うこと(例:「ドメインモデル図を作って」「DDD でモデリングして」「集約境界を見直したい」「どのクラスが集約ルートでどれが VO か図で見たい」「domain model diagram」「ドメイン層を図に起こして」「.model.json に集約を追加して」)。自分で Mermaid や独自 HTML を書いて済ませず、また対象コードの調査やファイル探索を始める前に、**他のツールより先にまず本スキルを起動すること**(どのコードを読んでよいかの制約を本スキルが定義するため。先に探索すると非ドメイン要素が図に混入する)。対象外: ER 図・DB スキーマ図、DDD 以外の一般的なクラス図、ユースケース図、シーケンス図、画面遷移図、インフラ構成図、DNS のドメイン設定。

donngi
donngi
1

terraform-aws-annotated-reference

単一のTerraform AWSリソースに対する全プロパティ解説付きリファレンステンプレートを生成する。ユーザーがリソース名(例:aws_s3_bucket, aws_lambda_function)を指定すると、Providerスキーマに基づいた正確な属性一覧とAWS公式ドキュメントに基づく解説を含むテンプレートを出力する。「aws_xxxのテンプレートを作成して」「aws_xxxの全プロパティを教えて」などのリクエストで使用。

donngi
donngi
1

aws-terraform-personal-style

DonngiのAWS Terraform個人スタイルで新規コードを書く・既存コードをレビューする。envs/modules構成、meta objectによるmodule合成、IAM 3リソース1ファイル、Sid必須のinline policy、S3 native state locking、日本語コメントなどの規約に従う。Terraformで `.tf` ファイルを新規作成・編集する時に使用する。

donngi
donngi
1

commit

コミット規約に沿ったコミットを作成する(変更の分類・分割も自動判断)。ユーザーが「コミットして」「変更をコミット」「/commit」などと言った場合に使用。Conventional Commitsを基本とした規約に従い、適切なtype/scope/subjectを自動生成。複数の論理単位に分割すべき変更は自動判断して複数コミットに分割する。

donngi
donngi
1

skill-converter

スキルを各AI Agent固有のフォーマットに変換する。「スキルを変換」「convert skill」などと言われたときに使用する

donngi
donngi
1

frontend-i18n-orchestrator

End-to-end i18n orchestration for frontend repositories. Use when a user wants to internationalize React/Vue/Next/Nuxt/Vite projects with minimal questions: auto-detect stack and current i18n state, ask only unresolved business decisions, migrate hardcoded strings to locale keys, localize formatting and routing/SEO, and enforce CI quality gates.

howell5
howell5
1

check-claude-md

检查本次对话的改动是否需要更新项目 CLAUDE.md。分析代码变更,识别新模式和约定,建议更新内容。

howell5
howell5
1

vitepress-tutorial

Generate VitePress documentation sites for source code learning and analysis. Use when creating tutorials that explain how a codebase is implemented internally.

howell5
howell5
1

social-polish

从核心观点生成优质社媒长文。运用 4D 框架深度分析选题,去除 AI 味,6 维度评审确保质量。

howell5
howell5
1

graphify

Use when exploring unfamiliar codebases, before searching for code, or after editing files. Builds a structural AST index (classes, functions, imports, call graph) from 12 languages via tree-sitter. Trigger: /graphify

howell5
howell5
1

subtraction-audit

|

howell5
howell5
1

react-three-game

Build and edit React Three Game scenes using WebGPU rendering, React Three Fiber composition, prefab components and the editor API for agents.

prnthh
prnthh
1

agent-config-import

|

hikaruegashira
hikaruegashira
11

codex-as-tools

|

hikaruegashira
hikaruegashira
11

Page 1384 of 1713 · 85630 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.