Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
component-library
Conditionally installs GitHub Packages component library at latest version. Adds to package.json when user requests it.
majiayu000/claude-skill-registry 163
-
container-scanner
Scans containers and Dockerfiles for security issues. Wraps Hadolint for Dockerfile linting and Trivy for container image scanning. Use when user asks to "scan Dockerfile", "lint Dockerfile", "container security", "image scan", "Dockerセキュリティ", "コンテナスキャン".
majiayu000/claude-skill-registry 163
-
alphavantage-earnings
Consensus estimates and earnings data from Alpha Vantage.
majiayu000/claude-skill-registry 163
-
Backend API Integration
Generate production-ready Saloon-based API integrations for Laravel projects including connector classes, request classes, readonly DTOs, service layer methods with comprehensive error handling, and complete Pest test suites. Use this skill when integrating external APIs using Saloon, creating API request/response handlers, adding new API endpoints to existing services, building API client wrappers for third-party services, or setting up API communication with proper error handling and testing. This skill applies when working on files in app/Services/Api/, app/DataTransferObjects/Api/, creating Saloon connectors and requests, implementing API service methods, or writing API integration tests.
majiayu000/claude-skill-registry 163
-
chatgpt
OpenAI's conversational AI assistant.
majiayu000/claude-skill-registry 163
-
database-designer
Conçoit des schémas de base de données avec ERD, migrations, indexes et optimisations. Utiliser pour les projets avec persistence, quand on définit des modèles, ou quand l'utilisateur dit "database", "schema", "tables", "migrations". Peut être déclenché après PRD ou Architecture.
majiayu000/claude-skill-registry 163
-
surveymonkey
Create surveys and collect responses via SurveyMonkey API. Manage surveys, view results, and export data.
majiayu000/claude-skill-registry 163
-
coinank-data-analysis
使用 Coinank MCP 工具进行加密货币衍生品市场分析
majiayu000/claude-skill-registry 163
-
process-ambiguous-task
指示の最初でコンテキストが不足している場合に自動的に呼び出す必要があるスキルです
majiayu000/claude-skill-registry 163
-
android-watch-logs
Start real-time log streaming from connected Android device using adb logcat. Shows only app's log messages. Use when monitoring app behavior, debugging, or viewing Android logs.
majiayu000/claude-skill-registry 163
-
solid-router-actions
Solid Router actions: action() for mutations, useAction for programmatic calls, useSubmission/useSubmissions for tracking state, form submissions with FormData.
majiayu000/claude-skill-registry 163
-
anti-ai-validator
AI 탐지 가능 패턴을 감지하고 제거하는 독립 검증 스킬. 금지 표현, 반복 단어, 부자연스러운 구조를 탐지한다. 게시 전 콘텐츠를 검증하거나 AI 패턴을 자동 교정할 때 사용한다.
majiayu000/claude-skill-registry 163
-
auth-security
JWT authentication with Better Auth, token verification, user isolation, and security middleware. Use when implementing auth, protecting endpoints, or verifying tokens.
majiayu000/claude-skill-registry 163
-
zod-validation
Zodライブラリによるランタイムバリデーション、スキーマ定義、TypeScript型推論を専門とするスキル。
型安全なバリデーションロジックを設計・実装し、API・フォーム・ドメイン層での検証を網羅する。
Anchors:
• Zod Official Documentation / 適用: スキーマAPI・バリデーション / 目的: 公式パターン準拠
• Effective TypeScript (Dan Vanderkam) / 適用: 型設計・型推論 / 目的: ランタイム安全性担保
• @hookform/resolvers / 適用: フォーム統合 / 目的: React Hook Form連携
Trigger:
Use when implementing runtime validation with Zod, defining TypeScript schemas, integrating form validation (react-hook-form), or validating API requests/responses. Keywords: zod, schema, safeParse, refine, z.infer, zodResolver.
majiayu000/claude-skill-registry 163
-
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
majiayu000/claude-skill-registry 163
-
planning-with-files
将工作流转换为使用 Evan 风格的持久化 markdown 文件进行规划、进度跟踪和知识存储。适用于开始复杂任务、多步骤项目、研究任务，或者当用户提到规划、组织工作、跟踪进度或需要结构化输出时使用。
majiayu000/claude-skill-registry 163
-
uv-oneliners
UV/UVX awesome one-liners for ephemeral Python environments with multi-package stacks
majiayu000/claude-skill-registry 163
-
53-dapr-core
Create your Dapr deployment skill in one prompt, then learn to improve it throughout the chapter
majiayu000/claude-skill-registry 163
-
skill-creator-openai
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the model's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
csctf
Chat Shared Conversation To File - convert ChatGPT, Gemini, Grok, and Claude share links to clean Markdown + HTML transcripts with preserved code fences.
majiayu000/claude-skill-registry 163
-
api-request-builder
Build a basic HTTP request (curl or fetch) for an API. Use when a junior developer needs a quick request example.
majiayu000/claude-skill-registry 163
-
phase-plan-generate
Generate comprehensive plan documentation following Template 1 format. Use when creating plan.md files for new components or subsections.
majiayu000/claude-skill-registry 163
-
package-review
Public package tester for GitHub repositories. Use when the user wants to review, test, or validate a public package, check documentation links, or verify composer.json quality.
majiayu000/claude-skill-registry 163
-
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
majiayu000/claude-skill-registry 163