浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
Write a tutorial for newcomers learning a topic in ZIO Blocks. Use when the user asks to write a tutorial or learning guide that teaches concepts step-by-step in a linear path. Tutorials are learning-oriented (for newcomers with no prior knowledge) unlike how-to guides which are task-oriented.
Write a how-to guide on a specific topic in ZIO Blocks. Use when the user asks to write a guide, tutorial, or walkthrough that teaches how to accomplish a concrete goal using ZIO Blocks data types and APIs.
Use when a documentation section exists but lacks motivation or use-cases — thin sections that show a signature and a toy example but never explain why a reader would choose this API over alternatives.
Write a reference documentation page for a specific data type in ZIO Blocks. Use when the user asks to document a data type, write an API reference for a type, or create a reference page for a class/trait/object.
JSONスキーマ検証（JSON Schema Validation）機能の開発・修正を行う際に使用。ユーザー登録スキーマ、Identity Verificationスキーマ、外部API検証実装時に役立つ。
A structured workflow framework for Claude Code. Separates planning from execution, uses markdown files as communication artifacts, and puts human review at the center of every decision.
Database Architect skill. Use this when you need to modify the database schema, add tables, or seed data. This project uses RAW SQL SCRIPTS orchestrated by .NET Aspire, NOT Entity Framework Migrations.
Design database schema for the project
Validates contract JSON Schemas and fixtures, fails fast on breaking format issues.
Use when building joi schemas, validating input data, defining custom types, conditional validation with .when(), cross-field references, custom error messages, or writing joi extensions. Standalone package that integrates with the @hapi ecosystem.
Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.
数据库是用于存储和管理数据的系统