Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...

aiwコマンドを活用して複数AIエンジンによる並列実装・評価・採用を行うスペシャリスト。複雑な実装で複数アプローチを比較したい時、AIエンジン間の品質比較、高信頼性が求められる実装に使用。

为通用 AI 助手安装技能。当用户请求列出可用技能、从 Git 仓库（GitHub/GitLab/Gitea）或本地目录安装技能到特定 AI 助手（Codex、Roo、Claude、Copilot、Cursor 等）的指定作用域时使用此技能。

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Git/PRの番人。変更の本質を見極め、適切な粒度・命名・戦略を提案する。PR準備、コミット戦略が必要な時に使用。

Trigger AI analysis for your data assets. Handles "analyze my database", "generate intelligence", "refresh analysis", "update AI knowledge".

Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development.

Design agentic AI systems for enterprise/banking clients. Use when advising on AI architecture, scoping agent projects, or creating design deliverables.

AI as TDD pair programmer with role-based collaboration. Use when you want to collaborate on TDD with the AI taking a specific role (driver, navigator, or alternating).

Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.

Удаляет следы AI-генерации из текста. Делает текст естественным и человечным. Основан на руководстве «Признаки AI-текста» из Википедии.

Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.

Query multiple AI agents in parallel for diverse perspectives. Use when you want multiple viewpoints on a question, to compare approaches, or to find consensus among AI models.

PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification...

Apple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, and intelligent assistants. Use when implementing AI-powered features.

Session memory that compounds - remember decisions, patterns, and corrections across AI coding sessions. Includes standards injection for consistent code quality.

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

Create flexible annotation workflows for AI applications. Contains common tools to explore raw ai agent logs/transcripts, extract out relevant evaluation data, and llm-as-a-judge creation.

AI-powered WeChat message assistant. Retrieve recent messages from contacts/groups and send messages directly through AI chat. Windows 10/11 only. Requires WeChat PC client logged in.

Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.