Killer-Skillsディレクトリで数千のAI Agentスキルを探索・インストール。Claude Code、Windsurf、Cursorなどに対応。
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatch, describe, grep, sample.
Update documentation to match code and design changes in this repo. Use when code or design changes cause drift in Rust doc comments (module-level //! and item-level ///), non-doc comments, and README.md. Focus on intent, rationale, invariants, and relationships between major symbols rather than restating obvious names or signatures.
Build a secure filesystem operations tool for Docker sandbox environments using the Loopstack framework
Universal Context Architecture. One source of truth for Cursor, Claude Code, GitHub Copilot, Gemini, Amazon Q, and 19+ AI coding assistants.
Creates detailed, step-by-step task lists in Markdown format from user requirements, feature requests, or existing documentation. Use when the user asks to create a task list, break down a feature into tasks, generate implementation steps, or needs a structured development plan.
Privacy-preserving ERC-4337 wallet development for vehicle identity and sensitive data protection. Use when implementing ERC-4337 account abstraction wallets that handle sensitive information (vehicle license plates, biometric data, personal IDs) requiring on-chain privacy. Triggers on requests like implement ERC-4337 wallet for vehicle, create privacy-protected account abstraction, build wallet with vehicle number privacy, develop ERC-4337 with ZK proof integration, or any smart contract wallet development requiring commitment schemes, deterministic address generation, and sensitive data protection.
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
MemoryLane gives Claude Code durable project memory by extracting knowledge locally and injecting only what matters.
Gracefully wrap up current work before agent shutdown. Use when you need to kill and restart agents.
Microsoft Agent Framework は AI エージェントを構築、デプロイするためのフレームワークです
Audit and refactor CSS to comply with Game Loopers design system and BEM methodology
My personal website