全部能力

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Architectural guidance for building node-based UIs with React Flow. Use when designing flow-based applications, making decisions about state management,…

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

MiniMax API for AI models. Use when user mentions "MiniMax", "Chinese

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Python FastAPI backend development with async patterns, SQLAlchemy, Pydantic, authentication, and production API patterns.

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

Use when new translation keys are added to packages to generate new translations strings

Open source eBPF-based network monitoring and blocking components for Little Snitch on Linux

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's…

Document codebase as-is with thoughts directory for historical context

Get paid from day one. Payments, subscriptions, billing portal, webhooks, metered billing, Stripe Connect. The complete guide to implementing Stripe correctly,…

Meta-skill for creating and managing Claude Code skills

Skill Development Rules

CLI skill for Bilibili (哔哩哔哩, B站) with token-efficient YAML output for AI agents to browse videos, users, search, trending, dynamics, favorites, and…

Draft a long-form book review from your Reader highlights — synthesizing the book with your broader reading history to generate original arguments

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

Build agentic AI with OpenAI Responses API - stateful conversations with preserved reasoning, built-in tools (Code Interpreter, File Search, Web Search), and MCP integration. Prevents 11 documented errors. Use when: building agents with persistent reasoning, using server-side tools, or migrating from Chat Completions/Assistants for better multi-turn performance.

Security audit workflow - vulnerability scan → verification

使用 Clean Architecture 和 Hilt 搭建和维护现代 Android 应用架构的专家级指导。当询问关于项目结构、依赖注入、模块划分、Repository 模式、UseCase 设计以及 MVVM 与 Jetpack 组件集成时使用。涵盖 Hilt 模块配置、作用域管理、测试策略以及从 Dagger 迁移的最佳实践。适用于需要可扩展、可测试且符合 Android 官方规范的代码库设计场景。