Create and update ai-context.md files that document modules for AI assistants. Use when adding documentation for packages, apps, or external references that should be discoverable via /modules commands.
Build production AI agents with Pydantic AI: type-safe tools, structured output, embeddings, MCP, 30+ model providers, evals, graphs, and observability.
Extract learnings from session transcripts or notes and incorporate them into existing skills or create new ones. Use when the user has analysis documents, session learnings, or patterns they want...
Guide for creating or updating Agent Skills using the standardized SKILL.md specification, including naming rules, optional frontmatter fields, validation, packaging, and best practices for...
Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and...
Convert AGENTS.md (or similar agent instruction docs) into reusable Codex skills. Use when asked to extract, split, or refactor AGENTS.md guidance into skill folders, or to create skills that...
智能桌面和目录整理工具。根据用户提示词自动分类、整理文件和应用程序图标，去除重复版本，生成整理报告。支持整理桌面或指定目录。
Define and implement AI tools using @effect/ai's Tool and Toolkit APIs. Use when building LLM integrations with type-safe tool definitions, parameter validation, and handler implementations....
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...
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...
>
Generate high-quality Claude Agent Skills following Anthropic's official guidelines and best practices. Creates properly structured SKILL.md files with YAML frontmatter, progressive disclosure,...
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and...
AI agent skill to generate optimized Open Graph and Twitter card metadata for Next.js portfolio websites.
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety...
Intelligent project management dashboard - view all projects status, priorities, and todos from a CEO perspective
Query financial accounts, balances, transactions, and spending via Plaid. Connect bank accounts and retrieve real-time balance and transaction data. Use when the user asks about bank balances,...
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual...
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies