LLM & Agents

Use to review OpenAI API integrations for correctness (endpoints, params, auth, response handling) and robustness.

Connect to and interact with Azure Blob Storage (ADLS Gen2). Use when working with Azure blob storage, listing containers, reading files, uploading data, or when user mentions Azure storage, blob containers, or ADLS. Handles authentication, container operations, and blob management.

Unified Twitter/X API client for retrieving user info and tweets via twitterapi.io. Supports user lookup and advanced tweet search with a clean Typer-based CLI and agent-friendly Python interface.

Use this skill when evaluating portfolio risk, checking position sizes, assessing market volatility, or performing risk management checks before trade execution. Based on TradingAgents risk management framework with conservative/aggressive/neutral debate system.

Enterprise AI security patterns - LLM vulnerabilities, prompt injection defense, guardrails, PII protection, and OWASP LLM Top 10 mitigations

Work with imp.lib and imp.gits for Nix flake development. Use when working with imp.lib directory imports, imp.gits multi-repo injection, .d fragment directories, flake-parts integration, or when the user mentions imp, imp.lib, imp.gits, or asks about directory-based Nix configuration.

Enhanced feature development combining Anthropic's feature-dev plugin (7-phase workflow, multi-agent exploration) with CIPS design principles (SOLID, GRASP, DRY, KISS, YAGNI, YSH) and efficiency rules (file read optimization, mental model caching).

Unified markdown and skill management specialist providing document quality enforcement (structure, style), content optimization for AI assistants, complete skill creation workflow (scaffolding, validation, packaging), ASCII flowchart creation for visualizing complex workflows, user journeys, and decision trees, and install guide creation for MCP servers, plugins, and tools.

Advise on choosing between Skills, Commands, Subagents, and Hooks for Claude Code. Analyze user requirements and recommend the appropriate artifact type with justification. Use when user asks "should I use a skill or command", "what artifact type", "skill vs command", or describes a workflow needing automation.

PostgreSQL VPS database expert. Manages database creation, Prisma schemas, migrations, seeding. Auto-activates on keywords "database", "postgresql", "prisma", "db", "sql" or when backend with data storage needed.

Dynamic task distribution, work-stealing algorithms, queue management, and adaptive load balancing. Use for optimizing task execution across agents, preventing overload, and maximizing throughput.

Use this skill in the scenario of intelligent agent application development.

Comprehensive guide for the Cloudflare Agents SDK - build AI-powered autonomous agents on Workers + Durable Objects.Use when: building AI agents, creating stateful agents with WebSockets, implementing chat agents with streaming, scheduling tasks with cron/delays, running asynchronous workflows, building RAG (Retrieval Augmented Generation) systems with Vectorize, creating MCP (Model Context Protocol) servers, implementing human-in-the-loop workflows, browsing the web with Browser Rendering, managing agent state with SQL, syncing state between agents and clients, calling agents from Workers, building multi-agent systems, or encountering Agent configuration errors.Prevents 15+ documented issues: migrations not atomic, missing new_sqlite_classes, Agent class not exported, binding name mismatch, global uniqueness gotchas, WebSocket state handling, scheduled task callback errors, state size limits, workflow binding missing, browser binding required, vectorize index not found, MCP transport confusion, authentic

효과적인 SKILL을 제작하기 위한 가이드입니다. 특화된 지식, 워크플로우 또는 도구 통합을 통해 Claude의 기능을 확장하는 새로운 SKILL을 생성하거나 기존 SKILL을 업데이트하려는 경우 이 SKILL을 사용하세요.

PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows

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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Creates and configures HTTP with Server-Sent Events Model Context Protocol (MCP) server connections for OpenAI Agents SDK

This skill guides creating autonomous agents for Claude Code plugins using markdown files with YAML frontmatter. Use when building new agents, designing agent system prompts, or configuring agent behavior.

Core test infrastructure patterns for monorepo Vitest setup including global configuration, browser API polyfills, mocking patterns, test cleanup, directory structure, and coverage philosophy. Use when setting up Vitest test infrastructure, configuring test environments, implementing test utilities, or establishing test standards. Triggers on: vitest setup, test configuration, test infrastructure setup, test mocking patterns, test cleanup, test standards, monorepo testing.

Analyzes tasks and recommends the optimal agent pattern from Anthropic's Building Effective Agents. Provides pattern selection guidance based on task complexity, structure, and requirements. Use this as the entry point when unsure which pattern (Sequential, Router, Parallel, Orchestrator, Evaluator) fits your task best.