LLM & Agents

Control Tuya devices via local Home Assistant (tuya-local) or Tuya Cloud using the tuya-hub Go CLI.

Comprehensive test suite generation with edge case coverage using PAL MCP. Use for creating tests, improving coverage, or identifying untested paths. Triggers on test generation requests, coverage improvement, or testing strategy.

This skill provides guidance for implementing robust Qdrant vector database integration with RAG (Retrieval Augmented Generation) systems, including proper async client handling, error management, and performance optimization.

Claude Code native tools reference. Prefer native tools over bash commands for file operations, search, and orchestration.

Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices

Manage Obsidian vault for persistent knowledge storage, search, and retrieval

Records agent execution results, performance metrics, and errors to SQLite database. Use after completing any agent task, when logging task results, or when an agent fails. Tracks success/failure rates and execution times for continuous improvement.

Unified UI development combining Anthropic's frontend-design plugin (anti-AI-slop aesthetics) with CIPS mobile-responsive-ui (dvh units, touch targets, testing protocol). Produces distinctive, production-grade, responsive interfaces.

AI agent and chatbot patterns including personas, pipelines, and messaging integrations. Use when building conversational agents, creating AI personas, designing insight pipelines, or integrating with Slack/Kakao platforms.

Intent-based code discovery for CLI AI agents using semantic search MCP tools. Use when finding code by what it does (not what it's called), exploring unfamiliar areas, or understanding feature implementations. Mandatory for code discovery tasks when you have MCP access.

Generate new Agent Skills following the open standard specification. Use this when asked to create a new skill, teach Copilot a new capability, or capture domain expertise as a reusable skill.

Complete RAG (Retrieval-Augmented Generation) pipeline implementation with document ingestion, vector storage, semantic search, and response generation. Supports FastAPI backends with OpenAI and Qdrant. LangChain-free architecture.

Trust-based bypass permissions earned through onboarding journey. Use when user asks about flow mode, bypass permissions, or wants to skip prompts.

Process aviation fuel surcharge bills from Excel files. Supports both automatic detection and Claude-assisted modes. Detects headers, matches columns, parses dates/routes, and fetches contract numbers via API. Use when working with aviation fuel bills, Excel file processing, or when user mentions fuel surcharges,航空燃油账单, or 燃油差价费.

Managing canvas operations in StickerNest including pan, zoom, selection, viewport, and canvas interactions. Use when implementing canvas navigation, selection tools, drag operations, viewport manipulation, or working with canvas coordinates. Covers useCanvasStore viewport, selection state, and gesture handling.

Configure and operate TinyDB for JSON-based document storage. Use when setting up databases, creating queries, or managing data persistence.

Expert in OCI Generative AI Dedicated AI Clusters - deployment, fine-tuning, optimization, and production operations

CloudBase platform knowledge and best practices. Use this skill for general CloudBase platform understanding, including storage, hosting, authentication, cloud functions, database permissions, and data models.

This skill enables honest, pressure-tested feedback on ideas, decisions, and proposals. Use this skill when prompted for an opinion on whether something is a good idea, should be done, or what to think about an approach.

Manage PowerShell profile, aliases, functions. Triggers: add alias, update profile, modify claude command, Microsoft.PowerShell_profile.ps1