自然語言處理

Research-driven design methodology producing unique, context-appropriate frontends. Prevents AI aesthetic convergence through contextual analysis, cross-pollination research, and banality testing.

Generate high-quality training datasets from documents, text corpora, and structured content. Use when creating AI training data from dictionaries, documents, or when generating examples for machine learning models. Optimized for low-resource languages and domain-specific knowledge extraction.

Generates standardized agent handoff documents for phase transitions. Ensures critical information is preserved and passed between agents during workflow orchestration. Automates handoff creation to prevent implementation failures from missing context.

Interactive prompt patterns for CLI tools with text, list, checkbox, password, autocomplete, and conditional questions. Use when building CLIs with user input, creating interactive prompts, implementing questionnaires, or when user mentions inquirer, prompts, interactive input, CLI questions, user prompts.

Navigate index.md files generated by the catalogador tool to identify the minimal set of documents or sections to read. Use this skill when exploring directories that contain index.md files, when attempting to read documentation in indexed folders, or when optimizing context usage by reading only relevant sections instead of entire documents.

Assess and validate translation quality between Chuukese and English with cultural context awareness, linguistic accuracy checking, and automated quality metrics. Use when evaluating translation outputs, building quality control systems, or validating translation models.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Build Model Context Protocol servers for Claude Code integration

Generates comprehensive planning documentation for web application projects, structuring work into context-safe phases with built-in verification criteria. Creates IMPLEMENTATION_PHASES.md, DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, and other planning docs based on project needs. Optimized for Cloudflare Workers + Vite + React stack. Use when starting new projects, adding major features, or restructuring existing work into manageable phases.Keywords: project planning, planning documentation, IMPLEMENTATION_PHASES.md, DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, UI_COMPONENTS.md, TESTING.md, AGENTS_CONFIG.md, phased development, context-safe phases, verification criteria, exit criteria, planning docs generator, web app planning, Cloudflare Workers planning, Vite React planning, project structure, project phases, major features planning, new project setup

Instrument RAG retrieval, memory operations, and context management

Mint new ordinals/NFTs on BSV blockchain using js-1sat-ord SDK. Inscribe images, text, or files as permanent on-chain assets.

This skill helps capture unstructured thoughts (via text or voice) across multiple turns and converts them into structured memos that are saved to a Notion inbox database. Use when the user wants to create a memo, capture thoughts, or provide content that should be documented verbatim without analysis or response.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Implementation Agent: Full TDD workflow in a single context window. Writes tests, implements code, and iterates until all tests pass.

Generate and edit images using the Gemini API (Nano Banana Pro). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Advanced CV for infrastructure inspection including forest fire detection, wildfire precondition assessment, roof inspection, hail damage analysis, thermal imaging, and 3D Gaussian Splatting reconstruction. Expert in multi-modal detection, insurance risk modeling, and reinsurance data pipelines. Activate on "fire detection", "wildfire risk", "roof inspection", "hail damage", "thermal analysis", "Gaussian Splatting", "3DGS", "insurance inspection", "defensible space", "property assessment", "catastrophe modeling", "NDVI", "fuel load". NOT for general drone flight control, SLAM, path planning, or sensor fusion (use drone-cv-expert), GPU shader development (use metal-shader-expert), or generic object detection without inspection context (use clip-aware-embeddings).

Convert Wiki-style image links to Markdown format with AI-generated descriptions. Use when preprocessing markdown files for PPT generation, converting ![[image.png]] to  format, or enabling text-based image understanding.

Extract a small, high-signal context packet around ripgrep matches (bounded by hits/files/output budget) for fast LLM consumption.

Meta-skill that wraps reasoning skills to capture notes in real-time, protecting against context compression. Creates checkpoint files during reasoning sessions.

Senior-level React and Tailwind CSS development expert with 10+ years experience. Automatically audits, generates, and optimizes React applications with focus on hooks, Context API, performance, security, and modern Tailwind styling. Use for React component generation using TypeScript, hook optimization, security audits, responsive design implementation, animation, Context API patterns, performance optimization, and project structure analysis. Ensures clean code, prevents backend data exposure, and follows senior-level best practices.