发现 Skills

Professional trading UI design principles — monospace-forward typography, zero-radius sharp corners, grid-based layouts, density, two-hue color, panel architecture, data display conventions. Stack-agnostic guide for building interfaces that prioritize signal through noise. Use when designing, implementing, or reviewing trading UI.

A complete front-end and back-end web application generation skill pack; trigger this skill when a user needs to rapidly generate a web application.

React component development guide. Use when working with React components (.tsx files), creating UI, using @lobehub/ui components, implementing routing, or building frontend features. Triggers on React component creation, modification, layout implementation, or navigation tasks.

Lightweight triage to decide how often to re-check critical work (services, agents, runtimes) while changes are in-flight. Use to avoid forgetting fragile tasks.

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.

```markdown

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Ollama is a lightweight tool for running large language models locally. It provides a simple CLI and REST API interface for downloading, managing, and serving open-source LLMs like Llama, Gemma, Mistral, and DeepSeek on your own hardware with minimal configuration.

Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Modern web development expertise covering React, Node.js, databases, and full-stack architecture. Use when: building web applications, developing APIs, creating frontends, setting up databases, deploying web apps, or when user mentions React, Next.js, Express, REST API, GraphQL, MongoDB, PostgreSQL, or full-stack development.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Remove traces of AI generation from text. Suitable for editing or reviewing text to make it sound more natural and more like human writing. Based on Wikipedia's comprehensive guide to 'AI Writing Features'. Detect and fix the following patterns: exaggerated symbolism, propagandistic language, shallow analysis ending in -ing, vague attribution, overuse of dashes, three-part rule, AI vocabulary, negative parallelism, excessive connective phrases.

This skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. It is triggered when the user requests assistance with fine-tuning a model, adapting a pre-trained model to a new dataset, or performing transfer learning. It analyzes the user's requirements, generates code for adapting the model, includes data validation and error handling, provides performance metrics, and saves artifacts with documentation. Use this skill when you need to leverage existing models for new tasks or datasets, optimizing for performance and efficiency.

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...

Run DeepSeek V3.2 LLM via Atlas Cloud API for coding, reasoning, and analysis. 685B parameter model at $0.26/M tokens with 164K context. Use when user asks to "analyze code with DeepSeek" or "use DeepSeek for reasoning".

Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.

Convert PDF files to Markdown using the MinerU API. Use when Kimi needs to extract structured text, images, tables, and formulas from PDF documents while preserving document layout and formatting. Supports batch conversion and outputs a full.md file with an images/ directory, JSON metadata, and other extracted assets. Now supports very large PDFs (600+ pages) through automatic splitting and merging.

Generate images using Flux (Black Forest Labs) via Atlas Cloud API. $0.012/image, LoRA support, NSFW mode, inpainting. Use when user asks to "generate an image with Flux" or "create a cheap AI image".

Two Codex MCP servers must be configured in the global `settings.json`:

Generate AI videos using Kling (Kuaishou) models via Atlas Cloud API. Supports text-to-video, image-to-video, 4K, multi-shot, avatar, motion control. Use when user asks to "generate a video with Kling" or "create a 4K video".

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges.

Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.