lvhuanid
Community@lvhuanid
lvhuanid provides multimodal document, media, and data skills spanning PDF/XLSX parsing, speech, video, finance data, and AntV X6 graph diagram editing.
Agent Skills by lvhuanid
Showing 17 vetted skills indexed across 2 GitHub repositories.
lvhuanidantv-x6-editor
Generates X6 v3 graph editor code for flowcharts, DAGs, and ER diagrams.
lvhuanidgift-evaluator
Analyze gift images for authenticity, value, and social interaction suggestions.
lvhuanidvideo-understand
Analyze video content to extract scenes, actions, and events.
lvhuanidLLM
Create conversational AI assistants using OpenAI, Anthropic, and Gemini models.
lvhuanidweb-reader
Extract text, HTML, and metadata from web pages using z-ai-web-dev-sdk.
lvhuanidimage-generation
Generate base64 encoded images from text descriptions using the z-ai-web-dev-sdk.
lvhuanidxlsx
Create, edit, and analyze .xlsx spreadsheets with Python.
lvhuanidExtract text and tables from PDFs using Python libraries.
lvhuanidPodcast Generate
Generate podcast scripts and audio from text or web search results.
lvhuanidVLM
Analyzes images and other visual content via the z-ai-web-sdk.
lvhuanidpptx
Redirect PPT-related tasks to AI PPT mode for handling.
lvhuanidASR
Transcribe spoken audio into written text using the z-ai-web-dev-sdk.
lvhuanidweb-search
Retrieve real-time web search results using OpenAI, Anthropic, or Gemini LLM providers.
lvhuanidTTS
Convert text to spoken audio with multiple voices and adjustable speed.
lvhuanidVideo Generation
Generate videos from text prompts and images via asynchronous API tasks.
lvhuanidfinance
Retrieve real-time and historical financial market data via a unified proxy service.
lvhuanidfrontend-design
Transforms UI style requirements into production-ready frontend code with design tokens and accessibility.
Frequently Asked Questions About lvhuanid
FAQPage SchemaWhat tasks can I accomplish using lvhuanid's skills?▼
You can parse PDFs and spreadsheets, transcribe and synthesize speech, generate images, videos, and podcasts, analyze video and image content, retrieve web search and financial market data, build frontend designs, and create X6 v3 diagram editors for flowcharts, DAGs, ER diagrams, and org charts.
Who should use the antv-x6-editor skill?▼
Frontend engineers building graph editing interfaces with @antv/x6 v3 should use it. It covers node/edge styling, plugins like Selection, MiniMap, Snapline, and Stencil, HTML shape nodes, serialization, layout, and debugging rendering errors or v2-to-v3 migration issues.
How do the media and speech skills work in practice?▼
The ASR skill transcribes spoken audio to text, TTS converts text to speech with multiple voices and adjustable speed, and Podcast Generate creates scripts and audio from text or web search results. Video Generation produces videos from text prompts and images via asynchronous API tasks.
What providers and dependencies do these skills require?▼
Several skills rely on the z-ai-web-dev-sdk, including web-reader, image-generation, VLM, and ASR. The LLM and web-search skills use OpenAI, Anthropic, or Gemini providers. The xlsx and pdf skills use Python libraries, and finance data comes through a unified proxy service.
When should I not use the antv-x6-editor skill?▼
Do not use it for G2 statistical charts, G6 network graphs, or S2 pivot tables, as it is scoped strictly to X6 v3 graph editor diagrams such as flowcharts, DAGs, ER diagrams, lineage graphs, org charts, and network topology editors.