Sizhou Chen
Community@jjyaoao · China
I am interested in LLM Agent、Audio、Speech.
Agent Skills by Sizhou Chen
Showing 17 vetted skills indexed across 1 GitHub repositories.
jjyaoaoTTS
Convert text to speech audio via the z-ai-web-dev-sdk backend.
jjyaoaopptx
Redirect PPT and PPTX tasks to AI PPT mode for slide handling.
jjyaoaovideo-understand
Analyze video content to extract scenes, actions, and events via video_url inputs.
jjyaoaoimage-generation
Generate AI images from text prompts via CLI or backend SDK.
jjyaoaoAutomate PDF text extraction, form filling, and metadata management with Python libraries.
jjyaoaoPodcast Generate
Convert input files or web searches into podcast scripts and WAV audio.
jjyaoaoVLM
Analyze images and generate natural-language responses using image URLs or base64-encoded images.
jjyaoaoASR
Transcribe base64-encoded audio into text using the z-ai-web-dev-sdk.
jjyaoaoweb-reader
Fetch web pages and extract title, HTML, and publication time.
jjyaoaofinance
Retrieve real-time and historical finance data via gateway-based API endpoints.
jjyaoaoxlsx
Automate Excel workbook creation, editing, and analysis with formula preservation.
jjyaoaoweb-search
Queries the internet via z-ai-web-dev-sdk to return structured search results.
jjyaoaogift-evaluator
Analyze uploaded gift images to determine authenticity, value, and social context.
jjyaoaoVideo Generation
Generate videos from text prompts or images using the z-ai-web-dev-sdk.
jjyaoaofrontend-design
Translate UI design goals into token-driven frontend design systems.
jjyaoaodocx
Create and edit Word documents with tracked changes and comments via Python OOXML.
jjyaoaoLLM
Implement multi-turn chat completions with the z-ai-web-dev-sdk.