Agent Skills by xjtlumedia
Showing 15 vetted skills indexed across 1 GitHub repositories.
XJTLUmediapersonal-blog
Operate a personal blog platform through standardized MCP tools.
XJTLUmediaLLM
Implement large language model chat completion for conversational AI applications.
XJTLUmediaweb-reader
Extract structured content and metadata from public web URLs.
XJTLUmediaimage-generation
Generate images from text prompts via the z-ai-web-dev-sdk.
XJTLUmediaVLM
Analyze images, videos, and documents via the createVision API.
XJTLUmediacanvas-design
Generates original visual art and static designs as PNG and PDF files.
XJTLUmediaASR
Convert spoken audio files into written text transcriptions.
XJTLUmediaweb-search
Execute targeted web searches with customizable result limits and recency filters.
XJTLUmediaTTS
Convert input text into WAV, MP3, or PCM audio files.
XJTLUmediaVideo Generation
Generate videos from text prompts or input images with configurable output parameters.
XJTLUmediafrontend-design
Convert UI style requirements into accessible frontend code with design tokens.
XJTLUmediaxlsx
Create and edit Excel spreadsheets with openpyxl, pandas, and LibreOffice.
XJTLUmediaExtract text and tables from PDFs using pypdf, pdfplumber, and reportlab.
XJTLUmediapptx
Create, edit, and analyze PowerPoint .pptx files with templates and HTML.
XJTLUmediadocx
Create, edit, and analyze Word .docx documents via JavaScript and Python interfaces.