liustack

Help text-only models work with images by converting visible text, layout, meaning, and visual clues into structured JSON. The skill also guides configuring image analysis providers and reporting unclear details from the returned evidence.

中文简介正在准备中。当前显示英语简介。

• Reading text from an image with a text-only model
• Checking image layout and visual clues
• Locating pasted images for analysis

Search the web or X and fetch pages through the modsearch CLI when an agent environment lacks native search or fetch tools. It returns structured evidence with links and caveats, and can also guide setup and engine configuration.

中文简介正在准备中。当前显示英语简介。

• Searching for current facts and source links
• Finding posts or discussions on X
• Fetching and extracting content from a URL

Generate a native, editable PPTX deck from an outline, notes, or source material with the PPTwise CLI. Use when the user asks to create a PPT, deck, presentation, or slides and wants a deterministic, editable, theme-consistent result.

中文简介正在准备中。当前显示原文说明。