modlens
Text-only model can't see? Drop a path or URL, it takes over vision. No OCR, no PIL—cures the blind-to-images.
What does this skill do?
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .bmp, .heic) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: ]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also tri
Why is it worth installing?
Unlike OCR hacks, it delegates to a real vision model and overrides all DIY attempts—accurate and hassle-free.
How do you install it?
git clone --depth 1 https://github.com/liustack/modlens.git Then point your agent at the skill directory.
Where does it come from?
Repository: liustack/modlens 842 stars on GitHub at the time of listing. The repository ships 1 skills in total. Homepage: https://liustack.dev
← pi-research · creative-web →