Enables multimodal visual capabilities for Claude Code on a text-only LLM foundation, for screenshot, UI, and chart analysis; combined with browser-harness, it can automate frontend layout checks.
1 file for Claude Code: claude-code-vision-skill CLAUDE.md — 264 tokens loaded in every session.
CLAUDE.md A 264 tok These files are xiincs/claude-code-vision-skill's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.