TIanle-art/agent-vision-skill

Enables large language models without vision capabilities, such as DeepSeek V4, to understand images — compliant with the Agent Skills open standard and compatible across major agents including Claude Code, Codex, opencode, and Cursor.

2Stars on the repository

2Mods indexed here, across every type

1mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

vision

TIanle-art/agent-vision-skill

Skill Claude CodeCodex

An image-description tool for coding agents whose main model cannot view images directly. It sends local images or image URLs to a separate vision model and returns descriptions.

not rated 2 1mo ago A 121 tokens original MIT