# asuojun/claude-vision-skill

Repository: https://github.com/asuojun/claude-vision-skill
Canonical: https://ross.abutalabs.com/products/claude-vision-skill
Language: JavaScript
License Family: other
Last push: 2026-08-11T08:53:30+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 8
- inputs: {"age_days": 123, "days_push": 22, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2229, forks 116 (observed 2026-08-28T04:06:28.993968+00:00)

## What it is
A small JavaScript skill/script that gives vision-less LLM setups (like Claude Code with DeepSeek) image understanding by sending images to an OpenAI-compatible vision model API and returning a text description. It ships as vision.js plus CLAUDE.md instructions for automatic configuration.

## Use cases
- add image recognition to claude code
- let deepseek describe images
- send pictures to a chatbot without vision
- image captioning via qwen vl api
- openai-compatible vision proxy script
- auto-configure vision for ai coding assistant

## When to choose
- your model or agent lacks native vision but you can access an OpenAI-compatible vision API
- you use Claude Code and want drop-in image understanding
- you want a cheap configurable vision bridge (e.g., Qwen free tier)

## When to avoid
- your model already has native vision support
- you need a production service with proper API key management rather than a hardcoded-key script
- you cannot use any external vision API

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, sdk, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, cross-platform
- tags: claude-code, vision-skill, multimodal, openai-compatible, image-captioning, qwen-vl, mcp-like-skill, nodejs

## Member repositories
- asuojun/claude-vision-skill (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:28.993968+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:40.186570+00:00, confidence not recorded.
  - readme: https://github.com/asuojun/claude-vision-skill (fetched 2026-08-28T04:06:28.993968+00:00, sha d1e6b3deae63)
- Data as of 2026-08-30T08:39:29.467469+00:00.