No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-vision-skill safe to install? View the security audit →
Claude Vision Skill 让没有识图能力的模型获得识图能力——把图片发给有 vision 的模型，用文字描述回来。 如果你是 AI（Claude Code），请读这里 用户把这个链接发给你，是想让你帮他配置识图。先确认信息，再按场景执行。 先确认 问用户： 想用哪个识图服务？ 推荐千问（ / ）：阿里云百炼，新用户 100 万 token 免费，约 0.02 元/次 也可以用 OpenAI（）或其他支持 OpenAI 兼容格式的 vision 模型 API Key 是什么？没申请的话引导去对应平台注册 （如果用非千问服务）API Base URL 是什么？ 场景 A：用户要在普通 Claude Code 项目里用 把这个仓库里的 下载到项目根目录 替换 里的 → 用户的 Key， → 模型名。如果用的不是千问，同步改 把 的内容合并到项目的 （没有就新建） 告诉用户：配置完成，以后直接发图片就行，AI 会自动识图 场景 B：用户要在 cyberboss 里用 先执行场景 A 的所有步骤 接着读这个仓库里的 ，按它说的改 persona 和 告诉用户：重启 cyberboss 后生效，微信里直接发图片就能识图 场景 C：用户只想了解这是什么 简要解释： 是核心，读取图片 → base64 → 发给 vision 模型 API → 返回文字描述 走 OpenAI 兼容格式，不绑定特定厂商 推荐千问是因为有免费额度；有别的便宜 vision API 也能用 配置好之后，用户直接发图片，AI 自动处理，无需手动打命令 如果你是人类，请读这里 这是什么 一个让 DeepSeek 等无 vision 能力的模型也能"看图"的脚本。配置好之后，直接发图片 AI 就会自动识别。 推荐识图服务 自动配置 方式一（推荐）：先把仓库 clone 到本地，然后告诉 Claude Code 本地路径： 然后在 Claude Code 里说： 读一下 claude-vision-skill/README.md，帮我配置识图 方式二：直接发 GitHub 链接（DeepSeek 等第三方模型可能无法访问 GitHub）：
| Stars | 1,810 |
| Forks | 85 |
| Language | JavaScript |
| Category | AI Tool |
| Quality Score | 36.6863922796863/100 |
| Open Issues | 6 |
| Last Updated | 2026-08-11 |
| Created | 2026-05-02 |
| Platforms | claude-code, node |
| Est. Tokens | ~2k |
These tools work well together with claude-vision-skill for enhanced workflows:
Looking for a claude-vision-skill alternative? If you're comparing claude-vision-skill with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
This tool has been deprecated. Use Agentic Document Extraction instead.
Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code
All powerful skills of ClaudeKit.cc!
A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report
A java agent to generate method mappings to use with the linux `perf` tool
Skills I use with Claude for shaping
Explore other popular ai tool tools:
claude-vision-skill is an open-source ai tool by asuojun with 1.8k GitHub stars.
claude-vision-skill is primarily written in JavaScript.
You can find installation instructions and usage details in the claude-vision-skill GitHub repository at github.com/asuojun/claude-vision-skill. The project has 1.8k stars and 85 forks, indicating an active community.
The top alternatives to claude-vision-skill on Agent Skills Hub include vision-agent, axton-obsidian-visual-skills, claudekit-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: