claude-code-vision-skill — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 →

by xiincs · Claude Skill · ★ 171

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claude-code-vision-skill safe to install? View the security audit →

About claude-code-vision-skill

Claude Code Vision Skill 为 Claude Code 提供多模态视觉能力,支持多种视觉模型分析截图、UI、图表。 专为使用 DeepSeek 等无多模态能力的模型作为 Claude Code 底座的用户设计。 本 skill 搭配 browser-harness skill 使用,驱动前端页面布局检查。 支持的模型 安装依赖 需要 Python 3.10+。 包仅在使用 时才会被导入,其他 provider 不受影响。 Claude Code 安装流程(给 Claude Code 看的指令) When the user asks you to install this skill, follow these steps IN ORDER. Do NOT skip any step. Step 1 — 询问用户 使用 AskUserQuestion 询问以下信息: 选择 provider:doubao / qwen / openai / anthropic(可多选) API Key:每个 provider 的 API key 默认 provider(多选时):选哪个作为默认 Step 2 — 运行安装脚本 可重复, 必须带上。 Step 3 — 合并 CLAUDE.md(如果 install.py 未自动完成) 如果未使用 ,则手动合并: 读取项目根目录的 检查 是否已有 标记 如果有标记 → 替换标记之间的内容 如果没有标记 → 追加到文件末尾(带标记) 此步骤不可跳过 Step 4 — 验证安装 手动安装 bash 交互式安装(你自己操作时) python install.py 预览 python install

agent-skillsanthropicclaude-codeclaude-skillsdeepseekmultimodalpythonqwenvision

Quick Facts

Stars171
Forks8
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score67.2146411023366/100
Last Updated2026-08-25
Created2026-05-21
Platformsbrowser, claude-code, python
Est. Tokens~6k

claude-code-vision-skill alternative? Top 6 similar tools

Looking for a claude-code-vision-skill alternative? If you're comparing claude-code-vision-skill with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • bridgic by bitsky-tech · ⭐ 150

    Bridgic is the next-generation agent development framework for building intelligent systems.

  • dsclaude by Agents365-ai · ⭐ 59

    Claude Code & Desktop launchers for 11+ third-party LLM backends (DeepSeek, Qwen, Kimi, GLM, MiniMax, Doubao,

  • SkillForge by tripleyak · ⭐ 855

    A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baselin

  • digital-marketing-pro by indranilbanerjee · ⭐ 795

    An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti

  • claude-skills-marketplace by mhattingpete · ⭐ 659

    Claude Code Skills for software engineering workflows - Git automation, testing, and code review

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is claude-code-vision-skill?

claude-code-vision-skill is 为 Claude Code 赋能多模态视觉能力,适配 纯文本 LLM 底座,用于截图 / UI / 图表分析;搭配 browser-harness 可做前端布局自动化检查。. It is categorized as a Claude Skill with 171 GitHub stars.

What programming language is claude-code-vision-skill written in?

claude-code-vision-skill is primarily written in Python. It covers topics such as agent-skills, anthropic, claude-code.

How do I install or use claude-code-vision-skill?

You can find installation instructions and usage details in the claude-code-vision-skill GitHub repository at github.com/xiincs/claude-code-vision-skill. The project has 171 stars and 8 forks, indicating an active community.

What license does claude-code-vision-skill use?

claude-code-vision-skill is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-code-vision-skill?

The top alternatives to claude-code-vision-skill on Agent Skills Hub include claudepro-directory, bridgic, dsclaude. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools