archify — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 tt-a1i · Claude Skill · ★ 76.1k

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

🔒 Is archify safe to install? View the security audit →

About archify

Archify 聊两句就画出好看的架构图、技术流程图、调用时序图、数据流图和生命周期图。深色 / 浅色一键切。导出最高 4× 清晰 PNG / JPEG / WebP / SVG,或直接复制到剪贴板。 Archify 是一个 Claude Skill:你用大白话描述自己的系统或流程,它就把你的描述变成一张做工精细的技术图 —— 一个单文件 HTML,在浏览器里打开就能切主题、复制到剪贴板、导出成各种图片格式。 不需要会画图 —— 把组件和连接关系说给 Claude 就行 支持 workflow / sequence / data flow / lifecycle —— 技术流程、审批链、工具调用、CI/CD、请求调用链、数据管线、PII 边界、状态机都可以画 内置主题切换 —— 深色 / 浅色一键切,浏览器记住偏好 一键复制到剪贴板 —— 直接贴到 Slack、飞书、微信、Notion、GitHub issue 导出图片超清晰 —— PNG / JPEG / WebP 全部由浏览器在最高 4× 源分辨率下原生光栅化(不是位图放大,没有糊),或导出 SVG 做真矢量 SVG 自动跟系统深浅色 —— 导出的 SVG 内嵌两套变量 + ,贴到 GitHub README 里,读者切深浅色图跟着切(不用两张 PNG + 包起来) 单文件 HTML —— 生成的 HTML 零运行时依赖,发一个文件就能分享 聊天迭代 —— "把 Redis 挪到左边"、"鉴权服务换成玫红"、"加个 Kafka" 在线落地页 → tt-a1i.github.io/archify English 预览 同一张图,两套主题,一键切换: Export 菜单 —— 复制到剪贴板 + 四种格式下载: 想亲自玩一下:克隆仓库后打开 [](ex

agent-skillsarchitecture-as-codearchitecture-diagramclaude-skillcode-visualizationcodexcoding-agentsdata-flow-diagramdeepseek-harnessdeveloper-tools

Quick Facts

Stars76,120
Forks5,124
LanguageJavaScript
CategoryClaude Skill
LicenseMIT
Quality Score63.1333546791928/100
Open Issues191
Last Updated2026-10-02
Created2026-04-15
Platformsclaude-code, codex, node
Est. Tokens~15k

archify alternative? Top 6 similar tools

Looking for a archify alternative? If you're comparing archify 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.

  • open-design by nexu-io · ⭐ 99.2k

    🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app

  • agents by wshobson · ⭐ 40.1k

    Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Anti

  • awesome-claude-skills by ComposioHQ · ⭐ 75.3k

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

  • cmux by manaflow-ai · ⭐ 27.6k

    Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for

  • cc-switch by farion1231 · ⭐ 139.7k

    A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes

  • ruflo by ruvnet · ⭐ 73.8k

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and bu

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is archify?

archify is Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.. It is categorized as a Claude Skill with 76.1k GitHub stars.

What programming language is archify written in?

archify is primarily written in JavaScript. It covers topics such as agent-skills, architecture-as-code, architecture-diagram.

How do I install or use archify?

You can find installation instructions and usage details in the archify GitHub repository at github.com/tt-a1i/archify. The project has 76.1k stars and 5124 forks, indicating an active community.

What license does archify use?

archify is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to archify?

The top alternatives to archify on Agent Skills Hub include open-design, agents, awesome-claude-skills. 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