tt-a1i / archify
tt-a1i / archify
Archify: Turn a codebase or system description into a polished, interactive system map — directly in chat. Archify 是一个为 Raven、Cursor、Claude Code、Codex CLI 和 OpenCode 设计的智能体技能。只需提供系统描述或代码仓库，即可获得交互式、可分享的技术架构图。打开并展示——包含五种图表类型、四种预设、深色/浅色主题、内置品牌标识以及有限的动画效果。
Review architecture changes before merge — compare two validated snapshots as Before / Delta / After, with exact added, removed, changed, moved, and rerouted facts. 在合并前审查架构变更——通过“变更前/差异/变更后”对比两个已验证的快照，精确展示新增、删除、修改、移动和重路由的事实。
Every interaction stays grounded — search nodes, optionally open revision-verified source, trace upstream/downstream authored reach and exact routes, compare roles, and play guided stories without inventing topology. 每一次交互都有据可依——支持搜索节点、可选打开经版本验证的源码、追踪上游/下游的逻辑覆盖范围及精确路径、对比角色，并播放引导式故事，无需凭空捏造拓扑结构。
One file, ready to trust and share — typed JSON IR and deterministic checks produce self-contained HTML plus PNG, SVG, WebM, and 1200×630 share cards. 单一文件，值得信赖且易于分享——通过类型化的 JSON 中间表示（IR）和确定性检查，生成自包含的 HTML，以及 PNG、SVG、WebM 和 1200×630 的分享卡片。
Current development version: v2.16.0-dev.0. See Changelog. 当前开发版本：v2.16.0-dev.0。查看更新日志。
Project page · Scenario guide · Proof Lab 项目页面 · 场景指南 · 验证实验室
npx skills add tt-a1i/archify -g
Using Cursor? Open the agent-aware quick start for exact global and project commands. Then ask your agent: Use archify to map this repository’s runtime architecture.
使用 Cursor？打开智能体感知快速入门以获取精确的全局和项目命令。然后询问你的智能体：使用 archify 绘制该仓库的运行时架构。
❤️ Sponsors (赞助商)
APINEBULA sponsors Archify with one API for Claude, GPT, Gemini, and more. Register through Archify and use Archify for 10% off. APINEBULA 为 Archify 提供支持，通过一个 API 整合 Claude、GPT、Gemini 等模型。通过 Archify 注册并使用可享受 9 折优惠。
EverMind · Raven: EverMind sponsors Archify and builds memory infrastructure for agents. Its Raven harness supports Archify as a Skill for verified, interactive system maps. EverMind · Raven：EverMind 赞助 Archify 并为智能体构建内存基础设施。其 Raven 框架支持将 Archify 作为一种技能，用于生成经过验证的交互式系统图。
Want to sponsor Archify? Contact us by email. 想要赞助 Archify？请通过电子邮件联系我们。
See Archify in action (查看 Archify 实际效果)
These are generated Archify artifacts, not product mockups. Click a frame to open its live, shareable state. Three real generated artifacts. 这些是生成的 Archify 制品，而非产品模型。点击框架即可打开其可实时交互、可分享的状态。以下是三个真实的生成制品。
Signal Flow · Blueprint · Classic · open the interactive Proof Lab ↗ 信号流 · 蓝图 · 经典 · 打开交互式验证实验室 ↗
Guided story: Play one finite named chapter. 引导式故事：播放一个有限的命名章节。 Route probe: Inspect the shortest authored directed path. 路径探测：检查最短的逻辑有向路径。 Semantic lens: Compare real traffic between semantic roles. 语义透镜：对比语义角色之间的真实流量。
The Proof Lab contains all 11 checked-in scenarios, their JSON sources, named views, and validation receipts. 验证实验室包含所有 11 个已提交的场景、它们的 JSON 源文件、命名视图和验证回执。
A real repository, mapped from source: Archify traced mco-org/mco at 9f1a1cf and produced this checked map. 一个真实的仓库，从源码映射：Archify 追踪了 mco-org/mco 的 9f1a1cf 版本，并生成了这张经过校验的地图。 Open it ↗ · trace reach ↗ · typed source 打开它 ↗ · 追踪覆盖范围 ↗ · 类型化源码
Preview (预览)
Same diagram, two themes, one click to switch: Dark / Light 同一张图，两种主题，一键切换：深色 / 浅色
The Export menu copies PNG to the clipboard and downloads static or motion formats: 导出菜单可将 PNG 复制到剪贴板，并下载静态或动态格式：
- Use Copy Share Card when you want a canonical 1200×630 image for a README, release, or social post. 当你需要为 README、发布说明或社交媒体帖子准备标准的 1200×630 图像时，使用“复制分享卡片”。
- After tracing a route, Export → Route Share Card downloads that authored path as a 1200×630 PNG with the full diagram retained for context. 追踪路径后，导出 → 路径分享卡片，可将该逻辑路径下载为 1200×630 的 PNG，并保留完整图表作为上下文。
- After tracing authored Upstream or Downstream reach, Export → Reach Share Card captures that exact reading without claiming runtime impact. 追踪逻辑上游或下游覆盖范围后，导出 → 覆盖范围分享卡片，可捕获该精确读数，且不声明运行时影响。
Open examples/web-app.html locally to try the complete viewer.
在本地打开 examples/web-app.html 以体验完整的查看器。
Quick start (快速入门)
1. Install
npx skills add tt-a1i/archify -g
For an explicit, non-interactive Cursor install:
对于明确的、非交互式的 Cursor 安装：
npx -y skills add tt-a1i/archify --skill archify --agent cursor --global --copy --yes
To try without installing:
无需安装即可尝试：
npx skills use tt-a1i/archify@archify --agent codex
DSH community opt-in:
dsh plugin --profile web add @tt-a1i/archify-dsh@0.1.0
The agent switcher covers cursor, codex, claude-code, and opencode. For Raven’s manual ZIP install, extract archify.zip into ~/.raven/workspace/skills; it yields ~/.raven/workspace/skills/archify. Raven is not a switcher target.
智能体切换器涵盖 cursor、codex、claude-code 和 opencode。对于 Raven 的手动 ZIP 安装，将 archify.zip 解压到 ~/.raven/workspace/skills；它将生成 ~/.raven/workspace/skills/archify。Raven 不属于切换器目标。
2. Ask for one bounded view Analyze this repository, then use archify to create a high-level runtime architecture diagram. Show 8–12 core components, one primary path, external dependencies, and trust boundaries. Put supporting detail in cards instead of adding more edges. 分析此仓库，然后使用 archify 创建高层运行时架构图。展示 8-12 个核心组件、一条主要路径、外部依赖和信任边界。将辅助细节放在卡片中，而不是增加更多的连线。
For a focused flow: Use archify to draw this login flow: Browser -> Web App -> API -> JWT validation -> Redis session lookup -> PostgreSQL fallback. Keep the cache-miss path secondary. 针对特定流程：使用 archify 绘制此登录流程：浏览器 -> Web 应用 -> API -> JWT 验证 -> Redis 会话查找 -> PostgreSQL 后备。将缓存未命中路径作为次要路径。
3. Refine in chat Continue with focused requests such as add Redis, move auth to the left, or highlight the rollback path. Archify keeps the typed source available for targeted iteration. 在聊天中继续进行针对性请求，例如“添加 Redis”、“将认证移到左侧”或“高亮回滚路径”。Archify 保留类型化源码，以便进行针对性迭代。
Choose the right diagram (选择合适的图表)
| Type | Best for | Include in your prompt |
|---|---|---|
| Architecture | Components, services, storage, boundaries | Scope, core components, primary path |
| Workflow | CI/CD, approvals, tool calls, runbooks | Participants, order, branches, exceptions |
| Sequence | API calls, cache fallback, auth, async traces | Callers, callees, returns, timing |
| Data Flow | Pipelines, lineage, PII, consumers | Sources, transforms, stores, boundaries |
| Lifecycle | States, retries, waits, terminal outcomes | States, events, retry and cancellation paths |
(表格翻译：)
| 类型 | 适用场景 | 提示词中包含 |
|---|---|---|
| 架构 (Architecture) | 组件、服务、存储、边界 | 范围、核心组件、主要路径 |
| 工作流 (Workflow) | CI/CD、审批、工具调用、运行手册 | 参与者、顺序、分支、异常 |
| 序列 (Sequence) | API 调用、缓存后备、认证、异步追踪 | 调用者、被调用者、返回、时序 |
| 数据流 (Data Flow) | 流水线、血缘、PII、消费者 | 源、转换、存储、边界 |
| 生命周期 (Lifecycle) | 状态、重试、等待、最终结果 | 状态、事件、重试和取消路径 |
For a production deployment review, Architecture can optionally enable the deployment-ownership engineering profile. It fails closed when owners, single-region placement, private database scope, or named boundary crossings are missing. It is never enabled silently and validates authored facts—not live infrastructure. See the checked deployment proof. 对于生产部署审查，Architecture 可选启用“部署所有权”工程配置。当缺少所有者、单区域部署、私有数据库范围或命名边界交叉时，它会触发失败。它绝不会静默启用，且仅验证已编写的事实，而非实时基础设施。查看已校验的部署证明。
For design or PR review, Architecture Delta compares validated Before / Delta / After snapshots with a machine receipt. Select an exact authored change or play one finite Review—viewer-only, with no impact, risk, or merge-safety inference. 对于设计或 PR 审查，Architecture Delta 通过机器回执对比已验证的“变更前/差异/变更后”快照。选择一个精确的逻辑变更或播放一次有限的审查——仅供查看，无影响、无风险，也不涉及合并安全性推断。
node archify/bin/archify.mjs compare architecture base.json head.json architecture-delta.html --json
Not sure which one fits? Use the interactive scenario guide, or ask the zero-dependency CLI:
不确定哪种适合？使用交互式场景指南，或询问零依赖 CLI：
node archify/bin/archify.mjs guide "Show an API request with Redis cache miss"
node archify/bin/archify.mjs guide "Map Kafka topics, consumer groups, replay, and DLQ" --json
Workflow keeps the happy path clear across lanes: 工作流保持跨通道的“成功路径”清晰： Sequence explains one interaction over time: 序列解释随时间推移的一次交互： Data Flow makes movement and sensitivity boundaries explicit: 数据流使移动和敏感度边界明确： Lifecycle separates progress, waits, retries, and terminal outcomes: 生命周期分离进度、等待、重试和最终结果：
Architecture examples: web-app · Archify pipeline · grid placement · desktop agent 架构示例：web-app · Archify 流水线 · 网格布局 · 桌面智能体
Why Archify: Layout judgment over generic auto-layout — the agent chooses hierarchy, spacing, routes, and emphasis; shared automatic endpoints. 为什么选择 Archify：布局判断优于通用自动布局——智能体选择层级、间距、路径和重点；共享自动端点。