xrk-project-overview
Skill140 starsChanged 8 months agoMITView on GitHub
当需要从整体理解 XRK-AGT 的架构、目录、运行流程和技术栈时使用。
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .cursor/rules/vibe-learn-craft.mdcCursor rule
- .cursor/rules/xrk-core-code.mdcCursor rule
- .cursor/rules/xrk-dev-requirements.mdcCursor rule
- .cursor/rules/xrk-infrastructure.mdcCursor rule
- .cursor/rules/xrk-project.mdcCursor rule
- .cursor/rules/xrk-third-party-plugins.mdcCursor rule
- accessibility-complianceSkill
- design-system-patternsSkill
- fronted-designSkill
- immersive-short-videoSkill
- interaction-designSkill
- mobile-android-designSkill
- mobile-ios-designSkill
- react-native-designSkill
- responsive-designSkill
- ui-ux-pro-maxSkill
- visual-design-foundationsSkill
- web-component-designSkill
- xrk-agent-runtimeSkill
- xrk-ai-workflowSkill
- xrk-app-devSkill
- xrk-authSkill
- xrk-coding-styleSkill
- xrk-configSkill
- xrk-crawlSkill
- xrk-dockerSkill
- xrk-docsSkill
- xrk-github-researchSkill
- xrk-http-apiSkill
- xrk-infrastructureSkill
- xrk-llmSkill
- xrk-mcpSkill
- xrk-node-runtimeSkill
- xrk-pluginsSkill
- xrk-rendererSkill
- xrk-runtime-utilSkill
- xrk-subserverSkill
- xrk-system-coreSkill
- xrk-taskerSkill
- xrk-v3-apiSkill
- xrk-www-compatSkill
The file
Files
文档
- 定位与分层:
docs/底层架构设计.md(架构单一事实源) - 启动链:
docs/startup.md - 目录树:
PROJECT_OVERVIEW.md、docs/README.md - Node 26:
docs/node-26-runtime.md、skillxrk-node-runtime(写 Core 服务端必读) - Core www:skill
xrk-www-compat(浏览器兼容层 / 内联垫片)
要点
- 定位:融合智能体业务逻辑的通用后端 — Runtime 在
src/,业务在core/。 - 分层:AgentRuntime(Runtime)→ 基础设施(Loader/基类)→ Tasker / 事件 → Core 业务。
- 业务在
core/<名>/(plugin|http|stream|tasker|events|commonconfig|www/<app>);src/仅基础设施与工厂。 - 启动:见
docs/startup.md(app.js→ bootstrap →start.js→agent-runtime.js)。 - Node ≥ 26.0(
package.jsonengines);包管理仅 pnpm。
Node 26
编码约定见 skill xrk-node-runtime 与 docs/node-26-runtime.md(本 skill 不重复禁止项表)。写 www/ 见 xrk-www-compat。
放码速查
| 类型 | 路径 |
| 业务 | core/<core>/ 各子目录 |
| 基类/加载器 | src/infrastructure/ |
| 工具 | src/utils/(bootstrap.js、process-signals.js、exec-async.js 等) |
| 工厂 | src/factory/ |
| 前端 | core/<core>/www/<app>/ |
| 浏览器兼容 | core/system-Core/www/xrk/modules/web-compat.js |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

