xrk-docs
Skill140 starsChanged 8 months agoMITView on GitHub
需要快速定位「该看哪份文档/哪段代码/哪份配置」时使用；提供文档导航与权威路径。
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-github-researchSkill
- xrk-http-apiSkill
- xrk-infrastructureSkill
- xrk-llmSkill
- xrk-mcpSkill
- xrk-node-runtimeSkill
- xrk-pluginsSkill
- xrk-project-overviewSkill
- xrk-rendererSkill
- xrk-runtime-utilSkill
- xrk-subserverSkill
- xrk-system-coreSkill
- xrk-taskerSkill
- xrk-v3-apiSkill
- xrk-www-compatSkill
The file
Files
读者：Coding Agent。产品模型技能在
.xrk/skills/，勿与本索引混用。
导航
主索引：docs/README.md。分层边界：docs/底层架构设计.md。启动链：docs/startup.md。
技能读者分流：.cursor/skills/SKILL_INDEX.md。
| 主题 | 文档 |
| 开发首读 | docs/runtime-surface.md、docs/coding-style.md、docs/base-classes.md |
| Cursor / 本仓开发入口 | 根 AGENTS.md、.cursor/skills/SKILL_INDEX.md |
| 办事助手（群聊/控制台） | docs/agents.md、agents/README.md（运营） |
| Agent 跑通 / 出站 / 安全 | docs/agent-context.md ⭐ |
| 写法 / 性能 | docs/coding-style.md、skill xrk-coding-style |
| Node 26 | docs/node-26-runtime.md、skill xrk-node-runtime |
| Core www / 挂载 | skill xrk-www-compat、docs/www-mount.md |
| 启动 / 引导 | docs/startup.md |
| 文档规范 | docs/DOCSTYLE.md |
| 数据库 | docs/database.md |
| 扩展点 / 基类 | docs/框架可扩展性指南.md、docs/base-classes.md |
| Loader 模式 | docs/infrastructure-shared.md |
| LLM / v3 / finalize | docs/factory.md、skill xrk-llm、core/system-Core/http/ai.js |
| 工作流 / 压缩 / 策略 | docs/ai-workflow.md、skill xrk-ai-workflow |
| system-Core | docs/system-core.md |
| HTTP | docs/http-api.md、docs/http-business-layer.md、docs/server.md |
| 鉴权 | docs/AUTH.md |
| MCP | docs/mcp-guide.md、docs/mcp-config-guide.md、skill xrk-mcp |
| 配置 | docs/config-base.md、skill xrk-config |
| 目录树 | PROJECT_OVERVIEW.md |
回答规范
- 配置类：给出 YAML 路径 + 字段 + 最小示例。
- 行为类：给出代码文件 + 函数/类名。
- 文档与代码冲突：以代码为准。
- 分清读者：改代码 →
xrk-*；办事助手怎么用工具 →.xrk/skills/core/agent-tools。
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.