Skills Plugins MCP Prompt Model 博客 我的中心

architecture

Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=iofficeai-aionui-claude-skills-architecture-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name architecture description Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers. Architecture Skill Determine correct file placement and structure for an Electron multi-process project. Detailed References Renderer layer (components, hooks, utils, pages, CSS): references/renderer.md Main process & shared layer (bridges, services, worker, preload): references/process.md Project root & monorepo layout (directory structure, migration status): references/project-layout.md Decision Tree — Where Does New Code Go? Is it UI (React components, hooks, pages)? └── YES → packages/desktop/src/renderer/ → see references/renderer.md Is it an IPC handler responding to renderer calls? └── YES → packages/desktop/src/process/bridge/ → see references/process.md Is it business logic running in the main process? └── YES → packages/desktop/src/process/services/ → see references/process.md Is it an AI platform connection (API client, message protocol)? └── YES → packages/desktop/src/process/agent/<platform>/ Is it a background task that runs in a worker thread? └── YES → packages/desktop/src/process/worker/ Is it used by BOTH main and renderer processes? └── YES → packages/desktop/src/common/ Is it an HTTP/WebSocket endpoint? └── YES → packages/desktop/src/process/webserver/ Is it a plugin/extension resolver or loader? └── YES → packages/desktop/src/process/extensions/ Is it a messaging channel (Lark, DingTalk, Telegram)? └── YES → packages/desktop/src/process/channels/ Process Boundary Rules Hard rules — violating them causes runtime crashes. Process Can use Cannot use Main ( packages/desktop/src/process/ ) Node.js, Electron main APIs, fs , path , child_process DOM APIs ( document , window , React) Renderer ( packages/desktop/src/renderer/ ) DOM APIs, React, browser APIs Node.js APIs ( fs , path ), Electron main APIs Worker ( packages/desktop/src/process/worker/ ) Node.js APIs DOM APIs, Electron APIs Preload ( packages/desktop/src/preload/ ) contextBridge , ipcRenderer DOM manipulation, Node.js fs Cross-process communication: Main ↔ Renderer: IPC via packages/desktop/src/preload/ + packages/desktop/src/process/bridge/*.ts Main ↔ Worker: fork protocol via packages/desktop/src/process/worker/WorkerProtocol.ts // NEVER in renderer import { something } from '@process/services/foo' ; // crashes at runtime // Use IPC instead const result = await window . api . someMethod (); // goes through preload Naming Conventions Directories Scope Convention Reason Renderer component/module dirs PascalCase React convention — dir name = component name Everything else lowercase Node.js convention Categorical dirs (everywhere) lowercase components/ , hooks/ , utils/ , services/ Platform dirs (everywhere) lowercase acp/ , codex/ , gemini/ — cross-process consistency Quick test: "Inside packages/desktop/src/renderer/ AND represents a specific component/feature (not a category)?" → PascalCase. Otherwise → lowercase. Files Content Convention Examples React components, classes PascalCase SettingsModal.tsx , CronService.ts Hooks camelCase with use prefix useTheme.ts , useCronJobs.ts Utilities, helpers camelCase formatDate.ts , cronUtils.ts Entry points index.ts / index.tsx Required for directory-based modules Config, types, constants camelCase types.ts , constants.ts Styles kebab-case or Name.module.css chat-layout.css Structural Rules Directory size limit : Max 10 direct children. Split into subdirectories by responsibility when approaching. No single-file directories : Merge into parent or related directory. Single file vs directory : If a component needs a private sub-component or hook, convert to a directory with index.tsx . Page-private first : Start code in pages/<PageName>/ . Promote to shared only when a second consumer appears. Test File Mapping Tests mirror source files in tests/ subdirectories: Source Test packages/desktop/src/process/services/CronService.ts tests/unit/cronService.test.ts packages/desktop/src/renderer/hooks/ui/useAutoScroll.ts tests/unit/useAutoScroll.dom.test.ts packages/desktop/src/process/extensions/ExtensionLoader.ts tests/unit/extensions/extensionLoader.test.ts When tests/unit/ exceeds 10 direct children, group into subdirectories matching source structure. Quick Checklist Code is in the correct process directory (no cross-process imports) Renderer code does not use Node.js APIs Main process code does not use DOM APIs New IPC channels are bridged through preload.ts Renderer component/module dirs use PascalCase; categorical dirs use lowercase Platform dirs use lowercase everywhere Directory-based modules have index.tsx / index.ts entry point Page-private code is under pages/<PageName>/ , not in shared dirs No single-file directories No directory exceeds 10 direct children New source files are auto-included in coverage — verify they are not accidentally excluded in vitest.config.ts → coverage.exclude New services separate pure logic from IO
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。