generate-subsystem-skills

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Generate Subsystem Skills

生成子系统技能

This skill analyzes each subsystem in the LlamaFarm monorepo and generates specialized Claude Code skills for security, performance, and language-specific best practices.

该技能会分析LlamaFarm单体仓库中的每个子系统，生成针对安全、性能和特定语言最佳实践的专属Claude Code技能。

Usage

使用方法

/generate-subsystem-skills

/generate-subsystem-skills

What Gets Generated

生成内容说明

Shared Language Skills (4)

共享语言技能（4项）

```
python-skills/
```
- Used by: server, rag, runtime, config, common
```
go-skills/
```
- Used by: cli
```
typescript-skills/
```
- Used by: designer, electron
```
react-skills/
```
- Used by: designer

```
python-skills/
```
- 适用子系统：server、rag、runtime、config、common
```
go-skills/
```
- 适用子系统：cli
```
typescript-skills/
```
- 适用子系统：designer、electron
```
react-skills/
```
- 适用子系统：designer

Subsystem-Specific Skills (8)

子系统专属技能（8项）

```
cli-skills/
```
- Cobra, Bubbletea patterns
```
server-skills/
```
- FastAPI, Celery, Pydantic patterns
```
rag-skills/
```
- LlamaIndex, ChromaDB patterns
```
runtime-skills/
```
- PyTorch, Transformers patterns
```
designer-skills/
```
- TanStack Query, Tailwind, Radix patterns
```
electron-skills/
```
- Electron IPC, security patterns
```
config-skills/
```
- Pydantic, JSONSchema patterns
```
common-skills/
```
- HuggingFace Hub patterns

```
cli-skills/
```
- Cobra、Bubbletea 模式
```
server-skills/
```
- FastAPI、Celery、Pydantic 模式
```
rag-skills/
```
- LlamaIndex、ChromaDB 模式
```
runtime-skills/
```
- PyTorch、Transformers 模式
```
designer-skills/
```
- TanStack Query、Tailwind、Radix 模式
```
electron-skills/
```
- Electron IPC、安全模式
```
config-skills/
```
- Pydantic、JSONSchema 模式
```
common-skills/
```
- HuggingFace Hub 模式

Generation Process

生成流程

Step 1: Read Registry

步骤1：读取注册表

Load subsystem definitions from subsystem-registry.md.

从subsystem-registry.md加载子系统定义。

Step 2: Generate Shared Language Skills

步骤2：生成共享语言技能

Launch sub-agents IN PARALLEL to generate:

Python Skills Agent - Analyze Python subsystems (server, rag, runtime, config, common), identify ideal patterns, generate
```
python-skills/
```
Go Skills Agent - Analyze CLI subsystem, identify ideal Go patterns, generate
```
go-skills/
```
TypeScript Skills Agent - Analyze designer and electron, identify ideal TS patterns, generate
```
typescript-skills/
```
React Skills Agent - Analyze designer, identify ideal React 18 patterns, generate
```
react-skills/
```

并行启动子Agent以生成：

Python技能Agent - 分析Python子系统（server、rag、runtime、config、common），确定理想模式，生成
```
python-skills/
```
Go技能Agent - 分析CLI子系统，确定理想Go模式，生成
```
go-skills/
```
TypeScript技能Agent - 分析designer和electron子系统，确定理想TS模式，生成
```
typescript-skills/
```
React技能Agent - 分析designer子系统，确定理想React 18模式，生成
```
react-skills/
```

Step 3: Generate Subsystem Skills

步骤3：生成子系统专属技能

Launch sub-agents IN PARALLEL for each subsystem:

For each subsystem, the agent should:

Read the subsystem's dependency files (package.json, pyproject.toml, go.mod)
Analyze code patterns using Grep and Read
Generate SKILL.md that links to shared language skills
Generate framework-specific checklist files
Write all files to
```
.claude/skills/{subsystem}-skills/
```

为每个子系统并行启动子Agent：

针对每个子系统，Agent需要：

读取子系统的依赖文件（package.json、pyproject.toml、go.mod）
使用Grep和Read工具分析代码模式
生成关联共享语言技能的SKILL.md文件
生成框架专属检查清单文件
将所有文件写入
```
.claude/skills/{subsystem}-skills/
```
目录

Step 4: Report Summary

步骤4：生成汇总报告

After all agents complete, report:

Number of skills generated
Total files created
Any errors encountered

所有Agent完成后，生成报告：

生成的技能数量
创建的文件总数
遇到的所有错误

Sub-Agent Prompt Templates

子Agent提示词模板

For Shared Language Skills

共享语言技能模板

You are generating a shared {LANGUAGE} skills directory for Claude Code.

Analyze these subsystems that use {LANGUAGE}:
{SUBSYSTEM_PATHS}

Your task:
1. Read key files to understand patterns used
2. When patterns vary, document the IDEAL approach (not inconsistencies)
3. Reference industry best practices
4. Generate files in .claude/skills/{LANGUAGE}-skills/

Files to generate:
- SKILL.md (overview, ~100 lines)
- patterns.md (idiomatic patterns)
- error-handling.md
- testing.md
- security.md
- {additional language-specific files}

Each checklist item should have:
- Description of what to check
- Search pattern (grep command)
- Pass/fail criteria
- Severity level

你正在为Claude Code生成共享{LANGUAGE}技能目录。

请分析以下使用{LANGUAGE}的子系统：
{SUBSYSTEM_PATHS}

你的任务：
1. 读取关键文件以理解所用模式
2. 当模式存在差异时，记录理想方案（而非不一致的地方）
3. 参考行业最佳实践
4. 在.claude/skills/{LANGUAGE}-skills/目录下生成文件

需要生成的文件：
- SKILL.md（概述，约100行）
- patterns.md（惯用模式）
- error-handling.md
- testing.md
- security.md
- {additional language-specific files}

每个检查清单项应包含：
- 检查内容描述
- 搜索模式（grep命令）
- 通过/失败标准
- 严重级别

For Subsystem Skills

子系统专属技能模板

You are generating subsystem-specific skills for {SUBSYSTEM} in Claude Code.

Directory: {PATH}
Tech Stack: {TECH_STACK}
Links to: {SHARED_SKILLS}

Your task:
1. Read dependency files and key source files
2. Identify framework-specific patterns
3. Generate SKILL.md that links to shared language skills
4. Generate framework-specific checklists

Files to generate:
- SKILL.md (overview with links to shared skills)
- {framework}.md for each framework used
- performance.md (subsystem-specific optimizations)

Remember: Document IDEAL patterns, not existing inconsistencies.

你正在为Claude Code生成{SUBSYSTEM}子系统的专属技能。

目录：{PATH}
技术栈：{TECH_STACK}
关联共享技能：{SHARED_SKILLS}

你的任务：
1. 读取依赖文件和关键源文件
2. 识别框架专属模式
3. 生成关联共享语言技能的SKILL.md文件
4. 生成框架专属检查清单

需要生成的文件：
- SKILL.md（包含共享技能链接的概述）
- 每个所用框架对应的{framework}.md文件
- performance.md（子系统专属优化方案）

注意：记录理想模式，而非现有不一致的内容。

Key Principle

核心原则

Prescribe ideal patterns - When the codebase has inconsistent patterns, the generated skills should document the BEST practice according to industry standards, not codify existing inconsistencies.

规定理想模式 - 当代码库中存在不一致的模式时，生成的技能应记录符合行业标准的最佳实践，而非固化现有不一致的内容。

Output Location

输出位置

All skills are written to

.claude/skills/

with this structure:

.claude/skills/
├── python-skills/      # Shared
├── go-skills/          # Shared
├── typescript-skills/  # Shared
├── react-skills/       # Shared
├── cli-skills/         # Subsystem
├── server-skills/      # Subsystem
├── rag-skills/         # Subsystem
├── runtime-skills/     # Subsystem
├── designer-skills/    # Subsystem
├── electron-skills/    # Subsystem
├── config-skills/      # Subsystem
└── common-skills/      # Subsystem

所有技能将写入

.claude/skills/

目录，结构如下：

.claude/skills/
├── python-skills/      # 共享技能
├── go-skills/          # 共享技能
├── typescript-skills/  # 共享技能
├── react-skills/       # 共享技能
├── cli-skills/         # 子系统专属
├── server-skills/      # 子系统专属
├── rag-skills/         # 子系统专属
├── runtime-skills/     # 子系统专属
├── designer-skills/    # 子系统专属
├── electron-skills/    # 子系统专属
├── config-skills/      # 子系统专属
└── common-skills/      # 子系统专属