librarian

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Librarian Skill

Deep codebase exploration across remote repositories.

跨远程代码仓库的深度代码库探索工具。

How to Use This Skill

如何使用该Skill

Reference Structure

参考文档结构

File	Purpose	When to Read
`tool-routing.md`	Tool selection decision trees	Always read first
`opensrc-api.md`	API reference, types	Writing opensrc code
`opensrc-examples.md`	JavaScript patterns, workflows	Implementation examples
`linking.md`	GitHub URL patterns	Formatting responses
`diagrams.md`	Mermaid patterns	Visualizing architecture

文件	用途	阅读时机
`tool-routing.md`	工具选择决策树	务必首先阅读
`opensrc-api.md`	API参考文档、类型定义	编写opensrc相关代码时
`opensrc-examples.md`	JavaScript代码模式、工作流	实现示例参考
`linking.md`	GitHub URL格式规范	格式化响应内容时
`diagrams.md`	Mermaid图表语法	可视化架构设计时

Reading Order

阅读顺序

Start with
```
tool-routing.md
```
→ choose tool strategy
If using opensrc:
- Read
```
opensrc-api.md
```
  for API details
- Read
```
opensrc-examples.md
```
  for patterns
Before responding:
```
linking.md
```
+
```
diagrams.md
```
for output formatting

第一步 阅读
```
tool-routing.md
```
→ 确定工具使用策略
若使用opensrc工具：
- 阅读
```
opensrc-api.md
```
  了解API细节
- 阅读
```
opensrc-examples.md
```
  参考代码模式
生成响应前： 参考
```
linking.md
```
+
```
diagrams.md
```
进行输出格式化

Tool Arsenal

工具库

Tool	Best For	Limitations
grep_app	Find patterns across ALL public GitHub	Literal search only
context7	Library docs, API examples, usage	Known libraries only
opensrc	Fetch full source for deep exploration	Must fetch before read

工具	最佳适用场景	局限性
grep_app	在所有公开GitHub仓库中查找代码模式	仅支持字面量搜索
context7	类库文档、API示例、使用方法查询	仅支持已知类库
opensrc	获取完整源码进行深度探索	必须先获取源码才能阅读

Quick Decision Trees

快速决策树

"How does X work?"

"X的工作原理是什么？"

Known library?
├─ Yes → context7.resolve-library-id → context7.query-docs
│        └─ Need internals? → opensrc.fetch → read source
└─ No  → grep_app search → opensrc.fetch top result

已知该类库？
├─ 是 → context7.resolve-library-id → context7.query-docs
│        └─ 需要了解内部实现？ → opensrc.fetch → 阅读源码
└─ 否  → grep_app搜索 → opensrc.fetch搜索结果中的Top项目

"Find pattern X"

"查找代码模式X"

Specific repo?
├─ Yes → opensrc.fetch → opensrc.grep → read matches
└─ No  → grep_app (broad) → opensrc.fetch interesting repos

指定了具体仓库？
├─ 是 → opensrc.fetch → opensrc.grep → 阅读匹配结果
└─ 否  → grep_app（大范围搜索） → opensrc.fetch感兴趣的仓库

"Explore repo structure"

"探索仓库结构"

1. opensrc.fetch(target)
2. opensrc.tree(source.name) → quick overview
3. opensrc.files(source.name, "**/*.ts") → detailed listing
4. Read: README, package.json, src/index.*
5. Create architecture diagram (see diagrams.md)

1. opensrc.fetch(target)
2. opensrc.tree(source.name) → 快速概览
3. opensrc.files(source.name, "**/*.ts") → 详细文件列表
4. 阅读：README、package.json、src/index.*
5. 创建架构图（参考diagrams.md）

"Compare X vs Y"

"对比X和Y"

1. opensrc.fetch(["X", "Y"])
2. Use source.name from results for subsequent calls
3. opensrc.grep(pattern, { sources: [nameX, nameY] })
4. Read comparable files, synthesize differences

1. opensrc.fetch(["X", "Y"])
2. 使用返回结果中的source.name进行后续调用
3. opensrc.grep(pattern, { sources: [nameX, nameY] })
4. 阅读可对比文件，归纳差异

Critical: Source Naming Convention

重要：源码命名规范

After fetching, always use
source.name
for subsequent calls:

javascript

const [{ source }] = await opensrc.fetch("vercel/ai");
const files = await opensrc.files(source.name, "**/*.ts");

Type	Fetch Spec	Source Name
npm	`"zod"`	`"zod"`
npm scoped	`"@tanstack/react-query"`	`"@tanstack/react-query"`
pypi	`"pypi:requests"`	`"requests"`
crates	`"crates:serde"`	`"serde"`
GitHub	`"vercel/ai"`	`"github.com/vercel/ai"`
GitLab	`"gitlab:org/repo"`	`"gitlab.com/org/repo"`

获取源码后，后续调用必须使用
source.name
：

javascript

const [{ source }] = await opensrc.fetch("vercel/ai");
const files = await opensrc.files(source.name, "**/*.ts");

类型	获取标识	源码名称
npm	`"zod"`	`"zod"`
npm 作用域包	`"@tanstack/react-query"`	`"@tanstack/react-query"`
pypi	`"pypi:requests"`	`"requests"`
crates	`"crates:serde"`	`"serde"`
GitHub	`"vercel/ai"`	`"github.com/vercel/ai"`
GitLab	`"gitlab:org/repo"`	`"gitlab.com/org/repo"`

When NOT to Use opensrc

不建议使用opensrc的场景

Scenario	Use Instead
Simple library API questions	context7
Finding examples across many repos	grep_app
Very large monorepos (>10GB)	Clone locally
Private repositories	Direct access

场景	替代方案
简单的类库API问题	context7
在大量仓库中查找示例	grep_app
超大型单体仓库（>10GB）	本地克隆
私有仓库	直接访问

Output Guidelines

输出规范

Comprehensive final message - only last message returns to main agent
Parallel tool calls - maximize efficiency
Link every file reference - see
```
linking.md
```
Diagram complex relationships - see
```
diagrams.md
```
Never mention tool names - say "I'll search" not "I'll use opensrc"

最终消息需全面 - 仅最后一条消息返回给主Agent
并行调用工具 - 最大化效率
所有文件引用需添加链接 - 参考
```
linking.md
```
复杂关系需生成图表 - 参考
```
diagrams.md
```
切勿提及工具名称 - 说“我将进行搜索”而非“我将使用opensrc”

References

参考链接

Tool Routing Decision Trees
opensrc API Reference
opensrc Code Examples
GitHub Linking Patterns
Mermaid Diagram Patterns

工具选择决策树
opensrc API参考文档
opensrc代码示例
GitHub链接格式规范
Mermaid图表语法