docs-seeker

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Documentation Discovery via Scripts

基于脚本的文档发现

Overview

概述

Script-first documentation discovery using llms.txt standard.

Execute scripts to handle entire workflow - no manual URL construction needed.

以脚本优先的方式，基于llms.txt标准进行文档发现。

执行脚本即可处理整个工作流——无需手动构建URL。

Primary Workflow

核心工作流

ALWAYS execute scripts in this order:

bash

undefined

请务必按照以下顺序执行脚本：

bash

undefined

1. DETECT query type (topic-specific vs general)

1. 检测查询类型（特定主题 vs 通用）

node scripts/detect-topic.js "<user query>"

node scripts/detect-topic.js "<用户查询>"

2. FETCH documentation using script output

2. 使用脚本输出结果获取文档

node scripts/fetch-docs.js "<user query>"

node scripts/fetch-docs.js "<用户查询>"

3. ANALYZE results (if multiple URLs returned)

3. 分析结果（若返回多个URL）

cat llms.txt | node scripts/analyze-llms-txt.js -


Scripts handle URL construction, fallback chains, and error handling automatically.

cat llms.txt | node scripts/analyze-llms-txt.js -


脚本会自动处理URL构建、回退链和错误处理。

Scripts

脚本说明

detect-topic.js
- Classify query type

Identifies topic-specific vs general queries
Extracts library name + topic keyword
Returns JSON:
```
{topic, library, isTopicSpecific}
```
Zero-token execution

fetch-docs.js
- Retrieve documentation

Constructs context7.com URLs automatically
Handles fallback: topic → general → error
Outputs llms.txt content or error message
Zero-token execution

analyze-llms-txt.js
- Process llms.txt

Categorizes URLs (critical/important/supplementary)
Recommends agent distribution (1 agent, 3 agents, 7 agents, phased)
Returns JSON with strategy
Zero-token execution

detect-topic.js
- 分类查询类型

识别特定主题查询与通用查询
提取库名称 + 主题关键词
返回JSON格式：
```
{topic, library, isTopicSpecific}
```
零Token执行

fetch-docs.js
- 获取文档

自动构建context7.com的URL
处理回退逻辑：主题 → 通用 → 错误
输出llms.txt内容或错误信息
零Token执行

analyze-llms-txt.js
- 处理llms.txt

对URL进行分类（关键/重要/补充）
推荐Agent分发策略（1个Agent、3个Agent、7个Agent、分阶段）
返回包含策略的JSON结果
零Token执行

Workflow References

工作流参考

Topic-Specific Search - Fastest path (10-15s)

General Library Search - Comprehensive coverage (30-60s)

Repository Analysis - Fallback strategy

特定主题搜索 - 最快路径（10-15秒）

通用库搜索 - 全面覆盖（30-60秒）

仓库分析 - 回退策略

References

参考文档

context7-patterns.md - URL patterns, known repositories

errors.md - Error handling, fallback strategies

advanced.md - Edge cases, versioning, multi-language

context7-patterns.md - URL模式、已知仓库

errors.md - 错误处理、回退策略

advanced.md - 边缘情况、版本控制、多语言

Execution Principles

执行原则

Scripts first - Execute scripts instead of manual URL construction
Zero-token overhead - Scripts run without context loading
Automatic fallback - Scripts handle topic → general → error chains
Progressive disclosure - Load workflows/references only when needed
Agent distribution - Scripts recommend parallel agent strategy

脚本优先 - 执行脚本而非手动构建URL
零Token开销 - 脚本运行无需加载上下文
自动回退 - 脚本处理主题→通用→错误的回退链
渐进式披露 - 仅在需要时加载工作流/参考文档
Agent分发 - 脚本推荐并行Agent策略

Quick Start

快速开始

Topic query: "How do I use date picker in shadcn?"

bash

node scripts/detect-topic.js "<query>"  # → {topic, library, isTopicSpecific}
node scripts/fetch-docs.js "<query>"    # → 2-3 URLs

特定主题查询示例： "如何在shadcn中使用日期选择器？"

bash

node scripts/detect-topic.js "<查询内容>"  # → {topic, library, isTopicSpecific}
node scripts/fetch-docs.js "<查询内容>"    # → 2-3个URL

Read URLs with WebFetch

使用WebFetch读取URL内容


**General query:** "Documentation for Next.js"
```bash
node scripts/detect-topic.js "<query>"         # → {isTopicSpecific: false}
node scripts/fetch-docs.js "<query>"           # → 8+ URLs
cat llms.txt | node scripts/analyze-llms-txt.js -  # → {totalUrls, distribution}


**通用查询示例：** "Next.js的文档"
```bash
node scripts/detect-topic.js "<查询内容>"         # → {isTopicSpecific: false}
node scripts/fetch-docs.js "<查询内容>"           # → 8个以上URL
cat llms.txt | node scripts/analyze-llms-txt.js -  # → {totalUrls, distribution}

Deploy agents per recommendation

根据推荐部署Agent

undefined

undefined

Environment

环境配置

Scripts load

.env

process.env

.claude/skills/docs-seeker/.env

.claude/skills/.env

.claude/.env

See

.env.example

for configuration options.

脚本会加载

.env

文件，优先级：

process.env

.claude/skills/docs-seeker/.env

.claude/skills/.env

.claude/.env

配置选项可参考

.env.example

。