research-methodology

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Methodology for Documentation

技术文档研究方法论

This skill provides systematic approach to researching technical documentation using WebSearch and WebFetch tools.

本Skill提供了一套使用WebSearch和WebFetch工具研究技术文档的系统化方法。

Core Principles

核心原则

Initialize first - Ensure project knowledge base skill exists
Validate before research - Ensure request is specific enough

Check local first - Look in

.claude/skills/project-knowledge-base/references/

before searching

Official sources priority - Start with official docs
Filter aggressively - Extract only what's relevant to context
Save for reuse - Document findings in standard format

优先初始化 - 确保项目知识库Skill已存在
研究前验证 - 确保请求足够具体

优先检查本地 - 搜索前先查看

.claude/skills/project-knowledge-base/references/

优先官方来源 - 从官方文档开始
严格过滤 - 仅提取与上下文相关的内容
保存以便复用 - 以标准格式记录研究结果

Request Validation

请求验证

A valid research request must contain three elements:

Element	Example	Invalid
Technology	"React", "Effect", "Prisma"	"JavaScript library"
Topic	"useEffect cleanup", "pipe operator"	"how it works"
Context	"fixing memory leak in subscription"	"learning"

If any element is missing, return validation error and request clarification.

有效的研究请求必须包含三个要素：

要素	示例	无效示例
技术	"React", "Effect", "Prisma"	"JavaScript库"
主题	"useEffect cleanup", "pipe operator"	"它如何工作"
上下文	"修复订阅中的内存泄漏"	"学习"

如果缺少任何要素，返回验证错误并请求澄清。

Search Strategy

搜索策略

Query Formulation

查询构建

Build queries progressively:

Level 1 (Official): {technology} official documentation {topic}
Level 2 (Tutorial): {technology} {topic} tutorial example
Level 3 (Problem): {technology} {topic} {error-message} solution

逐步构建查询：

Level 1 (Official): {technology} official documentation {topic}
Level 2 (Tutorial): {technology} {topic} tutorial example
Level 3 (Problem): {technology} {topic} {error-message} solution

Source Hierarchy

来源优先级

Prioritize sources in this order:

Official documentation (always check first)
- react.dev, docs.python.org, effect.website
- GitHub official repos and examples
Trusted secondary sources
- MDN Web Docs (web technologies)
- DigitalOcean Community tutorials
- Dev.to (high-quality articles only)
- Stack Overflow (accepted answers)
Avoid
- SEO-optimized content farms
- Outdated tutorials (check dates)
- AI-generated summaries
- Forums without accepted solutions

按以下优先级选择来源：

官方文档（始终优先检查）
- react.dev, docs.python.org, effect.website
- GitHub官方仓库及示例
可信的二级来源
- MDN Web Docs（Web技术）
- DigitalOcean社区教程
- Dev.to（仅高质量文章）
- Stack Overflow（已采纳的答案）
需避免的来源
- 经过SEO优化的内容农场
- 过时的教程（注意检查日期）
- AI生成的摘要
- 无已采纳解决方案的论坛

WebSearch Patterns

WebSearch查询模式

Reference

references/query-patterns.md

for specific query templates per technology domain.

参考

references/query-patterns.md

获取各技术领域的特定查询模板。

Filtering Results

结果过滤

Relevance Criteria

Extraction Process

提取流程

Scan search results for relevance
Open 2-3 most promising sources
Extract specific sections, not entire pages
Verify code examples are complete
Note version compatibility

扫描搜索结果以判断相关性
打开2-3个最有价值的来源
提取特定章节，而非整页内容
验证代码示例是否完整
记录版本兼容性

Document Format

文档格式

Save all knowledge files to

.claude/skills/project-knowledge-base/references/

using the template in

references/document-template.md

使用

references/document-template.md

中的模板，将所有知识文件保存至

.claude/skills/project-knowledge-base/references/

目录。

File Naming

文件命名

Format:

{technology}-{topic}.md

Examples:

```
react-useeffect-cleanup.md
```
```
effect-pipe-operator.md
```
```
prisma-relations.md
```
```
nextauth-jwt-session.md
```

Rules:

All lowercase
Hyphens between words
Technology first, then topic
No version numbers in filename

格式：

{technology}-{topic}.md

示例：

```
react-useeffect-cleanup.md
```
```
effect-pipe-operator.md
```
```
prisma-relations.md
```
```
nextauth-jwt-session.md
```

规则：

全小写
单词间用连字符连接
先写技术名称，再写主题
文件名中不包含版本号

Frontmatter Structure

前置元数据结构

Required fields in YAML frontmatter:

```
topic
```
: Descriptive title
```
technology
```
: Library/framework name
```
version
```
: Version researched (or "latest")
```
sources
```
: List of URLs used
```
created
```
: Date in YYYY-MM-DD format
```
context
```
: Original problem that triggered research

YAML前置元数据中的必填字段：

```
topic
```
: 描述性标题
```
technology
```
: 库/框架名称
```
version
```
: 研究的版本（或"latest"）
```
sources
```
: 使用的URL列表
```
created
```
: 创建日期，格式为YYYY-MM-DD
```
context
```
: 触发研究的原始问题

Progressive Disclosure

渐进式披露

Threshold: 500 lines

When a reference file exceeds 500 lines, split into a tree structure:

references/tanstack-router.md  (>500 lines)
↓ split to
references/tanstack-router/
├── _index.md        # Overview + TOC linking to sub-files
├── route-guards.md
├── data-loading.md
└── navigation.md

阈值：500行

当参考文件超过500行时，拆分为树形结构：

references/tanstack-router.md  (>500 lines)
↓ split to
references/tanstack-router/
├── _index.md        # Overview + TOC linking to sub-files
├── route-guards.md
├── data-loading.md
└── navigation.md

When to Split

拆分时机

Single reference file exceeds 500 lines
Topic has clearly distinct sub-topics
Different aspects serve different use cases

单个参考文件超过500行
主题包含明确区分的子主题
不同方面服务于不同的使用场景

Split Structure

拆分结构

_index.md: Overview, quick reference, TOC with links
Sub-files: One file per major sub-topic
Cross-references: Link between related sub-files

_index.md：概述、快速参考、带链接的目录
子文件：每个主要子主题对应一个文件
交叉引用：在相关子文件之间建立链接

SKILL.md Update

SKILL.md更新

After splitting, update SKILL.md index to reference

_index.md

markdown

- [tanstack-router](references/tanstack-router/_index.md) - TanStack Router comprehensive guide

拆分完成后，更新SKILL.md索引以引用

_index.md

：