search-and-fetch

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Search & Fetch

通用搜索与内容提取技能，提供两个核心能力：搜索模式（多源并行搜索 + 结果综合）和提取模式（URL 内容提取 + 结构化分析）。

General search and content extraction skill, providing two core capabilities: Search Mode (multi-source parallel search + result synthesis) and Fetch Mode (URL content extraction + structured analysis).

工具概览

Tool Overview

本技能编排以下几类工具，按需组合使用：

类别	工具	说明
内置搜索	`WebSearch`	DuckDuckGo 搜索，始终可用
MCP 搜索	当前环境中可用的 MCP 搜索工具	中文搜索、专业搜索等，按可用性自动选用
技术文档	`ctx7` CLI	编程库/框架官方文档查询
浏览器	`agent-browser` CLI	访问搜索引擎、提取 JS 重度页面（Rust 原生，token 高效）
内容提取	`defuddle` CLI → `WebFetch` → MCP fetch → `agent-browser`	按优先级降级

具体调用语法参见

references/tool-catalog.md

。

This skill orchestrates the following types of tools, combining them as needed:

Category	Tool	Description
Built-in Search	`WebSearch`	DuckDuckGo search, always available
MCP Search	Available MCP search tools in the current environment	Chinese search, professional search, etc., automatically selected based on availability
Technical Docs	`ctx7` CLI	Query official docs for programming libraries/frameworks
Browser	`agent-browser` CLI	Access search engines, extract content from JS-heavy pages (Rust native, token-efficient)
Content Extraction	`defuddle` CLI → `WebFetch` → MCP fetch → `agent-browser`	Degrade by priority

Refer to

references/tool-catalog.md

for specific invocation syntax.

意图检测

Intent Detection

本技能负责所有 URL 和搜索意图的识别与路由。根据用户输入自动判断：

This skill is responsible for identifying and routing all URL and search intents. Automatically judge based on user input:

URL 检测

URL Detection

情况	处理
消息仅含 URL（无其他文字，或只有 URL + 空格/标点）	直接进入 Fetch Mode
消息含 URL + 阅读意图（"读一下"、"分析"、"看看这个"）	直接进入 Fetch Mode
消息含 URL + 保存意图（"保存"、"clip"、"save"、"归档"）	Fetch Mode 完成后，自动触发知识库技能的 Clipping Save
URL 出现在较长消息中，意图不明	询问："要我提取内容分析，还是只需要链接？"
URL 明显是工具性的（localhost、内网地址、文件路径）	不触发

Scenario	Handling
Message contains only URL (no other text, or only URL + spaces/punctuation)	Directly enter Fetch Mode
Message contains URL + reading intent ("read this", "analyze", "take a look at this")	Directly enter Fetch Mode
Message contains URL + save intent ("save", "clip", "save", "archive")	After completing Fetch Mode, automatically trigger the Clipping Save of the knowledge base skill
URL appears in a long message with unclear intent	Ask: "Would you like me to extract and analyze the content, or just keep the link?"
URL is obviously tool-based (localhost, internal network address, file path)	Do not trigger

搜索检测

Search Detection

情况	处理
用户提问、研究主题、需要查找信息	Search Mode
提供 URL + "搜索更多类似的"	先 Fetch 再 Search
其他技能委托调用	按委托方指定的模式执行

Scenario	Handling
User asks questions, researches topics, needs to find information	Search Mode
Provides URL + "search for more similar content"	First Fetch then Search
Delegated call by other skills	Execute according to the mode specified by the delegator

Search Mode

多源并行搜索，综合去重后输出结构化结果。

Multi-source parallel search, output structured results after deduplication and synthesis.

Step 1 — 查询分类

Step 1 — Query Classification

根据查询内容判断类型，选择工具组合：

查询类型	判断依据	工具组合
技术文档	涉及编程库、API、框架用法	`ctx7` （library → docs）+ `WebSearch`
中文内容	中文查询，或中国特定话题	MCP 搜索 + `WebSearch` 并行
通用查询	其他一般性问题	`WebSearch` + MCP 搜索并行
深度研究	用户明确要求全面/深入调研	全部工具并行，含 `agent-browser` 访问 Google/Bing

Judge the type based on query content, select tool combinations:

Query Type	Judgment Basis	Tool Combination
Technical Docs	Involves programming libraries, APIs, framework usage	`ctx7` (library → docs) + `WebSearch`
Chinese Content	Chinese query, or China-specific topics	MCP search + `WebSearch` in parallel
General Query	Other general questions	`WebSearch` + MCP search in parallel
In-depth Research	User explicitly requests comprehensive/in-depth research	All tools in parallel, including `agent-browser` to access Google/Bing

Step 2 — 并行执行搜索

Step 2 — Parallel Search Execution

根据分类结果，在同一轮响应中并行调用多个搜索工具。工具调用细节参见

references/tool-catalog.md

。

关键原则：

独立工具并行调用，不等待
context7 有顺序依赖：先
```
ctx7 library
```
解析库 ID，再
```
ctx7 docs
```
查询内容（每个问题最多 3 次调用）
对同一查询可以为不同搜索引擎调整措辞（如中文查询给 MCP 搜索原文，给 WebSearch 翻译为英文）
深度研究时使用
```
agent-browser
```
打开 Google/Bing 搜索页，通过
```
snapshot
```
获取元素引用后提取结果

Based on classification results, call multiple search tools in parallel within the same response round. Refer to

references/tool-catalog.md

for tool invocation details.

Key Principles:

Call independent tools in parallel, no waiting
context7 has sequential dependencies: first
```
ctx7 library
```
to resolve library ID, then
```
ctx7 docs
```
to query content (max 3 calls per question)
Adjust wording for different search engines for the same query (e.g., send original Chinese query to MCP search, translate to English for WebSearch)
For in-depth research, use
```
agent-browser
```
to open Google/Bing search pages, extract results after getting element references via
```
snapshot
```

Step 3 — 结果综合

Step 3 — Result Synthesis

去重：按 URL 去重，合并来自不同来源的同一页面信息
分组：按子主题或关联度分组
排序：按相关性和信息质量排序
输出格式：

markdown

undefined

Deduplication: Deduplicate by URL, merge information from the same page from different sources
Grouping: Group by sub-topic or relevance
Sorting: Sort by relevance and information quality
Output Format:

markdown

undefined

搜索结果：[查询主题]

Search Results: [Query Topic]

[子主题 1]

[Sub-topic 1]

要点摘要（来源：标题）
要点摘要（来源：标题）

Key point summary (Source: Title)
Key point summary (Source: Title)

[子主题 2]

[Sub-topic 2]

来源列表

标题 — 简述
标题 — 简述

undefined

Source List

Title — Brief description
Title — Brief description

undefined

Step 4 — 后续操作

Step 4 — Follow-up Operations

搜索结果展示后，提供后续选项：

"要我读取某个链接的完整内容吗？" → 转入 Fetch Mode
"要保存到知识库吗？" → 引导用户触发 obsidian-knowledge 等知识管理技能
用户可继续追问以缩小或扩大搜索范围

After displaying search results, provide follow-up options:

"Would you like me to read the full content of a certain link?" → Switch to Fetch Mode
"Would you like to save to the knowledge base?" → Guide users to trigger knowledge management skills like obsidian-knowledge
Users can continue to ask questions to narrow or expand the search scope

Fetch Mode

从 URL 提取干净内容并进行结构化分析。

Extract clean content from URLs and perform structured analysis.

Step 1 — 提取内容

Step 1 — Content Extraction

按优先级尝试，前一个失败（报错、返回空、内容 < 100 字符）时自动降级：

1. defuddle parse <url> --md          ← 首选，去除噪音
2. WebFetch(url)                       ← 通用降级
3. MCP fetch 工具（如有）               ← MCP 降级
4. agent-browser open <url> → snapshot → get text   ← JS 重度页面最终手段

提取成功后记录使用了哪个工具，便于透明告知用户。

工具调用细节参见

references/tool-catalog.md

。

Attempt in priority order, automatically degrade if the previous one fails (error, returns empty, content < 100 characters):

1. defuddle parse <url> --md          ← Preferred, removes noise
2. WebFetch(url)                       ← General degradation
3. MCP fetch tool (if available)               ← MCP degradation
4. agent-browser open <url> → snapshot → get text   ← Final resort for JS-heavy pages

Record which tool was used after successful extraction, to transparently inform users.

Refer to

references/tool-catalog.md

for tool invocation details.

Step 2 — 结构化分析

Step 2 — Structured Analysis

根据内容类型选择性应用分析维度。详细模板参见

references/analysis-template.md

。

内容类型	适用维度
文章、评论、论文	全部五维（文本解构 → 概念提炼 → 批判审视 → 思想深化 → 实践转化）
新闻、产品页	文本解构 + 概念提炼 + 实践转化
教程、技术文档	文本解构 + 概念提炼 + 实践转化
数据页、API 文档、参考表	跳过分析，直接呈现提取内容

Selectively apply analysis dimensions based on content type. See

references/analysis-template.md

for detailed templates.

Content Type	Applicable Dimensions
Articles, comments, papers	All five dimensions (text deconstruction → concept extraction → critical examination → idea deepening → practical transformation)
News, product pages	Text deconstruction + concept extraction + practical transformation
Tutorials, technical docs	Text deconstruction + concept extraction + practical transformation
Data pages, API docs, reference tables	Skip analysis, directly present extracted content

Step 3 — 输出

Step 3 — Output

两种输出模式：

独立模式（用户直接使用时）：

markdown

undefined

Two output modes:

Standalone Mode (when used directly by users):

markdown

undefined

页面标题

Page Title

作者: xxx | 日期: xxx | 字数: xxx

Author: xxx | Date: xxx | Word Count: xxx

摘要

Summary

一段话总结。

A paragraph summary.

分析

Analysis

[按 analysis-template.md 输出适用维度]

[Output applicable dimensions according to analysis-template.md]

关键要点

Key Points

要点一
要点二
要点三


分析输出后，主动提示："要保存到知识库吗？" 若用户同意，引导触发 obsidian-knowledge 的 Clipping Save 流程。

**集成模式**（被其他技能委托调用时）：

以自然语言输出以下信息块，供调用方直接消费（不要输出 JSON）：

1. **页面标题**和**原始 URL**
2. **一句话摘要**
3. **关键要点**（要点列表）
4. **五维分析**（按适用维度输出）
5. **完整正文**（提取的干净 markdown 全文）
6. **提取的实体**：提到的工具/软件、股票/公司、人物（姓名+身份）、书籍/论文/资源

---

Point 1
Point 2
Point 3


After analysis output, actively prompt: "Would you like to save to the knowledge base?" If the user agrees, guide to trigger the Clipping Save process of obsidian-knowledge.

**Integration Mode** (when delegated by other skills):

Output the following information blocks in natural language, for direct consumption by the caller (do not output JSON):

1. **Page Title** and **Original URL**
2. **One-sentence Summary**
3. **Key Points** (list of points)
4. **Five-dimensional Analysis** (output applicable dimensions)
5. **Full Clean Text** (extracted clean markdown full text)
6. **Extracted Entities**: Mentioned tools/software, stocks/companies, people (name + identity), books/papers/resources

---

降级策略

Degradation Strategy

当某个工具不可用时的处理方式：

工具不可用	影响	替代方案
defuddle	无法提取干净正文	降级到 WebFetch
WebFetch	提取能力下降	使用 MCP fetch 或 agent-browser
MCP 搜索	搜索来源减少	用 WebSearch 处理所有查询
ctx7	无库文档搜索	用 WebSearch + site:xxx 定向搜索
agent-browser	无法处理 JS 重度页面	告知用户，使用 WebFetch 尽力提取
全部搜索工具	无法搜索	告知用户，建议直接提供 URL

不要因为某个工具失败就中断流程——始终尝试下一个降级方案，直到全部耗尽才告知用户。

Handling methods when a tool is unavailable:

Tool Unavailable	Impact	Alternative Solution
defuddle	Cannot extract clean main content	Degrade to WebFetch
WebFetch	Reduced extraction capability	Use MCP fetch or agent-browser
MCP search	Reduced search sources	Use WebSearch for all queries
ctx7	No library doc search	Use WebSearch + site:xxx targeted search
agent-browser	Cannot process JS-heavy pages	Inform users, use WebFetch to extract as much as possible
All search tools	Cannot search	Inform users, suggest providing URL directly

Do not interrupt the process because a tool fails — always try the next degradation solution until all are exhausted before informing the user.

集成协议

Integration Protocol

本技能可被其他技能委托调用。调用方在自己的 SKILL.md 中指定"委托 search-and-fetch"即可。

This skill can be called by other skills. The delegator only needs to specify "delegate to search-and-fetch" in their own SKILL.md.

被委托时的行为

Behavior When Delegated

按调用方指定的模式（Search/Fetch）执行
使用集成模式输出格式
不直接与用户交互后续问题（由调用方处理）
如果内容提取完全失败，返回失败标记和原因，由调用方决定如何告知用户

Execute according to the mode (Search/Fetch) specified by the delegator
Use Integration Mode output format
Do not directly interact with users about follow-up questions (handled by the delegator)
If content extraction completely fails, return failure marker and reason, and the delegator decides how to inform the user