General-purpose search and content extraction skill, providing two core capabilities:Search mode(multi-source parallel search + result synthesis) andExtraction mode(URL content extraction + structured analysis).
Tool overview
This skill orchestrates the following categories of tools, used in combination as needed:
| Category | Tool | Description |
|---|---|---|
| Built-in search | WebSearch |
DuckDuckGo search, always available |
| MCP search | MCP search tools available in the current environment | Chinese-language search, specialized search, etc., automatically selected based on availability |
| Technical documentation | ctx7 CLI |
Official documentation lookup for programming libraries/frameworks |
| Browser | agent-browser CLI |
Access search engines, page interaction (Rust native, token-efficient) |
| Content extraction | crwl CLI → agent-browser |
Degrade by priority |
For specific call syntax, see references/tool-catalog.md。
Intent detection
This skill is responsible for identifying and routing all URL and search intents. Automatically determine based on user input:
URL detection
| Situation | Handling |
|---|---|
| MessageContains only a URL(no other text, or only URL + spaces/punctuation) | Go directly to Fetch Mode |
| Message contains URL + reading intent ("read this", "analyze", "take a look at this") | Go directly to Fetch Mode |
| Message contains URL + save intent ("save", "clip", "save", "archive") | Fetch Mode After completion, automatically trigger the knowledge base skill's Clipping Save |
| URL appears in a longer message, intent unclear | Ask: "Do you want me to extract the content and analyze it, or do you just need the link?" |
| URL is clearly utilitarian (localhost, intranet address, file path) | Do not trigger |
Search detection
| Situation | Handling |
|---|---|
| User asks a question, research topic, needs to find information | Search Mode |
| Provides URL + "search for more similar ones" | Fetch first, then Search |
| Delegated call from another skill | Execute in the mode specified by the delegating party |
Search Mode
Multi-source parallel search, synthesized and deduplicated, then output structured results.
Step 1 — Query classification
Determine the type based on the query content, and select the tool combination:
| Query type | Basis for determination | Tool combination |
|---|---|---|
| Technical documentation | Involves programming libraries, APIs, framework usage | ctx7(library → docs)+ WebSearch |
| General query | General questions | WebSearch + MCP search in parallel (Chinese queries prefer MCP search) |
| Deep research | User explicitly requests comprehensive/in-depth investigation | All tools in parallel, including agent-browser access Google/Bing |
Step 2 — Execute searches in parallel
Based on the classification results, withinthe same round of responsescall multiple search tools in parallel. For tool call details, see references/tool-catalog.md。
Key principles:
- Independent tools are called in parallel without waiting
- context7 has sequential dependencies: first
ctx7 libraryresolve the library ID, thenctx7 docsquery the content (at most 3 calls per question) - For the same query, wording can be adjusted for different search engines (e.g., for Chinese queries, provide the original text to MCP Search, and translate it into English for WebSearch)
- For deep research, use
agent-browseropen the Google/Bing search page, and throughsnapshotobtain element references and then extract the results
Step 3 — Result synthesis
- Deduplicate: deduplicate by URL, merging information from the same page across different sources
- Group: group by subtopic or degree of relevance
- Sort: sort by relevance and information quality
- Output format:
## 搜索结果:[查询主题]
### [子主题 1]
- 要点摘要(来源:[标题](url))
- 要点摘要(来源:[标题](url))
### [子主题 2]
- ...
---
**来源列表**
1. [标题](url) — 简述
2. [标题](url) — 简述
Step 4 — Follow-up actions
After the search results are displayed, provide follow-up options:
- "Do you want me to read the full content of a link?" → Switch to Fetch Mode
- "Do you want to save it to the knowledge base?" → Guide the user to trigger the knowledge management skill
- The user can continue asking follow-up questions to narrow or broaden the search scope
Fetch Mode
Extract clean content from a URL and perform structured analysis.
Step 1 — Extract content
Try in order of priority, and automatically fall back when the previous one fails (errors, returns empty, content < 100 characters):
1. crwl <url> -o md-fit ← 首选,支持 JS 渲染
2. agent-browser open <url> → snapshot → get text ← 最终手段
After successful extraction, record which tool was used, so the user can be informed transparently.
For tool call details, see references/tool-catalog.md。
Step 2 — Structured analysis
Selectively apply analysis dimensions based on the content type. For detailed templates, see references/analysis-template.md。
| Content type | Applicable dimensions |
|---|---|
| Articles, reviews, papers | All five dimensions (text deconstruction → concept extraction → critical examination → thought deepening → practical transformation) |
| News, product pages | Text deconstruction + concept extraction + practical transformation |
| Tutorials, technical documentation | Text deconstruction + concept extraction + practical transformation |
| Data pages, API documentation, reference tables | Skip analysis and directly present the extracted content |
Step 3 — Output
Two output modes:
Standalone mode(when used directly by the user):
## [页面标题](url)
**作者**: xxx | **日期**: xxx | **字数**: xxx
### 摘要
一段话总结。
### 分析
[按 analysis-template.md 输出适用维度]
### 关键要点
- 要点一
- 要点二
- 要点三
After outputting the analysis, proactively prompt: "Do you want to save it to the knowledge base?" If the user agrees, guide them to trigger the knowledge management skill's save process.
Integrated mode(when delegated by other skills):
Output the following information blocks in natural language for the caller to consume directly (do not output JSON):
- Page titleandOriginal URL
- One-sentence summary
- Key points(list of points)
- Five-dimensional analysis(output according to applicable dimensions)
- Full body text(the full extracted clean markdown text)
- Extracted entities: tools/software, stocks/companies, people (name + role), books/papers/resources mentioned
Fallback strategy
How to handle when a certain tool is unavailable:
| Tool unavailable | Impact | Alternative |
|---|---|---|
| crwl | Unable to extract content | Fall back to agent-browser |
| MCP search | Fewer search sources | Use WebSearch to handle all queries |
| ctx7 | No library documentation search | Use WebSearch + site:xxx for targeted search |
| agent-browser | Unable to handle JS-heavy pages | Inform the user, extraction failed |
| All search tools | Unable to search | Inform the user, suggest providing the URL directly |
Do not interrupt the process just because a certain tool fails—always try the next fallback until all are exhausted before informing the user.
Integration protocol
This skill can be invoked by delegation from other skills. The caller can simply specify "delegate search-and-fetch" in its own SKILL.md.
Behavior when delegated
- Execute in the mode specified by the caller (Search/Fetch)
- UseIntegration modeOutput format
- Do not directly interact with the user for follow-up questions (handled by the caller)
- If content extraction fails completely, return a failure flag and reason, and let the caller decide how to inform the user