Back to Details

web-research-workflow

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Web Research Workflow

网页调研工作流

Unified approach for web content research that automatically selects the right tool for each situation.
一种针对网页内容调研的统一方案，可根据不同场景自动选择合适的工具。

Quick Decision Tree

快速决策树

URL to research
     │
     ▼
┌─────────────────┐
│ 1. Try WebFetch │ ← Fast, free, no overhead
│    (always try) │
└─────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (empty/partial/<500 chars)
     │
     ▼
┌───────────────────────┐
│ 2. TAVILY_API_KEY set?│
└───────────────────────┘
     │          │
    Yes         No ──► Skip to step 3
     │
     ▼
┌───────────────────────────┐
│ Tavily search/extract/    │ ← Raw markdown, batch URLs
│ crawl/research            │
└───────────────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (JS-rendered/auth-required)
     │
     ▼
┌─────────────────────┐
│ 3. Use agent-browser │ ← Full browser, last resort
└─────────────────────┘
     │
├─ SPA (react/vue/angular) ──► wait --load networkidle
├─ Login required ──► auth flow + state save
├─ Dynamic content ──► wait --text "Expected"
└─ Multi-page ──► crawl pattern
URL to research
     │
     ▼
┌─────────────────┐
│ 1. Try WebFetch │ ← Fast, free, no overhead
│    (always try) │
└─────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (empty/partial/<500 chars)
     │
     ▼
┌───────────────────────┐
│ 2. TAVILY_API_KEY set?│
└───────────────────────┘
     │          │
    Yes         No ──► Skip to step 3
     │
     ▼
┌───────────────────────────┐
│ Tavily search/extract/    │ ← Raw markdown, batch URLs
│ crawl/research            │
└───────────────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (JS-rendered/auth-required)
     │
     ▼
┌─────────────────────┐
│ 3. Use agent-browser │ ← Full browser, last resort
└─────────────────────┘
     │
├─ SPA (react/vue/angular) ──► wait --load networkidle
├─ Login required ──► auth flow + state save
├─ Dynamic content ──► wait --text "Expected"
└─ Multi-page ──► crawl pattern

Tavily Enhanced Research

Tavily增强型调研

When 
TAVILY_API_KEY
is set, Tavily provides a powerful middle tier between WebFetch and agent-browser. It returns raw markdown content, supports batch URL extraction, and offers semantic search with relevance scoring. If 
TAVILY_API_KEY
is not set, the 3-tier tree collapses to 2-tier (WebFetch → agent-browser) automatically.
Load details: 
Read("${CLAUDE_SKILL_DIR}/rules/tool-selection.md")
for when-to-use-what tables, escalation heuristics, SPA detection patterns, and cost awareness.
Load details: 
Read("${CLAUDE_SKILL_DIR}/references/tavily-api.md")
for Search, Extract, Map, Crawl, and Research endpoint examples and options.
当配置了
TAVILY_API_KEY
时，Tavily在WebFetch和agent-browser之间提供了一个功能强大的中间层。它可返回原始markdown内容，支持批量URL提取，并提供带有相关性评分的语义搜索。如果未配置
TAVILY_API_KEY
，三层决策树会自动简化为两层（WebFetch → agent-browser）。
加载详细信息：
Read("${CLAUDE_SKILL_DIR}/rules/tool-selection.md")
获取工具使用场景表、升级启发规则、SPA检测模式以及成本相关说明。
加载详细信息：
Read("${CLAUDE_SKILL_DIR}/references/tavily-api.md")
获取Search、Extract、Map、Crawl和Research端点的示例及配置选项。

Browser Patterns

浏览器模式

For content requiring JavaScript rendering, authentication, or multi-page crawling, fall back to agent-browser.
Load details: 
Read("${CLAUDE_SKILL_DIR}/rules/browser-patterns.md")
for auto-fallback, authentication flow, multi-page research patterns, best practices, and troubleshooting.
对于需要JavaScript渲染、身份验证或多页面爬取的内容，可降级到agent-browser。
加载详细信息：
Read("${CLAUDE_SKILL_DIR}/rules/browser-patterns.md")
获取自动降级、身份验证流程、多页面调研模式、最佳实践及故障排除方法。

Competitive Monitoring

竞品监控

Track competitor websites for changes in pricing, features, positioning, and content.
Load details: 
Read("${CLAUDE_SKILL_DIR}/rules/monitoring-competitor.md")
for snapshot capture, structured data extraction, and change classification.
Load details: 
Read("${CLAUDE_SKILL_DIR}/rules/monitoring-change-detection.md")
for diff detection, structured comparison, Tavily site discovery, and CI automation.
追踪竞品网站的定价、功能、定位和内容变更。
加载详细信息：
Read("${CLAUDE_SKILL_DIR}/rules/monitoring-competitor.md")
获取快照捕获、结构化数据提取和变更分类的相关内容。
加载详细信息：
Read("${CLAUDE_SKILL_DIR}/rules/monitoring-change-detection.md")
获取差异检测、结构化对比、Tavily站点发现和CI自动化的相关内容。

Change Classification

变更分类

SeverityExamplesAction
CriticalPrice increase/decrease, major feature changeImmediate alert
HighNew feature added, feature removedReview required
MediumCopy changes, positioning shiftNote for analysis
LowTypos, minor stylingLog only
严重级别示例行动建议
严重价格上涨/下降、重大功能变更立即告警
高新增功能、移除功能需要评审
中文案变更、定位调整记录用于分析
低拼写错误、轻微样式调整仅记录

Integration with Agents

与Agent的集成

This skill is used by:
  • web-research-analyst
    - Primary user
  • market-intelligence
    - Competitor research
  • product-strategist
    - Deep competitive analysis
该技能被以下角色使用：
  • web-research-analyst
    - 主要使用者
  • market-intelligence
    - 竞品调研
  • product-strategist
    - 深度竞品分析

Related Skills

相关技能

  • browser-content-capture
    - Detailed browser patterns
  • agent-browser
    - CLI reference
Version: 1.3.0 (February 2026)
  • browser-content-capture
    - 详细浏览器模式
  • agent-browser
    - CLI参考文档
**版本：**1.3.0（2026年2月）