product-competitor-intelligence

作者: tavily-ai

调研竞品产品、SKU、定价、包装、定位、功能对比、产品目录、品类页面、零售商列表、市场……

npx skills add https://github.com/tavily-ai/use-case-skills --skill product-competitor-intelligence

Product Competitor Intelligence

Workflow

Use search and extract for product, pricing, SKU, feature, and competitor intelligence; use map or crawl for known catalogs and large competitor sites. Keep this skill focused on query construction, site navigation, source filtering, and synthesis; execution mechanics should come from companion endpoint skills.

Treat the guidance below as base guidance; adapt it to the user's request when appropriate.

  • Clarify the category, competitors, geography, target customer, price band, feature set, and desired output format.
  • Split broad questions into short subqueries under 400 characters: competitors, product category, pricing, alternatives, reviews, SKUs, specs, marketplaces, and recent launches.
  • Search for relevant competitors, product pages, category pages, retailer listings, pricing pages, reviews, docs, and official sources.
  • Filter by relevance score, domain trust, page type, and freshness before extracting.
  • Extract only selected pages that can support the requested comparison, table, or brief.
  • Use site mapping before broad collection on known competitor, retailer, manufacturer, marketplace, docs, or catalog domains.
  • Collect multiple pages only after choosing relevant path patterns and a tight scope.

Research Budget

  • Start with a small focused search set covering competitors, category, pricing, features/specs, reviews, or launches.
  • Extract only the strongest product, pricing, catalog, marketplace, docs, or review pages before drafting.
  • Add more searches only for named gaps, such as missing pricing, missing SKU evidence, or missing official competitor pages.
  • Do not use map unless a known competitor, retailer, manufacturer, marketplace, docs, or catalog domain needs URL discovery.
  • Do not use crawl until map has identified a narrow product, pricing, category, docs, or catalog section.

Capability Guidance

  • Use search for competitor discovery, pricing checks, feature comparisons, product claims, reviews, and launch signals.
  • Use extract on selected product, pricing, docs, catalog, marketplace, review, or changelog pages.
  • Use map when the domain is known but the relevant product, pricing, changelog, docs, category, or catalog pages are hard to find.
  • Use crawl for SKU/catalog discovery only after narrowing to relevant sections.
  • Use research only when the user asks for a market report rather than product-level evidence.

Query And Source Guidance

  • Include product category, buyer segment, geography, price band, SKU/model terms, competitor names, and feature terms in separate subqueries.
  • Prioritize official product pages, pricing pages, docs, catalogs, retailer listings, marketplaces, review sites, customer stories, changelogs, and credible launch coverage.
  • For known sites, look for paths such as products, pricing, category, collections, docs, blog, changelog, customers, or case studies.
  • Avoid irrelevant paths such as login, cart, checkout, account, admin, tag archives, and unrelated content.
  • Dedupe near-identical product pages, regional variants, and syndicated listings before synthesis.
  • Report failed or inaccessible sources when they affect pricing, specs, availability, or competitor coverage.

Output Template

Use this markdown structure and adapt columns to the user's request:

# Product And Competitor Intelligence: <category/company>

## Scope
- Category:
- Geography:
- Competitors covered:
- Source coverage limits:

## Product Comparison
| Product/SKU | Company | Category | Pricing/availability | Key features/specs | Positioning | Source |
| --- | --- | --- | --- | --- | --- | --- |

## Competitor Notes
### <Competitor>
- Positioning:
- Product/pricing evidence:
- Strengths:
- Gaps or uncertainty:

## Market Signals
- Launches or changes:
- Review/customer signals:
- Distribution or channel signals:

## Follow-Up Searches
- <query idea>

Keep each claim tied to a source. Mark pricing, availability, or specs as unavailable when they are not visible.

来自 tavily-ai 的更多技能

research
tavily-ai
针对任意主题进行综合研究,自动收集来源、分析并生成引用。通过多源网络研究并附带明确引用,适用于对比分析、时事追踪、市场调研及详细报告。提供三种模型选项:mini用于针对性单主题研究(约30秒),pro用于全面多角度分析(约60-120秒),auto通过API自动检测复杂度。通过Tavily MCP服务器的OAuth进行身份验证,支持基于浏览器的自动登录...
official
search
tavily-ai
基于LLM优化的网页搜索,具备相关性评分与灵活筛选功能。支持四种搜索深度模式(极速、快速、基础、高级),可配置延迟与相关性权衡。包含域名过滤、时间范围限制、日期区间、国家加权及原始内容提取。返回结果含标题、URL、内容摘要及相关性评分;可选图片结果与网站图标。通过Tavily MCP服务器或API密钥配置实现自动OAuth认证;...
official
tavily-best-practices
tavily-ai
面向LLM的网页搜索API,支持实时数据访问、内容提取、站点爬取及AI驱动研究。五大核心方法:search()获取网页结果,extract()提取URL内容,crawl()进行全站提取,map()发现URL,research()实现端到端AI综合。提供Python和JavaScript SDK,支持异步客户端并行查询及可配置搜索深度(极速/快速/基础/高级)。crawl方法接受语义指令以聚焦提取内容...
official
tavily-cli
tavily-ai
通过Tavily CLI实现网页搜索、内容提取、站点爬取及深度研究。五种命令模式涵盖搜索、提取、URL发现、批量爬取及带引用的多源研究。所有命令支持JSON输出及文件保存,适用于结构化、智能体工作流。升级模式根据需求引导您从简单搜索逐步过渡到提取、映射、爬取乃至全面研究。需安装tavily-cli并通过tvly login进行API密钥认证。
official
tavily-crawl
tavily-ai
多页网站爬虫,具备语义过滤和Markdown导出功能。可控制深度和广度爬取整个网站部分;通过路径正则表达式、域名或自然语言指令过滤结果,聚焦所需内容。使用--output-dir参数将每个页面保存为本地Markdown文件,或返回结构化JSON供智能体处理。采用语义指令与分块提取,防止向LLM输入结果时上下文膨胀;支持全页提取用于离线文档下载。支持...
official
tavily-dynamic-search
tavily-ai
搜索网络、过滤结果并提取内容,使原始搜索数据永远不会进入您的上下文窗口。只有您精心整理的print()输出会返回。
official
tavily-extract
tavily-ai
从最多20个URL中提取干净的Markdown或文本,支持JavaScript渲染和查询聚焦分块。可处理JavaScript渲染页面,提取深度可配置(简单页面使用基础模式,动态SPA和表格使用高级模式)。支持查询聚焦提取,仅返回相关的内容块而非完整页面。默认返回经LLM优化的Markdown格式,也可选择纯文本格式和结构化JSON输出。单次调用最多处理20个URL;...
official
tavily-map
tavily-ai
快速发现网站上的URL而不提取内容,适用于在大型网站上查找特定页面。返回域内所有URL的结构化列表,支持可配置的深度和广度、正则表达式路径过滤,以及用于语义过滤的自然语言指令。支持深度控制(1-5层)、每页广度限制、外部链接的包含/排除,以及通过正则表达式模式进行域过滤。设计为工作流程中的第一步:通过映射找到正确页面,然后使用提取或...
official