sales-account-intelligence

作者: tavily-ai

为各类公司、潜在客户、现有客户、合作伙伴及目标买家构建可直接用于销售的账户情报。当用户需要销售准备、账户简报等信息时使用。

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

Sales Account Intelligence

Workflow

Use search and extract to produce fast, useful sales account context with cited sources; use map or crawl only when a known company site needs scoped navigation. Keep this skill focused on research planning, query construction, source selection, and sales-ready 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.

  • Define the account, audience, sales motion, geography, and meeting or outreach goal.
  • Split research into short subqueries under 400 characters: company overview, recent news, products, customers, leadership, funding/financials, hiring, partnerships, pain points, and relevant initiatives.
  • Use search for discovery, then filter by source quality before extracting.
  • Extract the strongest sources: official website, newsroom, product pages, customer stories, investor/press pages, credible news, job postings, and relevant executive profiles.
  • Use site navigation when the company site is large and useful pages are hard to find.
  • Collect scoped site sections only when the user needs broad coverage of customers, case studies, news, products, solutions, or careers.

Research Budget

  • Start with a small focused search set: account overview, recent triggers, product/initiative context, and buyer/pain-point evidence.
  • Extract only the strongest sources before drafting the brief.
  • Add more searches only for named gaps that block the brief, such as missing trigger events or missing official product context.
  • Do not use map until search finds the company domain and there is a specific buried page type to locate.
  • Do not use crawl for first-pass account prep unless the user explicitly asks for a site scan.

Capability Guidance

  • Use search for most account briefs, meeting prep, outreach research, and trigger-event checks.
  • Use extract on selected official pages, newsroom posts, customer stories, credible news, job postings, and executive profiles.
  • Use map when the company domain is known but important pages are buried.
  • Use crawl for account site scans only after narrowing to sections that support the sales goal.
  • Use research only when the user asks for a deep strategic account report.

Query And Source Guidance

  • Include company name, aliases, product names, executive names, industry terms, geography, and the sales motion in separate subqueries.
  • For trigger events, use explicit recency language and search for funding, hiring, partnerships, launches, expansion, regulation, incidents, and leadership changes.
  • Prioritize official company pages, newsroom posts, customer stories, product pages, investor or press pages, credible news, job postings, and relevant executive profiles.
  • Treat LinkedIn-style profile snippets, unsourced lists, and old syndicated pages as lower confidence.
  • Report failed or inaccessible sources when they affect trigger events, official pages, customer evidence, or buyer context.

Output Template

Use this markdown structure and keep it practical:

# Account Brief: <company>

## Account Snapshot
- What they do:
- Size/market/geography:
- Relevant products or business lines:

## Trigger Events
- <event>: <why it matters> ([source](URL))

## Business Priorities And Likely Pain Points
- Priority:
- Evidence:
- Sales relevance:

## Buyer And Executive Context
- Person/team:
- Relevant context:
- Confidence:

## Outreach Angles
- Angle:
- Supporting evidence:
- Discovery question:

## Source Gaps
- <missing or uncertain item>

Keep claims practical. Do not invent budget, intent, internal priorities, or buyer names when sources do not support them.

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