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

academic-scientific-research
tavily-ai
查找、筛选并综合学术论文、科学文献、技术报告、预印本、临床或生物医学出版物,以及围绕某一…的证据。
crawl
tavily-ai
提取网站内容并保存为markdown文件,以便离线访问和分析。支持可配置的爬取深度(1-5层)、广度限制和页面上限,以平衡覆盖范围与性能。通过正则表达式路径过滤,聚焦特定部分并排除无关内容。提供两种模式:全页提取用于数据收集,或基于自然语言指令的语义分块,将结果输入LLM上下文。附带Map API用于URL...
extract
tavily-ai
使用Tavily的提取API从特定URL中提取干净内容。每次请求最多支持20个URL,可选基于查询的重新排序以聚焦相关内容块。两种提取模式:基础模式用于快速文本提取,高级模式用于JavaScript渲染页面和结构化数据。首次运行时通过浏览器自动进行OAuth认证,或在设置中手动配置API密钥。返回markdown或纯文本格式,可选包含图片URL,超时时间可配置至多60秒。
investment-research-briefs
tavily-ai
生成简洁的投资研究简报、公司备忘录、行业快照、投资组合监控更新、财报/新闻摘要、风险与催化剂简报……
product-competitor-intelligence
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……
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...
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;...
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...