lead-intelligence

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Lead Intelligence

线索情报

Agent-powered lead intelligence pipeline that finds, scores, and reaches high-value contacts through social graph analysis and warm path discovery.

基于Agent驱动的线索情报流程，通过社交图谱分析和暖路径发现功能，实现高价值联系人的查找、评分与对接。

When to Activate

触发场景

User wants to find leads or prospects in a specific industry
Building an outreach list for partnerships, sales, or fundraising
Researching who to reach out to and the best path to reach them
User says "find leads", "outreach list", "who should I reach out to", "warm intros"
Needs to score or rank a list of contacts by relevance
Wants to map mutual connections to find warm introduction paths

用户需要查找特定行业的线索或潜在客户
为合作、销售或募资搭建外联名单
调研需要对接的对象以及最佳对接路径
用户提及「找线索」、「外联名单」、「我该联系谁」、「熟人介绍」等内容
需要按相关性对联系人列表进行评分或排名
需要梳理共同联系人以找到熟人介绍路径

Tool Requirements

工具要求

Required

必选

Exa MCP — Deep web search for people, companies, and signals (
```
web_search_exa
```
)
X API — Follower/following graph, mutual analysis, recent activity (
```
X_BEARER_TOKEN
```
,
```
X_ACCESS_TOKEN
```
)

Exa MCP — 用于人物、企业和信号的深度网络搜索（
```
web_search_exa
```
）
X API — 用于关注/粉丝关系图谱、共同关联分析、近期动态查询（需要配置
```
X_BEARER_TOKEN
```
、
```
X_ACCESS_TOKEN
```
）

Optional (enhance results)

可选（用于优化结果）

LinkedIn — Via browser-use MCP or direct API for connection graph
Apollo/Clay API — For enrichment cross-reference if user has access
GitHub MCP — For developer-centric lead qualification

LinkedIn — 通过browser-use MCP或者直接调用API获取关系图谱
Apollo/Clay API — 如果用户有访问权限，可用于数据交叉补全
GitHub MCP — 用于面向开发者群体的线索筛选

Pipeline Overview

流程概览

┌─────────────┐     ┌──────────────┐     ┌─────────────────┐     ┌──────────────┐     ┌─────────────────┐
│ 1. Signal   │────>│ 2. Mutual    │────>│ 3. Warm Path    │────>│ 4. Enrich    │────>│ 5. Outreach     │
│    Scoring  │     │    Ranking   │     │    Discovery    │     │              │     │    Draft        │
└─────────────┘     └──────────────┘     └─────────────────┘     └──────────────┘     └─────────────────┘

┌─────────────┐     ┌──────────────┐     ┌─────────────────┐     ┌──────────────┐     ┌─────────────────┐
│ 1. Signal   │────>│ 2. Mutual    │────>│ 3. Warm Path    │────>│ 4. Enrich    │────>│ 5. Outreach     │
│    Scoring  │     │    Ranking   │     │    Discovery    │     │              │     │    Draft        │
└─────────────┘     └──────────────┘     └─────────────────┘     └──────────────┘     └─────────────────┘

Stage 1: Signal Scoring

阶段1：信号评分

Search for high-signal people in target verticals. Assign a weight to each based on:

Signal	Weight	Source
Role/title alignment	30%	Exa, LinkedIn
Industry match	25%	Exa company search
Recent activity on topic	20%	X API search, Exa
Follower count / influence	10%	X API
Location proximity	10%	Exa, LinkedIn
Engagement with your content	5%	X API interactions

在目标垂直领域搜索高信号值人物，根据以下维度为每个对象分配权重：

信号	权重	来源
角色/职位匹配度	30%	Exa、LinkedIn
行业匹配度	25%	Exa企业搜索
相关主题近期动态	20%	X API搜索、Exa
粉丝数/影响力	10%	X API
地理位置邻近度	10%	Exa、LinkedIn
对你内容的互动度	5%	X API互动数据

Signal Search Approach

信号搜索方法

python

undefined

python

undefined

Step 1: Define target parameters

target_verticals = ["prediction markets", "AI tooling", "developer tools"] target_roles = ["founder", "CEO", "CTO", "VP Engineering", "investor", "partner"] target_locations = ["San Francisco", "New York", "London", "remote"]

Step 2: Exa deep search for people

for vertical in target_verticals: results = web_search_exa( query=f"{vertical} {role} founder CEO", category="company", numResults=20 ) # Score each result

Step 3: X API search for active voices

x_search = search_recent_tweets( query="prediction markets OR AI tooling OR developer tools", max_results=100 )

Extract and score unique authors

undefined

undefined

Stage 2: Mutual Ranking

阶段2：双向排名

For each scored target, analyze the user's social graph to find the warmest path.

针对每个完成评分的目标对象，分析用户的社交图谱，找到最顺畅的对接路径。

Algorithm

算法

Pull user's X following list and LinkedIn connections
For each high-signal target, check for shared connections
Rank mutuals by:

Factor	Weight
Number of connections to targets	40% — highest weight, most connections = highest rank
Mutual's current role/company	20% — decision maker vs individual contributor
Mutual's location	15% — same city = easier intro
Industry alignment	15% — same vertical = natural intro
Mutual's X handle / LinkedIn	10% — identifiability for outreach

拉取用户的X关注列表和LinkedIn联系人
针对每个高信号值目标，检查是否有共同联系人
按以下维度对共同联系人排名：

影响因素	权重
与目标的连接数	40% — 权重最高，连接数越多排名越高
共同联系人的当前职位/所属公司	20% — 决策者权重高于普通员工
共同联系人的地理位置	15% — 同城更容易促成介绍
行业匹配度	15% — 同垂直领域的介绍更自然
共同联系人的X账号/LinkedIn信息	10% — 身份可识别度高便于外联

Output Format

输出格式

MUTUAL RANKING REPORT
=====================

#1  @mutual_handle (Score: 92)
    Name: Jane Smith
    Role: Partner @ Acme Ventures
    Location: San Francisco
    Connections to targets: 7
    Connected to: @target1, @target2, @target3, @target4, @target5, @target6, @target7
    Best intro path: Jane invested in Target1's company

#2  @mutual_handle2 (Score: 85)
    ...

MUTUAL RANKING REPORT
=====================

#1  @mutual_handle (Score: 92)
    Name: Jane Smith
    Role: Partner @ Acme Ventures
    Location: San Francisco
    Connections to targets: 7
    Connected to: @target1, @target2, @target3, @target4, @target5, @target6, @target7
    Best intro path: Jane invested in Target1's company

#2  @mutual_handle2 (Score: 85)
    ...

Stage 3: Warm Path Discovery

阶段3：暖路径发现

For each target, find the shortest introduction chain:

You ──[follows]──> Mutual A ──[invested in]──> Target Company
You ──[follows]──> Mutual B ──[co-founded with]──> Target Person
You ──[met at]──> Event ──[also attended]──> Target Person

为每个目标对象找到最短的介绍链路：

You ──[follows]──> Mutual A ──[invested in]──> Target Company
You ──[follows]──> Mutual B ──[co-founded with]──> Target Person
You ──[met at]──> Event ──[also attended]──> Target Person

Path Types (ordered by warmth)

路径类型（按亲近度排序）

Direct mutual — You both follow/know the same person
Portfolio connection — Mutual invested in or advises target's company
Co-worker/alumni — Mutual worked at same company or attended same school
Event overlap — Both attended same conference/program
Content engagement — Target engaged with mutual's content or vice versa

直接共同联系人 — 你们都关注/认识同一个人
投资组合关联 — 共同联系人投资过目标的公司或担任其顾问
同事/校友关系 — 共同联系人和目标曾就职于同一家公司或就读于同一所学校
活动交集 — 双方都参加过同一场会议/项目
内容互动 — 目标互动过共同联系人的内容，反之亦然

Stage 4: Enrichment

阶段4：信息补全

For each qualified lead, pull:

Full name, current title, company
Company size, funding stage, recent news
Recent X posts (last 30 days) — topics, tone, interests
Mutual interests with user (shared follows, similar content)
Recent company events (product launch, funding round, hiring)

为每个通过筛选的线索拉取以下信息：

全名、当前职位、所属公司
公司规模、融资阶段、近期动态
近期X帖子（近30天）—— 主题、语气、兴趣点
与用户的共同兴趣（共同关注的账号、相似内容偏好）
公司近期事件（产品发布、融资、招聘）

Enrichment Sources

补全信息来源

Exa: company data, news, blog posts
X API: recent tweets, bio, followers
GitHub: open source contributions (for developer-centric leads)
LinkedIn (via browser-use): full profile, experience, education

Exa：企业数据、新闻、博客文章
X API：近期推文、个人简介、粉丝数据
GitHub：开源贡献记录（面向开发者类线索）
LinkedIn（通过browser-use）：完整个人资料、工作经历、教育背景

Stage 5: Outreach Draft

阶段5：外联草稿

Generate personalized outreach for each lead. Two modes:

为每个线索生成个性化外联内容，支持两种模式：

Warm Intro Request (to mutual)

向共同联系人请求介绍（暖介绍）

hey [mutual name],

quick ask. i see you know [target name] at [company].
i'm building [your product] which [1-line relevance to target].
would you be open to a quick intro? happy to send you a
forwardable blurb.

[your name]

hey [mutual name],

quick ask. i see you know [target name] at [company].
i'm building [your product] which [1-line relevance to target].
would you be open to a quick intro? happy to send you a
forwardable blurb.

[your name]

Direct Cold Outreach (to target)

直接给目标的冷外联

hey [target name],

[specific reference to their recent work/post/announcement].
i'm [your name], building [product]. [1 line on why this is
relevant to them specifically].

[specific low-friction ask].

[your name]

hey [target name],

[specific reference to their recent work/post/announcement].
i'm [your name], building [product]. [1 line on why this is
relevant to them specifically].

[specific low-friction ask].

[your name]

Anti-Patterns (never do)

反面案例（绝对不要做）

Generic templates with no personalization
Long paragraphs explaining your whole company
Multiple asks in one message
Fake familiarity ("loved your recent talk!" without specifics)
Bulk-sent messages with visible merge fields

无任何个性化内容的通用模板
大段文字介绍你的公司全貌
一条消息里提出多个请求
虚假的熟悉感（比如没有具体依据就说「loved your recent talk!」）
批量发送带有明显合并字段的消息

Configuration

配置

Users should set these environment variables:

bash

undefined

用户需要设置以下环境变量：

bash

undefined

Required

export X_BEARER_TOKEN="..." export X_ACCESS_TOKEN="..." export X_ACCESS_TOKEN_SECRET="..." export X_API_KEY="..." export X_API_SECRET="..." export EXA_API_KEY="..."

Optional

export LINKEDIN_COOKIE="..." # For browser-use LinkedIn access export APOLLO_API_KEY="..." # For Apollo enrichment

undefined

export LINKEDIN_COOKIE="..." # For browser-use LinkedIn access export APOLLO_API_KEY="..." # For Apollo enrichment

undefined

Agents

This skill includes specialized agents in the

agents/

subdirectory:

signal-scorer — Searches and ranks prospects by relevance signals
mutual-mapper — Maps social graph connections and finds warm paths
enrichment-agent — Pulls detailed profile and company data
outreach-drafter — Generates personalized messages

本技能在

agents/

子目录下包含多个专用Agent：

signal-scorer — 根据相关性信号搜索并排名潜在客户
mutual-mapper — 梳理社交图谱连接并找到暖路径
enrichment-agent — 拉取详细的个人资料和企业数据
outreach-drafter — 生成个性化消息

Example Usage

使用示例

User: find me the top 20 people in prediction markets I should reach out to

Agent workflow:
1. signal-scorer searches Exa and X for prediction market leaders
2. mutual-mapper checks user's X graph for shared connections
3. enrichment-agent pulls company data and recent activity
4. outreach-drafter generates personalized messages for top ranked leads

Output: Ranked list with warm paths and draft outreach for each

用户：帮我找20个预测市场领域我应该对接的顶尖人物

Agent工作流：
1. signal-scorer通过Exa和X搜索预测市场领域的领袖
2. mutual-mapper检查用户的X社交图谱寻找共同联系人
3. enrichment-agent拉取企业数据和近期动态
4. outreach-drafter为排名靠前的线索生成个性化消息

输出：带暖路径的排名列表，以及每个线索的外联草稿