people-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Lessie — People Search & Enrichment

Lessie — 人员搜索与信息丰富

Setup

设置

Lessie supports two modes: CLI (default, recommended) and MCP Server.

Lessie支持两种模式：CLI（默认推荐）和MCP Server。

Mode A: CLI (default)

模式A：CLI（默认）

Install the Lessie CLI binary:

bash

npm install -g @lessie/cli

Or use without installing:

bash

npx @lessie/cli --version

First-time authorization:

bash

lessie auth

This opens a browser for login/registration. Token is cached at

~/.lessie/oauth.json

Verify connection:

bash

lessie status

安装Lessie CLI二进制文件：

bash

npm install -g @lessie/cli

或无需安装直接使用：

bash

npx @lessie/cli --version

首次授权：

bash

lessie auth

此命令会打开浏览器进行登录/注册。令牌将缓存至

~/.lessie/oauth.json

。

验证连接：

bash

lessie status

Mode B: MCP Server

模式B：MCP Server

Add to your MCP config (Claude Code

~/.claude.json

, Cursor

~/.cursor/mcp.json

, Codex

~/.codex/config.toml

, etc.):

json

{
  "mcpServers": {
    "lessie": {
      "command": "npx",
      "args": ["-y", "@lessie/mcp-server"],
      "env": {
        "LESSIE_REMOTE_MCP_URL": "https://app.lessie.ai/mcp-server/mcp"
      }
    }
  }
}

将以下内容添加到你的MCP配置文件中（Claude Code对应

~/.claude.json

，Cursor对应

~/.cursor/mcp.json

，Codex对应

~/.codex/config.toml

等）：

json

{
  "mcpServers": {
    "lessie": {
      "command": "npx",
      "args": ["-y", "@lessie/mcp-server"],
      "env": {
        "LESSIE_REMOTE_MCP_URL": "https://app.lessie.ai/mcp-server/mcp"
      }
    }
  }
}

Uninstall

卸载

CLI:

npm uninstall -g @lessie/cli && rm -rf ~/.lessie/

MCP: Remove the
```
"lessie"
```
entry from your
```
.json
```
and
```
rm -rf ~/.lessie/
```

CLI模式：

npm uninstall -g @lessie/cli && rm -rf ~/.lessie/

MCP模式：从你的
```
.json
```
配置文件中移除
```
"lessie"
```
条目，并执行
```
rm -rf ~/.lessie/
```

Version check

版本检查

Run these checks once at the start of each session, before mode detection. Both checks are non-blocking — if any command fails (network error, timeout), skip silently and proceed.

在每次会话开始、模式检测前执行以下检查。两项检查均为非阻塞式——若任一命令失败（网络错误、超时），则静默跳过并继续。

Skill version

技能版本

Read current local version from this file's metadata
```
version
```
field above.

Fetch remote version:

bash

curl -sf --max-time 5 https://raw.githubusercontent.com/LessieAI/lessie-skill/main/people-search/SKILL.md | head -5 | grep 'version:' | head -1 | awk '{print $2}'

If the remote version is newer than the local version → tell the user:
⬆️ A newer version of people-search skill is available ({local} → {remote}). Run this command to update:
```
npx skills add LessieAI/lessie-skill -y -g
```
If versions match or check fails → skip, say nothing.

从此文件元数据的
```
version
```
字段读取当前本地版本。

获取远程版本：

bash

curl -sf --max-time 5 https://raw.githubusercontent.com/LessieAI/lessie-skill/main/people-search/SKILL.md | head -5 | grep 'version:' | head -1 | awk '{print $2}'

若远程版本比本地版本新→告知用户：
⬆️ 人员搜索技能有新版本可用（{本地版本} → {远程版本}）。执行以下命令进行更新：
```
npx skills add LessieAI/lessie-skill -y -g
```
若版本匹配或检查失败→跳过，不提示。

CLI version

CLI版本

Get local CLI version:

bash

lessie --version 2>/dev/null || npx @lessie/cli --version 2>/dev/null

Get latest published version:

bash

npm view @lessie/cli version 2>/dev/null

If the remote version is newer → tell the user:
⬆️ A newer version of Lessie CLI is available ({local} → {remote}). Run this command to update:
```
npm install -g @lessie/cli
```
If versions match or either command fails → skip, say nothing.

获取本地CLI版本：

bash

lessie --version 2>/dev/null || npx @lessie/cli --version 2>/dev/null

获取最新发布版本：

bash

npm view @lessie/cli version 2>/dev/null

若远程版本更新→告知用户：
⬆️ Lessie CLI有新版本可用（{本地版本} → {远程版本}）。执行以下命令进行更新：
```
npm install -g @lessie/cli
```
若版本匹配或任一命令失败→跳过，不提示。

Quick start

快速开始

After setup, try saying to Claude:

"Find Engineering Managers at Stripe in San Francisco"
"Look up Sam Altman's contact info"
"Research OpenAI — recent news and open job postings"

完成设置后，可尝试向Claude发送以下指令：

"在旧金山的Stripe公司寻找工程经理"
"查询Sam Altman的联系方式"
"调研OpenAI——近期新闻及公开招聘信息"

Mode detection

模式检测

Determine which mode to use at the start of each session:

Check if
```
lessie
```
CLI is available: run
```
lessie status
```
If the command succeeds → use CLI mode (call tools via Bash)
If the command fails (not found) → attempt auto-install:
```
npm install -g @lessie/cli
```
After install, run
```
lessie status
```
again to verify
If install succeeds → use CLI mode
If install fails (no npm, permission denied, network error, etc.) → check if MCP tools are available (
```
authorize
```
,
```
use_lessie
```
)
If MCP tools are available → use MCP mode
If neither → inform the user that installation failed and suggest manual install or MCP setup

在每次会话开始时确定使用哪种模式：

检查
```
lessie
```
CLI是否可用：执行
```
lessie status
```
若命令成功→使用CLI模式（通过Bash调用工具）
若命令失败（未找到）→尝试自动安装：
```
npm install -g @lessie/cli
```
安装完成后，再次执行
```
lessie status
```
验证
若安装成功→使用CLI模式
若安装失败（无npm、权限不足、网络错误等）→检查MCP工具是否可用（
```
authorize
```
、
```
use_lessie
```
）
若MCP工具可用→使用MCP模式
若两者均不可用→告知用户安装失败，并建议手动安装或设置MCP

Credits & Pricing

积分与定价

Lessie is a credit-based service.

New accounts receive free trial credits. View your balance and purchase more at https://lessie.ai/pricing.

The agent will disambiguate company names before searching to avoid wasting credits on wrong results.

Lessie是基于积分的服务。

新账户可获得免费试用积分。查看余额及购买更多积分请访问https://lessie.ai/pricing。

Agent会在搜索前明确公司名称，避免因结果错误浪费积分。

Data & Privacy

数据与隐私

Data sources: Contact and company information is aggregated from publicly available sources (business directories, social profiles, corporate websites).
Query logging: Search queries are logged for service improvement and abuse prevention. No query data is shared with third parties.
Data compliance: Lessie follows applicable data protection regulations. Users are responsible for using retrieved contact data in compliance with local laws (GDPR, CAN-SPAM, etc.).
Privacy policy: https://lessie.ai/privacy
Terms of service: https://lessie.ai/terms-of-service

数据源：联系人和企业信息来自公开可用的数据源（商业目录、社交档案、企业官网）。
查询日志：搜索查询会被记录，用于服务改进和防滥用。查询数据不会共享给第三方。
数据合规：Lessie遵循适用的数据保护法规。用户需确保使用获取的联系数据符合当地法律（GDPR、CAN-SPAM等）。
隐私政策：https://lessie.ai/privacy
服务条款：https://lessie.ai/terms-of-service

Authorization

授权

CLI mode

CLI模式

Run
```
lessie status
```
to check token validity.
If
```
authorized: false
```
→ run
```
lessie auth
```
to open browser for login.
After the user completes login, run
```
lessie status
```
again to confirm.

执行
```
lessie status
```
检查令牌有效性。
若
```
authorized: false
```
→执行
```
lessie auth
```
打开浏览器进行登录。
用户完成登录后，再次执行
```
lessie status
```
确认。

MCP mode

MCP模式

Call
```
authorize
```
to check connection status.
If already authorized → proceed to use tools directly.
If not authorized →
```
authorize
```
returns an authorization URL. Tell the user you need to open a browser for Lessie login/registration, and open it using the appropriate system command:
- macOS:
```
open "<url>"
```
- Linux:
```
xdg-open "<url>"
```
- Windows:
```
start "<url>"
```
Tell the user the browser has been opened and they need to complete login/registration.
After the user confirms, call
```
authorize
```
again to verify the connection.
If authorization fails (timeout, denied, port conflict), follow the diagnostic hints returned by
```
authorize
```
and retry.

Always inform the user before opening the browser — never silently redirect.

调用
```
authorize
```
检查连接状态。
若已授权→直接使用工具。
若未授权→
```
authorize
```
会返回授权URL。告知用户需要打开浏览器进行Lessie登录/注册，并使用相应的系统命令打开：
- macOS：
```
open "<url>"
```
- Linux：
```
xdg-open "<url>"
```
- Windows：
```
start "<url>"
```
告知用户浏览器已打开，需完成登录/注册。
用户确认后，再次调用
```
authorize
```
验证连接。
若授权失败（超时、拒绝、端口冲突），按照
```
authorize
```
返回的诊断提示重试。

在打开浏览器前务必告知用户——切勿静默跳转。

Agent behavior rules

Agent行为规则

CRITICAL: Confirm before every credit-consuming action

重要：每次消耗积分的操作前需确认

Every Lessie tool call costs credits. Credit costs per tool:

Tool	Cost
`find-people`	20 credits per search
`enrich-people`	1 credit × number of people (only charged for successful matches)
`review-people`	1 credit × number of people
`enrich-org`	1 credit
`find-orgs`	1 credit
`job-postings`	1 credit
`company-news`	1 credit
`web-search`	1 credit
`web-fetch`	1 credit

Before executing any command, you MUST:

Tell the user what you are about to do and the estimated cost (e.g., "I'll enrich 3 people — this costs ~3 credits").
Wait for explicit confirmation before executing.
Never batch multiple credit-consuming calls without confirming the full plan first.

Exception — skip confirmation if the user has explicitly said they don't want to be prompted (e.g., "don't ask me every time", "just do it", "skip confirmations"). In that case, proceed directly but still log what you executed and the credits spent after each call.

每个Lessie工具调用都会消耗积分。各工具的积分成本如下：

工具	成本
`find-people`	每次搜索20积分
`enrich-people`	1积分×人数（仅对匹配成功的人员收费）
`review-people`	1积分×人数
`enrich-org`	1积分
`find-orgs`	1积分
`job-postings`	1积分
`company-news`	1积分
`web-search`	1积分
`web-fetch`	1积分

执行任何命令前，你必须：

告知用户你即将执行的操作及预估成本（例如：“我将为3位人员补充信息——预计消耗3积分”）。
等待用户明确确认后再执行。
未经确认完整计划，切勿批量执行多个消耗积分的调用。

例外情况——跳过确认：若用户明确表示不想被提示（例如：“不要每次都问我”、“直接执行”、“跳过确认”），则可直接执行，但仍需在每次调用后记录执行内容及消耗的积分。

CRITICAL: Report credit usage after every call

重要：每次调用后报告积分使用情况

After each conversation turn that involved one or more Lessie tool calls, append a one-line summary of credits consumed. Format:

Used
<tool-name>
, cost <N> credit(s).

If multiple tools were called in the same turn, combine them:

Used
web-search
+
enrich-org
, cost 2 credits total.

在每次涉及一个或多个Lessie工具调用的对话回合后，添加一行积分消耗摘要。格式如下：

使用了
<工具名称>
，消耗<N>积分。

若同一回合调用了多个工具，合并显示：

使用了
web-search
+
enrich-org
，共消耗2积分。

CRITICAL: Read references before first CLI call

重要：首次CLI调用前阅读参考文档

Before executing any
lessie
CLI command for the first time in a session, you MUST read references/cli-reference.md to learn the exact parameter syntax. Do NOT guess parameter names — the CLI uses

--filter

with JSON, not

--title

--company

style flags.

在会话中首次执行任何
lessie
CLI命令前，你必须阅读references/cli-reference.md以了解确切的参数语法。切勿猜测参数名称——CLI使用带JSON的

--filter

，而非

--title

--company

类的标志。

Search mode disambiguation (B2B vs KOL)

搜索模式区分（B2B vs KOL）

Lessie supports two search modes with different data sources and result types:

B2B mode: Searches professional databases (LinkedIn-based). Best for finding people by job title, company, seniority, or industry. Returns work email, phone, employment history.
KOL mode: Searches social media platforms (Instagram, YouTube, TikTok, Twitter/X). Best for finding influencers, content creators, or public figures by audience, follower count, or content topic. Returns social links, follower counts.

When the user's intent is ambiguous — i.e., the query could reasonably target either professionals on LinkedIn or creators on social media — you MUST ask the user to clarify before searching. Present both options concisely:

Example ambiguous query: "Find individuals who have hands-on experience with brain-monitoring sleep devices to share their insights."

This could mean:

B2B: Product managers, engineers, or researchers at sleep-tech companies (via LinkedIn)
KOL: Health/tech influencers who have reviewed or used such devices (via social media)

Ask: "This could be LinkedIn professionals (PMs, engineers at sleep-tech companies) or social media creators who review sleep devices. Which direction do you prefer — or both?"

When intent is clear, proceed directly:

"Find CTOs at fintech startups" → B2B (obvious)
"Find beauty influencers on Instagram with 100k+ followers" → KOL (obvious)

Lessie支持两种搜索模式，数据源和结果类型不同：

B2B模式：搜索专业数据库（基于LinkedIn）。最适合按职位、公司、职级或行业寻找人员。返回工作邮箱、电话、工作经历。
KOL模式：搜索社交媒体平台（Instagram、YouTube、TikTok、Twitter/X）。最适合按受众、粉丝数或内容主题寻找网红、内容创作者或公众人物。返回社交链接、粉丝数。

当用户意图不明确时——即查询既可能指向LinkedIn上的专业人士，也可能指向社交媒体上的创作者——你必须在搜索前请用户明确说明。简洁呈现两种选项：

示例模糊查询：“寻找有脑电波睡眠设备实操经验的人士分享见解。”

这可能指：

B2B：睡眠科技公司的产品经理、工程师或研究员（通过LinkedIn）
KOL：评测或使用过此类设备的健康/科技网红（通过社交媒体）

询问：“这既可以指LinkedIn上的专业人士（睡眠科技公司的PM、工程师），也可以指评测睡眠设备的社交媒体创作者。你倾向于哪个方向——还是两者都要？”

当意图明确时，直接执行：

“寻找金融科技初创公司的CTO” → B2B（明确）
“在Instagram上寻找粉丝数10万+的美妆网红” → KOL（明确）

Entity disambiguation

实体区分

When a user mentions a company name that could refer to multiple entities (e.g., "Manus" could be Manus AI, Manus Bio, Manus Plus, etc.), disambiguate before searching:

Ask the user which company they mean, or present the top candidates and let them pick.
If context makes it unambiguous (e.g., user previously discussed AI agents), state your assumption and confirm: "你是指做 AI Agent 的 Manus AI (manus.im) 吗？"
Never silently assume one entity over another — wrong domain = wasted search credits and irrelevant results.

当用户提及的公司名称可能指向多个实体时（例如：“Manus”可能指Manus AI、Manus Bio、Manus Plus等），需在搜索前明确：

询问用户所指的公司，或列出候选公司让用户选择。
若上下文明确（例如：用户之前讨论过AI Agent），说明你的假设并确认：“你是指开发AI Agent的Manus AI (manus.im)吗？”
切勿默认选择某一实体——错误的领域会浪费搜索积分并返回无关结果。

Tools overview

工具概览

People

人员相关

Tool	CLI command	When to use
`find_people`	`lessie find-people`	Discover people by title, company, location, seniority, audience. Default strategy is `hybrid` . If a request times out or fails, retry with `--strategy saas_only` — it's faster (~30s vs ~60s) and more stable, though recall may be lower
`enrich_people`	`lessie enrich-people`	Enrich known people with full profiles. Two paths: B2B (via linkedin_url or name+domain → email, phone, work history) and KOL (via twitter/instagram/tiktok/youtube username → follower count, social links). Max 10 per call
`review_people`	`lessie review-people`	Deep-qualify ambiguous candidates via web research — skip for obvious matches/mismatches

工具	CLI命令	使用场景
`find_people`	`lessie find-people`	按职位、公司、地点、职级或受众寻找人员。默认策略为 `hybrid` 。若请求超时或失败，使用 `--strategy saas_only` 重试——速度更快（约30秒 vs 约60秒）且更稳定，但召回率可能较低
`enrich_people`	`lessie enrich-people`	为已知人员补充完整档案。两种路径：B2B（通过linkedin_url或姓名+域名→邮箱、电话、工作经历）和KOL（通过twitter/instagram/tiktok/youtube用户名→粉丝数、社交链接）。每次调用最多10人
`review_people`	`lessie review-people`	通过网络调研深度筛选模糊候选人——明显匹配/不匹配的情况可跳过

Companies

企业相关

Tool	CLI command	When to use
`find_organizations`	`lessie find-orgs`	Discover companies by name, keyword, location, size, funding
`enrich_organization`	`lessie enrich-org`	Get full profile for known company domain(s) — industry, employees, funding, tech stack
`get_company_job_postings`	`lessie job-postings`	View active job openings (needs `organization_id` from enrich)
`search_company_news`	`lessie company-news`	Find recent news articles (needs `organization_id` from enrich)

工具	CLI命令	使用场景
`find_organizations`	`lessie find-orgs`	按名称、关键词、地点、规模、融资情况寻找企业
`enrich_organization`	`lessie enrich-org`	获取已知企业域名的完整档案——行业、员工数、融资、技术栈
`get_company_job_postings`	`lessie job-postings`	查看活跃职位空缺（需来自enrich的 `organization_id` ）
`search_company_news`	`lessie company-news`	查找近期新闻文章（需来自enrich的 `organization_id` ）

Web research

网络调研

Tool	CLI command	When to use
`web_search`	`lessie web-search`	General web search; cached results make follow-up `web_fetch` free
`web_fetch`	`lessie web-fetch`	Extract specific info from a URL via AI summarization

工具	CLI命令	使用场景
`web_search`	`lessie web-search`	通用网络搜索；缓存结果使后续 `web_fetch` 免费
`web_fetch`	`lessie web-fetch`	通过AI总结从URL提取特定信息

Detailed references

详细参考文档

CLI command examples & MCP calling: See references/cli-reference.md
Workflow patterns (domain resolution, company research, search+qualify): See references/workflow-patterns.md
Domain resolution decision tree: See references/domain-resolution.md

CLI命令示例及MCP调用：查看references/cli-reference.md
工作流模式（域名解析、企业调研、搜索+筛选）：查看references/workflow-patterns.md
域名解析决策树：查看references/domain-resolution.md

Key constraints

关键限制

```
enrich_people
```
/
```
enrich_organization
```
: max 10 per call; split larger lists into batches
```
find_people
```
/
```
find_organizations
```
: paginated — use
```
--page
```
for more results
```
web_search
```
caches page content; if a result has
```
has_content: true
```
, calling
```
web_fetch
```
on that URL is instant

Seniority levels:

owner

founder

c_suite

partner

vp

head

director

manager

senior

entry

intern

For people enrichment, providing
```
domain
```
(company domain) alongside name greatly improves match accuracy
CLI output is JSON on stdout, status messages on stderr — parse stdout for data

```
enrich_people
```
/
```
enrich_organization
```
：每次调用最多10个；较大列表需拆分批次
```
find_people
```
/
```
find_organizations
```
：分页——使用
```
--page
```
获取更多结果
```
web_search
```
会缓存页面内容；若结果包含
```
has_content: true
```
，调用该URL的
```
web_fetch
```
可即时完成

职级等级：

owner

、

founder

、

c_suite

、

partner

、

vp

、

head

、

director

、

manager

、

senior

、

entry

、

intern

为人员补充信息时，提供
```
domain
```
（企业域名）+姓名可大幅提高匹配准确率
CLI输出在stdout为JSON格式，状态信息在stderr——解析stdout获取数据