Token导航 LogoToken导航

Agent Skill · 研究检索

email-search(电子邮件搜索)

email-search 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

email-search 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 44,490。

总安装 912周安装 38GitHub Stars 93下载 304核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:email-search(电子邮件搜索)
来源仓库:https://github.com/extruct-ai/gtm-skills
仓库路径:skills/email-search
安装命令:
npx skills add https://github.com/extruct-ai/gtm-skills --skill email-search
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/extruct-ai/gtm-skills --skill email-search

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

email-search 将 LinkedIn 资料转化为经第三方验证的邮箱与电话号码。适用于拓展 B2B 客户联系渠道并丰富联系人数据库完整性。依赖 Extruct API 对接 Prospeo、FullContact 等数据增强服务商。使用前需确认目标国家/地区数据获取合法性,避免触碰隐私红线。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/email-search

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/extruct-ai/gtm-skills --skill email-search;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

email-search 怎么安装?

在终端执行 npx skills add https://github.com/extruct-ai/gtm-skills --skill email-search。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

email-search 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

email-search 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

email-search 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

email-search 用的人多吗?

公开数据是累计安装 912 次,近一周安装 38 次,下载 304 次,GitHub 93 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

email-search 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
email-search

电子邮件搜索 · 本页

91293接触敏感数据未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Email Finder

Turn LinkedIn profiles into verified emails and phones. Takes the output of people-search and runs it through contact enrichment providers like Prospeo or Fullenrich.

Related Skills

list-segmentation → people-search → email-search → email-generation → email-response-simulation → campaign-sending

After people-search finds WHO to contact (with LinkedIn URLs), this skill gets their verified contact info.

Extruct API Operations

This skill delegates all Extruct API calls to the extruct-api skill.

For all Extruct API operations, read and follow the instructions in skills/extruct-api/SKILL.md.

The only Extruct operation in this skill is reading people table data. Contact enrichment uses separate providers (Prospeo, Fullenrich, etc.) with their own APIs.

Inputs

InputSourceRequired
People table IDChild table from people-searchyes (or CSV)
People CSVclaude-code-gtm/csv/input/{campaign}/people_linkedin.csvyes (or table)
Provider preferenceUser choiceyes
Include mobile phonesUser choiceno (default: no)

Choosing a Provider

Ask the user which contact enrichment provider they want to use. If they need guidance, consider:

  • Have LinkedIn URLs? → providers with LinkedIn enrichment work best
  • Need highest email hit rate? → waterfall providers try multiple sources
  • Budget-conscious? → check credit costs per match
  • Need mobile phones? → confirm the provider covers phone data
  • Want maximum coverage? → run one provider first, then a second for misses

If the user doesn't know where to start, pre-configured options with local reference docs are available in references/.

Workflow

Step 0: Confirm provider and learn API

  1. Ask the user which contact enrichment provider they want to use
  2. Fetch or read the provider's API documentation and identify:

- Enrichment endpoint (single and bulk) - Required input fields (LinkedIn URL, name, domain, etc.) - Authentication method and credentials - Throughput limits and request constraints - Response format (email, phone, verification status) - Credit/pricing model

  1. Ask for their API credentials and confirm access
  2. Plan the implementation and confirm with the user before proceeding

Step 1: Load people data

Option A: From Extruct people table (recommended) — Use the extruct-api skill to fetch data from the people table. Extract full_name, profile_url, role, and parent_row_id from each row. Split full name into first/last.

Option B: From CSV — Read claude-code-gtm/csv/input/{campaign}/people_linkedin.csv.

Step 2: Check credits

Before running enrichment, check the user's available credits or quota with the chosen provider (using the endpoint identified in Step 0). Present a cost estimate based on the number of contacts to enrich.

Step 3: Run enrichment

Using the chosen provider's API (from Step 0):

  1. Prepare contact data in the format the provider expects (LinkedIn URL, name + domain, etc.)
  2. Submit contacts in batches according to the provider's rate limits
  3. Handle async responses if the provider uses polling
  4. Collect results: emails, phone numbers, verification status
  5. Track matched vs. unmatched contacts

If the user wants a waterfall (two providers), run the first provider, collect misses, then run misses through the second.

Step 4: Deduplicate and clean

Deduplicate by email. Filter out:

  • Entries with no email
  • Results where the provider marks verification as invalid

Step 5: Output contact CSV

Save enriched contacts to claude-code-gtm/csv/input/{campaign}/contacts.csv with columns:

  • first_name, last_name, email, email_verified, job_title, company_name, domain, linkedin_url, phone, location, source

Step 6: Review with user

Present summary:

Enrichment Results:
- Contacts submitted: N
- Emails found: N (X% hit rate)
- Emails verified: N
- Phones found: N
- No match: N
- Provider: [chosen provider]

Show a sample of 10 contacts for spot-checking:

NameTitleCompanyEmailPhoneSource
..................

Ask:

  • "Hit rate look acceptable? (>60% is good, >80% is great)"
  • "Want to run the misses through another provider?"
  • "Ready to proceed to email-generation?"

API References

Pre-configured provider docs in references/ directory. For other providers, docs are fetched during Step 0.

平台分布

Codex

39.14%
按下载量换算119

Claude

29.65%
按下载量换算90

Cursor

20.03%
按下载量换算61

Gemini CLI

8.52%
按下载量换算26

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills