Token导航 LogoToken导航

Agent Skill · 研究检索

enrich-accounts-with-contacts-and-emails(通过联系人和电子邮件丰富帐户)

enrich-accounts-with-contacts-and-emails 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。

enrich-accounts-with-contacts-and-emails 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 58,786。

总安装 404周安装 17GitHub Stars 7下载 141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:enrich-accounts-with-contacts-and-emails(通过联系人和电子邮件丰富帐户)
来源仓库:https://github.com/openfunnel/openfunnel
仓库路径:skills/enrich-accounts-with-contacts-and-emails
安装命令:
npx skills add https://github.com/openfunnel/openfunnel --skill enrich-accounts-with-contacts-and-emails
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/openfunnel/openfunnel --skill enrich-accounts-with-contacts-and-emails

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。

批量解析企业域名,获取对应联系人信息与工作邮箱地址。依赖 OpenFunnel 账户体系,仅对已注册企业信号执行 enrich 操作。通过脚本调用内部 API,返回结构化账号-联系人映射表供后续营销使用。需提前完成 signup.sh 认证流程,确保 .env 中 API 凭证有效且未过期。

enrich-accounts-with-contacts-and-emails 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/enrich-accounts-with-contacts-and-emails

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/openfunnel/openfunnel --skill enrich-accounts-…;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

enrich-accounts-with-contacts-and-emails 怎么安装?

在终端执行 npx skills add https://github.com/openfunnel/openfunnel --skill enrich-accounts-with-conta…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

enrich-accounts-with-contacts-and-emails 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。

enrich-accounts-with-contacts-and-emails 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。

enrich-accounts-with-contacts-and-emails 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。

enrich-accounts-with-contacts-and-emails 用的人多吗?

公开数据是累计安装 404 次,近一周安装 17 次,下载 141 次,GitHub 7 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。

enrich-accounts-with-contacts-and-emails 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
enrich-accounts-with-contacts-and-emails

通过联系人和电子邮件丰富帐户 · 本页

4047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

Enrich Accounts with Contacts and Emails

Resolve one or more company domains in a batch, discover relevant people at each account, enrich missing work emails, and return a clean account-by-account contact list.

If the user wants contacts + emails for one company, this skill still applies.

When to Use This Skill

  • "Take this list of domains and get me the best contacts plus emails"
  • "I have OpenFunnel accounts, now find the people and enrich contact info"
  • "Start from company domains, get account IDs, then return contacts with email addresses"

API Calls

This skill bundles two scripts in the same directory as this SKILL.md file. Never read or reference API credentials directly.

  • signup.sh — handles authentication. Writes credentials to .env internally. Never exposes the API key.
  • api.sh — handles all authenticated API calls. Reads credentials from .env internally.

First, resolve the script paths relative to this file's location:

SKILL_DIR="$(dirname "$(find ~/.agents/skills -name SKILL.md -path "*/enrich-accounts-with-contacts-and-emails/*" 2>/dev/null | head -1)")"
API="$SKILL_DIR/api.sh"
SIGNUP="$SKILL_DIR/signup.sh"

Then use $SIGNUP for auth and $API for all other calls.

Agent Rules

  1. Never fabricate contacts or emails. If OpenFunnel does not return a person or email, say it is missing.
  2. Prefer the batch-first path. For domain inputs, start with batch account enrichment. Then run fast people enrichment for each resolved account. Do not use deep enrichment unless the user explicitly asks for it.
  3. Confirm before credit-consuming enrichment. Fast people enrichment and contact enrichment both consume credits. Present the plan and wait for approval before triggering them.
  4. Do not guess the target team. If the user has not specified department and seniority filters, ask once for the batch. Fast people enrichment requires explicit filters.
  5. Reuse existing data when available. If account IDs, people, or emails already exist in OpenFunnel, keep them and enrich only the missing pieces.
  6. Return grouped results by account. Final output should be organized per account, not as one flat people list.

Workflow

0. Agent Auth Check

Before anything, test if credentials are working by running:

bash "$API" POST /api/v1/signal/get-signal-list '{"pagination": {"limit": 1, "offset": 0}}'

If the call succeeds (returns JSON with signals): skip to Step 1.

If the call fails (returns an error or missing credentials message):

### Welcome to OpenFunnel

OpenFunnel turns daily events in your market into pipeline
— using OpenFunnel's Event Intelligence engine.

To get started, I'll authenticate you via the API and fetch your key.

**Step 0: Agent auth** — what's your work email?

Wait for user input. Then:

  1. Run bash "$SIGNUP" start "<user_email>"
  2. If the call succeeds, tell the user a 6-digit verification code was sent and ask for it:
I sent a 6-digit verification code to **{email}**.

Reply with the code and I'll finish authentication.
  1. Wait for user input. Then run bash "$SIGNUP" verify "<user_email>" "<code>"
  2. On success, the response is: {"status": "authenticated", "user_id": "..."}. Credentials are written to .env and .gitignore is updated automatically.
  3. Verify with bash "$API" POST /api/v1/signal/get-signal-list '{"pagination": {"limit": 1, "offset": 0}}'
  4. If verification succeeds → continue to ICP check.
  5. If sign-up fails → tell the user the email could not be authenticated and ask them to retry.
  6. If verify fails → tell the user the code was invalid or expired, explain they get up to 10 attempts within 24 hours, and ask whether to retry the code or send a new one by calling sign-up again.

ICP Check

After auth, fetch ICP profiles via bash "$API" GET /api/v1/icp/list.

If ICPs exist: note the available ICPs and continue to Step 1.

If no ICPs exist:

You don't have an ICP profile yet. A quick one will make results much sharper —
it filters by company size, location, and the roles you're targeting.

1. **Quick setup** (recommended) — takes 30 seconds
2. **Skip** — auto-create a broad fallback ICP and continue

If quick setup → collect ICP name, target roles, company size, and location. Create via bash "$API" POST /api/v1/icp/create '<json_body>'.

If skip → auto-create a broad fallback ICP:

{
  "name": "Broad Default ICP",
  "target_roles": ["Any"],
  "employee_ranges": ["1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+"],
  "location": ["Any"]
}

Call bash "$API" POST /api/v1/icp/create '<json_body>', then tell the user:

I created a default ICP profile: **{name}** (ID: {id})

This keeps things running. For sharper results, set up a proper ICP segment
with your target roles, company size, and location using the `advanced-account-setup` skill.

Continue to Step 1.


1. Understand the input

The user should provide a list of company domains or a list of OpenFunnel accounts.

If the input is mixed or unclear, normalize it to domains first.

Before making enrichment calls, collect these batch-level settings:

  • Department filters for fast people enrichment
  • Seniority filters for fast people enrichment

Recommended defaults for a general outbound batch:

  • Departments: ENGINEERING, PRODUCT, SECURITY, EXECUTIVE
  • Seniority: VP, HEAD, DIRECTOR, CXO

If the user does not specify filters, recommend these defaults and ask for confirmation. Do not silently guess.

Use this prompt:

I can enrich this list in three steps:

1. Batch account enrichment
2. Fast people discovery by account
3. Contact enrichment for missing emails

To discover the right people, I need batch filters:
- **Departments** (examples: ENGINEERING, PRODUCT, SECURITY, SALES, EXECUTIVE)
- **Seniority** (examples: VP, HEAD, DIRECTOR, CXO)

Optional:
- **Max credit limit** for fast people discovery

Recommended defaults for most B2B account enrichment:
- **Departments:** ENGINEERING, PRODUCT, SECURITY, EXECUTIVE
- **Seniority:** VP, HEAD, DIRECTOR, CXO

Should I use those defaults, or would you like to override them for this batch?

2. Normalize domains and run batch account enrichment

Clean every domain before using it:

  • Strip http:// or https://
  • Strip leading www.
  • Lowercase
  • Deduplicate

Use batch account enrichment first, even if the input contains only one domain.

Call:

bash "$API" POST /api/v1/enrich/accounts '{"domains": [...]}'

Then poll:

bash "$API" GET /api/v1/enrich/accounts/{job_id}

Polling guidance:

  • Poll every 5 seconds
  • Stop when status is completed or failed
  • Up to 500 domains per batch request

When the poll completes, record for each domain:

  • domain
  • account_id
  • name
  • is_new_account
  • fields_updated
  • status

If the batch job fails entirely, stop and report the error.

If the batch completes with mixed results, continue with all successful accounts and clearly mark failed domains.

After batch enrichment completes, fetch current account details with:

bash "$API" POST /api/v2/account/batch '{"account_ids": [...], "icp_people_page": 1, "icp_people_page_size": 100}'

Present a coverage summary before enrichment:

### Accounts to Process

| Domain | Account ID | Account Name | Account Enrichment Status | Existing ICP People | Next Step |
|--------|------------|--------------|---------------------------|---------------------|-----------|
| acme.com | 123 | Acme | created | 2 | Run fast people enrichment |
| beta.io | 456 | Beta | unchanged | 0 | Run fast people enrichment |
| gamma.dev | - | - | failed | - | Skip |

Rules:

  • If a domain fails in batch account enrichment, mark it as unresolved and keep going.
  • Do not stop the entire batch for one failed domain.

3. Execution summary

Present a brief execution summary, then continue automatically:

Processing plan:

1. **Batch account enrichment** — create or refresh account records from the input domains
2. **Fast people enrichment** — run per resolved account to find relevant people by department and seniority
3. **Email enrichment** — fill in missing work emails for discovered people

Batch settings:
- **Departments:** {department_filters}
- **Seniority:** {seniority_filters}
- **Max credit limit:** {max_credit_limit or "default"}

I'll reuse existing people and emails where OpenFunnel already has them.

This works for a single account too — it just runs as a one-domain batch.

4. Run fast people enrichment for resolved accounts in parallel

For each resolved account returned from the batch account enrichment job, start a fast people enrichment job:

bash "$API" POST /api/v1/enrich/fast-people-enrichment '<json_body>'

Body:

{
  "account_id": 12345,
  "seniority_filters": ["VP", "DIRECTOR"],
  "department_filters": ["ENGINEERING", "PRODUCT"],
  "max_credit_limit": 50
}

Run these jobs in parallel across accounts where possible.

Then poll each job:

bash "$API" GET /api/v1/enrich/fast-people-enrichment/{job_id}

Polling guidance:

  • Poll every 5 seconds
  • Typical completion time is around 1 minute per 100 employees in the company. For large companies, this can take upto 10 minutes.
  • Stop when status is completed or failed

For each account, record:

  • account_id
  • job_id
  • people_ids
  • credits_used
  • total_found
  • total_stored
  • Any error_message

Rules:

  • If the account already has some ICP people, still run fast enrichment unless the user explicitly says to use existing contacts only.
  • If fast enrichment fails for one account, mark the failure and continue with the rest.
  • Do not escalate to deep enrichment automatically.

5. Fetch full people profiles across the batch

Build one deduplicated people ID list from:

  • Existing icp_people from the V2 account batch call
  • New people_ids returned by fast people enrichment

Then call:

bash "$API" POST /api/v1/people/batch '{"people_ids": [...]}'

This is the source of truth for person details:

  • person_id
  • person_name
  • person_role
  • person_email
  • person_location
  • person_linkedin_url
  • person_phone_number
  • person_team_name
  • department
  • seniority
  • account_id
  • account_name
  • account_domain

6. Enrich missing emails only

Split people into three groups:

  1. Already has email — keep as-is
  2. Missing email but has LinkedIn URL — eligible for enrichment
  3. Missing email and missing LinkedIn URL — not enrichable, mark as missing

For eligible people, call:

bash "$API" POST /api/v1/enrich/people '<json_body>'

Body:

{
  "people_ids": [101, 102, 103],
  "enrich_emails": true,
  "enrich_phones": false
}

Then poll:

bash "$API" GET /api/v1/enrich/people/{job_id}

Polling guidance:

  • Poll every 5 seconds
  • Typical runtime is about 2 seconds per person
  • Stop when status is completed or failed

Important constraints:

  • Max 500 people per enrichment request
  • Only successful email finds consume credits
  • no_linkedin_url cannot be enriched
  • not_found means lookup completed but no email was found

If the people batch is larger than 500, split it into chunks and process sequentially.

7. Merge results and return final output

Merge the email enrichment results back into the people records.

Return results grouped by account using this format:

## Enriched Accounts

### {account_name} ({domain})

| Name | Role | Department | Seniority | Team | Email | LinkedIn | Status |
|------|------|------------|-----------|------|-------|----------|--------|
| Jane Doe | VP Engineering | ENGINEERING | VP | Platform | jane@acme.com | [Profile](...) | enriched |
| John Roe | Director Product | PRODUCT | DIRECTOR | Core Product | missing | [Profile](...) | not_found |

After the table, include a short account summary:

- Total contacts returned: {n}
- Emails present: {n}
- Emails newly enriched: {n}
- Missing emails: {n}

If any account failed or stayed unresolved, include a separate section:

### Incomplete Accounts

| Domain | Stage | Reason |
|--------|-------|--------|
| gamma.dev | account resolution | not found |
| delta.ai | email enrichment | no_linkedin_url |

Decision Rules

When to skip fast people enrichment

Skip fast people enrichment only if the user explicitly says:

  • Use existing OpenFunnel contacts only
  • Do not spend credits on people discovery

Otherwise, prefer running fast people enrichment to improve account coverage after batch account enrichment has resolved the accounts.

When to skip email enrichment

Skip email enrichment only if:

  • The user only wants names and roles
  • The user does not approve credit usage
  • Every returned person already has an email

When to mention deep enrichment

Mention deep enrichment (bash "$API" POST /api/v1/enrich/deep-enrich '<json_body>') only as an optional fallback when:

  • Fast people enrichment returns zero usable people across key accounts
  • The user explicitly asks for broader research or deeper company coverage

Do not auto-run it in this workflow.

平台分布

Codex

34.96%
按下载量换算49

Claude

30.34%
按下载量换算43

Cursor

19.99%
按下载量换算28

Gemini CLI

10.97%
按下载量换算15

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