Token导航 LogoToken导航

Agent Skill · 研究检索

advanced-account-setup(高级帐户设置)

advanced-account-setup 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。

advanced-account-setup 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 55,679。

总安装 470周安装 19GitHub Stars 7下载 147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:advanced-account-setup(高级帐户设置)
来源仓库:https://github.com/openfunnel/openfunnel
仓库路径:skills/advanced-account-setup
安装命令:
npx skills add https://github.com/openfunnel/openfunnel --skill advanced-account-setup
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 advanced-account-setup

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。

advanced-account-setup 用于配置 OpenFunnel 生产环境账户,包括 ICP 画像、黑名单和客户集成设置。适用于需要精细化过滤数据源、排除竞争对手或对接 Salesforce/Slack 等系统的场景。通过脚本自动写入凭据并调用 API,但需避免直接读取或暴露密钥信息。

使用前请确认权限边界,防止误改关键配置或触发不必要的数据同步。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/advanced-account-setup

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 advanced-account…;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

advanced-account-setup 怎么安装?

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

advanced-account-setup 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。

advanced-account-setup 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。

advanced-account-setup 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。

advanced-account-setup 用的人多吗?

公开数据是累计安装 470 次,近一周安装 19 次,下载 147 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。

advanced-account-setup 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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
advanced-account-setup

高级帐户设置 · 本页

4707接触敏感数据未明确有提醒

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

Advanced Account Setup

Configure your OpenFunnel account for production use. This skill handles ICP profiles, blocklists, and CRM/Slack integrations — the settings that control how OpenFunnel filters, excludes, and syncs data.

Authentication is handled by Step 0 (Agent Auth Check) in every skill. This skill is for what comes after — dialing in the configuration.

When to Use This Skill

  • "Set up my ICP"
  • "Configure my ideal customer profile"
  • "Block competitors from showing up in results"
  • "Connect Salesforce / HubSpot / Slack"
  • "Set up integrations"
  • "Fine-tune my account settings"

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 "*/advanced-account-setup/*" 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. Walk through one section at a time. Don't dump the entire setup flow. Present each section, complete it, then move to the next.
  2. Fetch options before asking for input. Always call the options endpoint first so the user picks from valid values — don't let them guess.
  3. Confirm before creating. Show the full configuration summary before hitting create.
  4. Present what the API returns. No fabrication.

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.

**What's your work email?**

Wait for user input. Then:

  1. Run bash "$SIGNUP" start "<user_email>"
  2. Tell the user a 6-digit code was sent: I sent a 6-digit verification code to **{email}**. Reply with the code.
  3. Wait for input. Run bash "$SIGNUP" verify "<user_email>" "<code>"
  4. On success, the response is: {"status": "authenticated", "user_id": "..."}. Credentials are written to .env and .gitignore is updated automatically.
  5. Verify with bash "$API" POST /api/v1/signal/get-signal-list '{"pagination": {"limit": 1, "offset": 0}}'
  6. If verification succeeds → continue to Step 1
  7. If sign-up fails → ask user to retry
  8. If verify fails → tell user the code was invalid or expired (up to 10 attempts in 24 hours), offer to retry or resend

1. Welcome & Setup Menu

Present the setup sections. The user can do them in any order or skip what they don't need.

### OpenFunnel Account Setup

Here's what you can configure:

1. **Create ICP (Ideal Customer Profile)** — Define the firmographic segment OpenFunnel should monitor: company size, funding stage, location, and target roles
2. **Advanced ICP** — Describe your ideal customer in natural language for more nuanced matching
3. **Blocklist** — Exclude specific companies or types of companies from your results
4. **Integrations** — Connect Salesforce, HubSpot, or Slack

Which would you like to set up? (or "all" to walk through everything)

Wait for user input.


2. Create Firmographic ICP

This is the foundation. OpenFunnel agents use the ICP to filter every signal, every audience, and every enrichment. Without an ICP, results are unfiltered.

Step 1: Fetch valid options

Call bash "$API" GET /api/v1/icp/options to get the valid values for each field.

Present them cleanly:

### ICP Configuration

First, let's set up the basics. Here are your options:

**Company Size (employee_ranges):**
{list each option from employee_ranges, e.g. "1-10", "11-50", "51-200", ...}
→ Pick one or more. These are AND-ed with other filters.

**Funding Stages:**
{list each option from funding_stages, e.g. "Seed", "Series A", ...}
→ Optional. Pick a min and max to define a range (e.g., Seed → Series B).

**Company HQ Location:**
{list each option as "value — label" from locations}
→ Pick one or more.

**Sub-locations (US only):**
{only show if relevant — list from sub_locations}
→ Available when location is "us". Pick specific states/cities.

**People Location:**
{list from people_locations}
→ Where the target people are located (can differ from company HQ).

**People Sub-locations (US only):**
{list from people_sub_locations}
→ Same as above, for US states/cities.
Step 2: Collect inputs

Walk through each required field:

**1. ICP Name** — A descriptive name for this profile (e.g., "Mid-market SaaS, Series A-B, US")

**2. Target Roles** — Job titles or role descriptions to target. Comma-separated.
   Examples: "VP Engineering", "CTO", "Head of Security", "Director of Data"

**3. Company Size** — Which employee ranges? (pick from the list above)

**4. Company HQ Location** — Where should these companies be headquartered?

Then optional fields:

**Optional:**
- **Funding stage range** — Min and max (e.g., "Seed" to "Series B"). Leave blank to skip.
- **Employee + Funding logic** — "AND" (must match both) or "OR" (match either). Default: AND.
- **Sub-locations** — US states/cities (only if location is "us").
- **People locations** — Where target people are located.
- **People sub-locations** — US states/cities for people.

Set any of these, or "skip" for defaults.

Wait for user input for each field (or collect all at once if the user provides them together).

Step 3: Confirm and create

Present the full configuration:

### ICP Summary

**Name:** {name}
**Target Roles:** {roles}
**Employee Ranges:** {ranges}
**Location:** {location}
**Funding:** {min_funding} → {max_funding} ({config logic})
{any other fields that were set}

Create this ICP? (yes / no / edit)

If yes → call bash "$API" POST /api/v1/icp/create '<json_body>' with:

{
  "name": "<name>",
  "target_roles": ["<role1>", "<role2>"],
  "employee_ranges": ["<range1>", "<range2>"],
  "location": ["<location_code>"],
  "min_funding": "<stage or null>",
  "max_funding": "<stage or null>",
  "employee_count_funding_config": "<AND or OR or null>",
  "sub_locations": ["<codes or null>"],
  "people_locations": ["<codes or null>"],
  "people_sub_locations": ["<codes or null>"]
}

On success, present:

ICP created: **{name}** (ID: {id})

This ICP is now active. All signals, audiences, and enrichments can use it.

Return to setup menu.


3. Advanced ICP (Natural Language)

For customers who want to go beyond firmographic filters. Describe your ideal customer in plain language — industry focus, pain points, tech stack, buying behavior.

### Advanced ICP — Natural Language Description

Firmographic ICP filters on company size, funding, and location. Advanced ICP adds a
natural language layer — describe *what kind* of company you're looking for in your own words.

**Examples:**
- "B2B SaaS companies in the data infrastructure space that are post-product-market-fit
  and scaling their go-to-market. Ideally series A-C, with a technical founder,
  selling to engineering or data teams."
- "Mid-market healthcare companies modernizing their patient data systems.
  They're moving off legacy EHR platforms and evaluating cloud-native alternatives."
- "Developer tools companies that sell to platform engineering teams.
  Companies where the buyer is a VP/Director of Engineering or Platform."

**What does your ideal customer look like?** Describe their industry, stage, pain points,
buying behavior — whatever helps OpenFunnel understand who you're after.

Wait for user input.

Once the user provides their description, confirm:

### Advanced ICP Description

**Your description:**
> {user's description}

Save this? (yes / edit)

If yes → call bash "$API" POST /api/v1/icp/advanced-description '<json_body>' with:

{
  "icp_id": "<id from firmographic ICP>",
  "description": "<user's natural language description>"
}
Note: This endpoint is coming soon. The description will be saved and used by OpenFunnel agents to qualify accounts beyond firmographic filters.

Return to setup menu.


4. Blocklist

Exclude specific companies or types of companies from all OpenFunnel results — signals, audiences, enrichments.

### Blocklist Setup

Two ways to block companies:

1. **By domain** — Provide specific domains to exclude
   Example: "competitor.com, acquired-company.io, our-own-domain.com"

2. **By description** — Describe what kind of companies to block in natural language
   Example: "Consulting firms, agencies, companies with fewer than 5 employees,
   any company in our own portfolio"

Which approach? (or "both")

Wait for user input.

If by domain:
**Provide the domains to block** (comma-separated):
Example: competitor.com, acme.io, example.org

Collect the list, confirm:

### Blocklist — Domains

Blocking these domains from all results:
{list each domain}

Confirm? (yes / edit)

If yes → call bash "$API" POST /api/v1/blocklist/domains '<json_body>' with:

{
  "domains": ["competitor.com", "acme.io", "example.org"]
}
Note: This endpoint is coming soon. Blocked domains will be excluded from all signal results, audiences, and enrichments.
If by description:
**Describe the companies you want to block:**
Example: "Consulting firms, dev agencies, any company under 10 employees,
competitors in our space (list names if you have them)"

Collect, confirm:

### Blocklist — Description

Blocking companies matching:
> {user's description}

Confirm? (yes / edit)

If yes → call bash "$API" POST /api/v1/blocklist/description '<json_body>' with:

{
  "description": "<user's natural language description>"
}
Note: This endpoint is coming soon. The description will be used to automatically exclude matching companies from results.

Return to setup menu.


5. Integrations

Salesforce
### Connect Salesforce

Salesforce integration lets OpenFunnel:
- Sync discovered accounts and contacts directly to Salesforce
- Enrich existing Salesforce accounts with buying signals
- Flag when CRM accounts show new activity

Want to connect Salesforce? (yes / skip)

If yes:

  1. Call bash "$API" POST /api/v1/integrations/salesforce/auth-url '{}' to get the OAuth authorization URL
  2. Present the URL to the user: Open this URL to authorize OpenFunnel with your Salesforce org: {auth_url} After authorizing, Salesforce will redirect you with a code. Paste the full redirect URL here.
  3. User pastes the redirect URL → extract the authorization code
  4. Call bash "$API" POST /api/v1/integrations/salesforce/callback '{"code": "...", "redirect_uri": "..."}' to complete the connection
  5. On success: ` Salesforce connected. You can now: - Sync accounts: bash "$API" POST /api/v1/crm/sync-accounts-job '{"account_ids": [...], "assigned_user_email": "..."}' - Sync people: bash "$API" POST /api/v1/crm/sync-people-job '{"people_ids": [...], "assigned_user_email": "..."}' - Check sync status: bash "$API" POST /api/v1/crm/check-job-status '{"job_id": "..."}' `

Return to setup menu.

HubSpot
### Connect HubSpot

HubSpot integration lets OpenFunnel:
- Sync discovered accounts and contacts directly to HubSpot
- Enrich existing HubSpot accounts with buying signals
- Flag when CRM accounts show new activity

Want to connect HubSpot? (yes / skip)

If yes:

  1. Call bash "$API" POST /api/v1/integrations/hubspot/auth-url '{}' to get the OAuth authorization URL
  2. Present the URL to the user: Open this URL to authorize OpenFunnel with your HubSpot account: {auth_url} After authorizing, HubSpot will redirect you with a code. Paste the full redirect URL here.
  3. User pastes the redirect URL → extract the authorization code
  4. Call bash "$API" POST /api/v1/integrations/hubspot/callback '{"code": "...", "redirect_uri": "..."}' to complete the connection
  5. On success: ` HubSpot connected. You can now: - Sync accounts: bash "$API" POST /api/v1/crm/sync-accounts-job '{"account_ids": [...], "assigned_user_email": "..."}' - Sync people: bash "$API" POST /api/v1/crm/sync-people-job '{"people_ids": [...], "assigned_user_email": "..."}' - Check sync status: bash "$API" POST /api/v1/crm/check-job-status '{"job_id": "..."}' `

Return to setup menu.

Slack
### Connect Slack

Slack integration lets OpenFunnel:
- Send real-time alerts when new signals fire
- Notify your team when high-priority accounts show buying activity
- Deliver daily/weekly signal digests to a channel

Want to connect Slack? (yes / skip)

If yes:

  1. Call bash "$API" POST /api/v1/integrations/slack/auth-url '{}' to get the OAuth authorization URL
  2. Present the URL to the user: Open this URL to authorize OpenFunnel with your Slack workspace: {auth_url} After authorizing, Slack will redirect you with a code. Paste the full redirect URL here.
  3. User pastes the redirect URL → extract the authorization code
  4. Call bash "$API" POST /api/v1/integrations/slack/callback '{"code": "...", "redirect_uri": "..."}' to complete the connection
  5. On success, configure notifications: Slack connected. **Configure notifications:** 1. **Channel** — Which Slack channel should receive alerts? (e.g., #sales-signals, #gtm-alerts) 2. **Alert frequency** — How often? - **Real-time** — instant notification per signal - **Daily digest** — summary once per day - **Weekly digest** — summary once per week 3. **Signal filter** — Which signals trigger Slack alerts? - All signals (default) - Specific signal IDs
  6. Collect user preferences, then call bash "$API" POST /api/v1/integrations/slack/configure '{"channel": "...", "frequency": "...", "signal_ids": [...]}' to save.

Return to setup menu.


6. Setup Complete

When the user has finished all sections (or says they're done):

### Setup Complete

Here's what's configured:

| Component | Status |
|-----------|--------|
| Firmographic ICP | {created — name (ID: x) / not set} |
| Advanced ICP | {saved / not set} |
| Blocklist | {x domains blocked / description set / not set} |
| Salesforce | {connected / not connected} |
| HubSpot | {connected / not connected} |
| Slack | {connected / not connected} |

You're ready to start finding accounts. Try:
- "Find companies hiring for [your space]"
- "Research [company name]"
- "Find people posting about [topic]"

平台分布

Codex

35.65%
按下载量换算52

Claude

30.6%
按下载量换算45

Cursor

20.19%
按下载量换算30

Gemini CLI

8.23%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

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