什么是 Apify 线索生成？

Apify 线索生成技能让您的智能体成为高效的拓客机器。通过利用庞大的 Apify Actors 库，此 Openclaw Skills 集成允许用户从 Google 地图、In@stagram、TikTok 和 Face@book 等平台提取有价值的联系信息、业务详情和社交媒体洞察。它将繁琐的手动数据收集过程自动化，提供可直接用于触达的结构化线索。

该技能基于 mcpc 协议构建，确保与 Apify 生态系统进行安全且动态的交互。用户可以为销售、营销或研究目的生成高度针对性的潜在客户列表，使其成为 Openclaw Skills 目录中数据驱动增长的重要工具。它处理了 API 交互和数据格式化的复杂性，让您能够专注于高层策略而非技术抓取逻辑。

下载入口:https://github.com/openclaw/skills/tree/main/skills/protoss70/apify-lead-generation

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Apify 线索生成 应用场景

• 通过 Google Places 自动发现餐厅或健身房等本地商家。
• 从 In@stagram 和 TikTok 提取红人联系详情和互动指标，用于营销活动。
• 通过抓取 Face@book 页面和群组获取商业智能，构建 B2B 潜在客户列表。
• 利用网站抓取工具获取的电子邮件和电话号码丰富现有联系人列表。
• 在 Openclaw Skills 内部坚控 Google 搜索结果，进行广泛的线索发现和竞争分析。

1. 智能体根据用户的具体拓客需求，确定最佳线索来源，如 Google 地图或 TikTok。
2. 它使用 mcpc CLI 动态获取最新的 Actor 架构，以确保识别所有必需的参数和输入结构。
3. 智能体会提示用户输入特定偏好，包括最大结果数和所需的输出格式（如 CSV 或 JSON）。
4. 它执行抓取脚本，将验证后的 JSON 输入和安全脱敏的参数传递给 Apify 平台。
5. 完成后，智能体会总结结果，提供特定的文件位置，并为收集的数据建议富化或过滤步骤。

Apify 线索生成 配置指南

要在您的 Openclaw Skills 环境中使用此功能，请确保已安装 Node.js 20.6+ 并准备好 API 令牌。将您的令牌添加到环境变量中：

export APIFY_TOKEN='your_apify_api_token'

mcpc CLI 会通过技能元数据自动处理，但您也可以通过运行以下命令手动确保就绪：

npm install -g @apify/mcpc

Apify 线索生成 数据架构与分类体系

该技能以多种格式生成结构化线索数据。输出文件使用清晰的命名规范保存，以保持您的 Openclaw Skills 工作区井然有序。

name: apify-lead-generation
description: Generates B2B/B2C leads by scraping Google Maps, websites, In@stagram, TikTok, Face@book, LinkedIn, YouTube, and Google Search. Use when user asks to find leads, prospects, businesses, build lead lists, enrich contacts, or scrape profiles for sales outreach.
version: 1.0.1
source: https://github.com/apify/agent-skills
homepage: https://apify.com
metadata:
  openclaw:
    requires:
      env:
        - APIFY_TOKEN
      bins:
        - node
        - mcpc
    primaryEnv: APIFY_TOKEN
    install:
      - kind: node
        package: "@apify/mcpc"
        bins: [mcpc]

Lead Generation

Scrape leads from multiple platforms using Apify Actors.

Prerequisites

• APIFY_TOKEN configured in OpenClaw settings
• Node.js 20.6+
• mcpc CLI (auto-installed via skill metadata)

Input Sanitization Rules

Before substituting any value into a bash command:

• ACTOR_ID: Must be either a technical name (owner/actor-name — alphanumeric, hyphens, dots, one slash) or a raw ID (exactly 17 alphanumeric characters, e.g., oeiQgfg5fsmIJB7Cn). Reject values containing shell metacharacters (; | & $ ` ( ) { } < > ! ).
• SEARCH_KEYWORDS: Plain text words only. Reject shell metacharacters.
• JSON_INPUT: Must be valid JSON. Must not contain single quotes (use escaped double quotes). Validate structure before use.
• Output filenames: Must match YYYY-MM-DD_descriptive-name.{csv,json}. No path separators (/, ..), no spaces, no metacharacters.

Workflow

Copy this checklist and track progress:

Task Progress:
- [ ] Step 1: Determine lead source (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the lead finder script
- [ ] Step 5: Summarize results

Step 1: Determine Lead Source

Select the appropriate Actor based on user needs:

Step 2: Fetch Actor Schema

Fetch the Actor's input schema and details dynamically using mcpc:

mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"

Replace ACTOR_ID with the selected Actor (e.g., compass/crawler-google-places).

This returns:

• Actor description and README
• Required and optional input parameters
• Output fields (if available)

Step 3: Ask User Preferences

Before running, ask:

1. Output format:
   • Quick answer - Display top few results in ch@t (no file saved)
   • CSV - Full export with all fields
   • JSON - Full export in JSON format
2. Number of results: Based on character of use case

Step 4: Run the Script

Quick answer (display in ch@t, no file):

node {baseDir}/reference/scripts/run_actor.js r
  --actor 'ACTOR_ID' r
  --input 'JSON_INPUT'

CSV:

node {baseDir}/reference/scripts/run_actor.js r
  --actor 'ACTOR_ID' r
  --input 'JSON_INPUT' r
  --output 'YYYY-MM-DD_OUTPUT_FILE.csv' r
  --format csv

JSON:

node {baseDir}/reference/scripts/run_actor.js r
  --actor 'ACTOR_ID' r
  --input 'JSON_INPUT' r
  --output 'YYYY-MM-DD_OUTPUT_FILE.json' r
  --format json

Step 5: Summarize Results

After completion, report:

• Number of leads found
• File location and name
• Key fields available
• Suggested next steps (filtering, enrichment)

Security & Data Privacy

This skill instructs the agent to select an Apify Actor, fetch its schema (via mcpc), and run scrapers. The included script communicates only with api.apify.com and writes outputs to files under the current working directory; it does not access unrelated system files or other environment variables.

Apify Actors only scrape publicly available data and do not collect private or personally identifiable information beyond what is openly accessible on the target platforms. For additional security assurance, you can check an Actor's permission level by querying https://api.apify.com/v2/acts/:actorId — an Actor with LIMITED_PERMISSIONS operates in a restricted sandbox, while FULL_PERMISSIONS indicates broader system access. For full details, see Apify's General Terms and Conditions.

Error Handling

APIFY_TOKEN not found - Ask user to configure APIFY_TOKEN in OpenClaw settings mcpc not found - Run npm install -g @apify/mcpc Actor not found - Check Actor ID spelling Run FAILED - Ask user to check Apify console link in error output Timeout - Reduce input size or increase --timeout