yuanjian068yuan/opc-comment-lead-radar / marketplace/skillhub/ppxc-find-customers
find-customers
Verified找客户 / Find Customers / 销售线索 / 评论区获客 Skill。用于找客户、获客、销售线索、潜在客户、客户名单、AI获客、社媒获客、评论分析、评论获客、评论区获客、小红书获客、抖音获客、快手获客,从抖音、小红书、快手公开评论中识别购买意向、AI sales leads、高意向客户和可跟进客户名单。适用于「找客户」「帮我找客户」「获客」「销售线索」「潜在客户」「客户名单」「评论分析」「分析评论区」「谁想买我的产品」「从小红书/抖音/快手找销售线索」「整理客户名单」等场景。连接器启用后可直接试跑;看不到工具时先按接线步骤启用。
| File | Kind | Size |
|---|---|---|
| FAQ.md | markdown | 5.8 KB |
| SKILL.md | skill md | 22.7 KB |
| agents/openai.yaml | config | 550 B |
| examples/b2b-tax-consulting.md | markdown | 1.1 KB |
| examples/content-ideas-from-comments.md | markdown | 1.1 KB |
| examples/douyin-link-analysis.md | markdown | 1.6 KB |
| examples/ecommerce-competitor-complaint.md | markdown | 961 B |
| examples/education-price-objection.md | markdown | 923 B |
| examples/local-service-parent.md | markdown | 1.1 KB |
| examples/no-leads-recovery.md | markdown | 1.1 KB |
| examples/xiaohongshu-trial-scan.md | markdown | 1.6 KB |
examples/xiaohongshu-trial-scan.md
View on GitHub# 示例:小红书试用扫描
## 用户输入
```text
我卖敏感肌防晒喷雾,主要卖给军训、通勤、户外拍摄的人。帮我先在小红书试搜一批客户。
```
## Skill 应该怎么做
1. 先读取 `get_workflow_manifest`。
2. 不要求 OPC 登录,不要求用户先建产品。
3. 建议 3 个搜索词:`军训防晒敏感肌`、`通勤防晒不闷痘`、`户外拍摄防晒补涂`。
4. 用户确认后调用 `search_keyword_for_leads`,传产品描述和 `platform=xiaohongshu`。
5. 汇报过程、客户名单、评论原话、跟进话术和解锁提示。
## 输出示例
```text
搜完了。我在小红书搜了「军训防晒敏感肌、通勤防晒不闷痘、户外拍摄防晒补涂」,实际看了 8 篇笔记,共读到 186 条公开评论,挑出 11 个潜在客户,其中 4 个高意向。
优先跟这几位:
1. 橙子要军训(高意向 · 购买咨询):“下周军训,敏感肌,求不闷痘防晒。”
跟进:可以从“敏感肌军训不闷痘”角度回复,给她使用场景和补涂建议。
2. momo(高意向 · 竞品不满):“买过一个很油,下午直接闷闭口。”
跟进:先共情油和闷闭口,再说明清爽和成分安全。
这批评论还显示,客户最关心的是“不闷痘、方便补涂、军训暴晒”。要不要我基于这些原话写一条小红书视频脚本?
```
## 为什么这个示例有效
- 它先试用扫描,不提前要求 OPC 登录。
- 它展示过程透明度:搜索词、内容数量、评论数量。
- 它不只给名单,还给了跟进话术和内容选题。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |