← 返回 Skills 市场
jayjjimenez

Google Reviews Pain Detector

作者 JayJJimenez · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
272
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install google-reviews-pain-detector
功能描述
Scrapes Google reviews for businesses to identify pain words related to missed calls and poor phone coverage, scoring lead quality for AI receptionist sales.
使用说明 (SKILL.md)

Google Reviews Pain Detector

Skill: google-reviews-pain-detector
Purpose: Scrape Google reviews for businesses and detect "pain words" that signal missed calls, poor phone coverage, and lost customers — hot signals for Gracie AI Receptionist leads.


What It Does

  1. Accepts a business name (+ optional address) as input
  2. Searches Google for [business name] reviews and scrapes result pages
  3. Also attempts to scrape Google Maps reviews directly
  4. Scans all review text for pain words indicating missed calls / unreachable staff
  5. Outputs: business name, matched pain words, example snippets, and a PAIN SCORE (0–10)
  6. Can run against the full Master Lead List with --list
  7. Can append HOT-tagged leads (score ≥ 3) to the Master Lead List with --save

Pain Words Detected

voicemail, no answer, hard to reach, couldn't get through, called 3 times,
never called back, missed call, didn't answer, goes to voicemail,
unanswered, unreachable, left a message

Usage

Single business

cd ~/StudioBrain/00_SYSTEM/skills/google-reviews-pain-detector
python3 detector.py "P.A.C. Plumbing Staten Island"
python3 detector.py "Victory Auto Repair" --address "3735 Victory Blvd, SI"

Full lead list scan

python3 detector.py --list

Scan + save HOT leads (score ≥ 3) back to master list

python3 detector.py --list --save

JSON output

python3 detector.py "Rafi's Auto Repair" --json
python3 detector.py --list --json

Output Example

══════════════════════════════════════════════════════
🔍 P.A.C. Plumbing, Heating & A/C
══════════════════════════════════════════════════════
📍 Address: 545 Port Richmond Ave, SI 10302
🔥 PAIN SCORE: 6/10
🎯 Pain Words Found: voicemail (3), no answer (1), never called back (1)

📋 Example Snippets:
  • "...went to voicemail every time I called after hours..."
  • "...no answer on Saturday, had to find another plumber..."
  • "...never called back after leaving a message..."

✅ HOT LEAD — Strong signal for Gracie AI Receptionist pitch

Dependencies

  • Python 3.9+
  • Scrapling skill at ~/StudioBrain/00_SYSTEM/skills/scrapling/ (with .venv)
  • No additional installs required

Files

File Purpose
SKILL.md This file
detector.py Main script
安全使用建议
This skill appears to implement the advertised scraping and pain-word detection, but it is not self-contained: it expects a local 'scrapling' virtualenv at a hardcoded absolute path and accesses a hardcoded MASTER_LEAD_LIST file in /Users/wlc-studio/. Before installing or running: (1) Verify the scrapling dependency exists and inspect that code (StealthyFetcher can run a headless browser and bypass protections). (2) Back up the MASTER_LEAD_LIST file and confirm you want this skill to read/modify it; the metadata does not declare this required path. (3) Review the rest of detector.py (saving logic) for any network callbacks or hidden uploads (the provided file was truncated). (4) Consider running the script in a sandboxed or isolated environment to avoid large-scale scraping or unintended modifications. (5) Be aware scraping Google/Maps/Yelp may violate terms of service or trigger rate-limiting; if you only need one-off lookups, run per-business rather than --list to reduce blast radius.
功能分析
Type: OpenClaw Skill Name: google-reviews-pain-detector Version: 1.0.0 The skill is a specialized lead generation tool designed to scrape and analyze business reviews from Google and Yelp to identify customer service 'pain points' (e.g., missed calls). The code in detector.py implements legitimate scraping logic using the Scrapling library and manages a local lead list in Markdown format. While it contains hardcoded absolute file paths (e.g., /Users/wlc-studio/...) and references to a future Python version (3.14), its behavior is entirely consistent with its stated purpose and lacks any indicators of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description (detect pain words in reviews) match the code's behavior (scrapes Google/Yelp/Maps and searches review sites). However the script depends on a local 'scrapling' virtualenv at an absolute user path and reads/writes a master lead list at a hardcoded path (/Users/wlc-studio/...). Those local path dependencies are not declared in the skill metadata (requires.env/config paths = none) and are specific to the pack author's environment.
Instruction Scope
SKILL.md instructs scanning single businesses or the full master list and saving HOT leads. The runtime instructions + code will perform headless stealth scraping of Google Search and Google Maps (via StealthyFetcher with cloudflare solving), follow external review links, and (per SKILL.md/flags) can append back to the MASTER_LEAD_LIST. That gives the skill the ability to perform bulk scraping and to read/modify a local lead file — behavior not emphasized in the metadata and potentially unexpected by users.
Install Mechanism
No install spec (instruction-only) which reduces installer risk. But the script forcibly boots a site-packages path for a local virtualenv (/Users/wlc-studio/…/scrapling/.venv/lib/python3.14/site-packages) and will exit if it can't import Scrapling. The lack of an explicit dependency declaration or a standard install step is a usability and coherence issue (the skill relies on an out-of-band local package).
Credentials
Metadata declares no required env vars or config paths, yet the code uses hardcoded filesystem locations (SCRAPLING_VENV_SITE and MASTER_LEAD_LIST) and will read and (per SKILL.md) append to that master lead list. This is a mismatch: the skill silently requires access to specific local files and directories which grant access to potentially sensitive lead data.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It does not attempt to modify other skills or system-wide configurations in the visible code. Its principal effect on the system is reading/parsing and potentially appending to the MASTER_LEAD_LIST file.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install google-reviews-pain-detector
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /google-reviews-pain-detector 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of Google Reviews Pain Detector. - Scrapes Google and Google Maps reviews for a given business. - Detects key "pain words" that indicate missed calls or poor phone coverage. - Outputs pain word matches, example review snippets, and a pain score (0–10). - Supports scanning individual businesses or the full Master Lead List, with options to save hot leads and output JSON.
元数据
Slug google-reviews-pain-detector
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Google Reviews Pain Detector 是什么?

Scrapes Google reviews for businesses to identify pain words related to missed calls and poor phone coverage, scoring lead quality for AI receptionist sales. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 272 次。

如何安装 Google Reviews Pain Detector?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install google-reviews-pain-detector」即可一键安装,无需额外配置。

Google Reviews Pain Detector 是免费的吗?

是的,Google Reviews Pain Detector 完全免费(开源免费),可自由下载、安装和使用。

Google Reviews Pain Detector 支持哪些平台?

Google Reviews Pain Detector 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Google Reviews Pain Detector?

由 JayJJimenez(@jayjjimenez)开发并维护,当前版本 v1.0.0。

💬 留言讨论