← Back to Skills Marketplace
jayjjimenez

Cold Email Generator

by JayJJimenez · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
319
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install cold-email-generator
Description
Generates personalized, concise cold emails pitching Gracie AI Receptionist by scraping business websites for relevant details.
README (SKILL.md)

cold-email-generator

Purpose: Generate personalized cold emails pitching Gracie AI Receptionist to local businesses.

Takes a business name + website URL, scrapes their site to extract real context (services, staff, location), then uses Ollama (llama3.2) to write a short, specific cold email — not a template.


Usage

Single business

python3 ~/StudioBrain/00_SYSTEM/skills/cold-email-generator/generator.py \
  --name "Victory Auto Repair" \
  --url "https://victoryautosi.com" \
  --phone "718-698-9896"

Single business + save to file

python3 ~/StudioBrain/00_SYSTEM/skills/cold-email-generator/generator.py \
  --name "P.A.C. Plumbing" \
  --url "https://pac-plumbing.com" \
  --save

Batch: all leads with websites from MASTER_LEAD_LIST.md

python3 ~/StudioBrain/00_SYSTEM/skills/cold-email-generator/generator.py --list
python3 ~/StudioBrain/00_SYSTEM/skills/cold-email-generator/generator.py --list --save

Output

  • Prints email to terminal
  • --save writes to: ~/StudioBrain/30_INTERNAL/WLC-Services/OUTREACH/[business-name].txt

What It Does

  1. Scrapes homepage (+ about/contact pages if linked)
  2. Extracts: business name, owner, services, location, staff mentions
  3. Sends context to ollama run llama3.2 with a structured prompt
  4. Returns a 3-paragraph email under 150 words

Dependencies

  • Scrapling: ~/StudioBrain/00_SYSTEM/skills/scrapling/scrape.py
  • Ollama with llama3.2: ollama list to verify
  • LEADS file: ~/StudioBrain/30_INTERNAL/WLC-Services/LEADS/MASTER_LEAD_LIST.md

Gracie Pitch Details

  • Setup: $299
  • Monthly: $399/mo
  • Demo line: (347) 851-1505
  • Pitched by: Jay Jimenez, White Lighter Club Studios
Usage Guidance
This skill appears to do what it says: it scrapes websites, calls your local Ollama model, and writes emails to ~/StudioBrain/30_INTERNAL/WLC-Services/OUTREACH. Before installing/running: (1) confirm ollama and the llama3.2 model are installed locally and you accept any license/usage implications; (2) inspect the scrape script at /Users/wlc-studio/StudioBrain/00_SYSTEM/skills/scrapling/scrape.py to ensure it is trusted (it will be executed for each URL); (3) check MASTER_LEAD_LIST.md for any sensitive data you don't want processed; (4) be aware generated emails include scraped site text — ensure compliance with privacy / terms of the target sites and with your outreach policies; and (5) note the script writes files in your home directory and uses a hardcoded path for the scrape script, so adapt paths if your environment differs.
Capability Analysis
Type: OpenClaw Skill Name: cold-email-generator Version: 1.0.0 The skill is a legitimate tool for generating personalized cold emails by scraping business websites and using a local LLM (Ollama). The generator.py script parses a local lead list (MASTER_LEAD_LIST.md), scrapes content from target websites using a secondary local script, and saves the generated emails to a specific outreach directory with sanitized filenames. The code uses safe subprocess calls and lacks any indicators of data exfiltration, persistence, or malicious intent.
Capability Assessment
Purpose & Capability
Name/description match the implementation: generator.py scrapes business websites, sends scraped text to a local Ollama model (llama3.2), and produces short cold emails. The declared dependencies in SKILL.md (a local scrape script and Ollama) are the resources the code actually calls. The only minor mismatch is a hardcoded absolute path for the scrape script (SCRAPE_SCRIPT = "/Users/wlc-studio/StudioBrain/00_SYSTEM/skills/scrapling/scrape.py") vs. the SKILL.md's use of a tilde path; this is a brittleness but not malicious.
Instruction Scope
SKILL.md and the script instruct scraping target websites, reading a local leads file (MASTER_LEAD_LIST.md), and saving outputs to ~/StudioBrain/30_INTERNAL/... — all of which the code does. These actions are within the stated scope, but they entail scraping arbitrary external sites and reading/writing files in your home directory, so verify the leads file and the scrape script are trusted before running.
Install Mechanism
There is no install spec; this is instruction+script only. The script uses subprocess to call an external local script and the local Ollama binary. No network downloads or archive extraction are performed by the skill itself. The highest risk is a dependency on locally present binaries/scripts (scrape.py and ollama).
Credentials
The skill requests no environment variables or credentials. It does read a local leads file and writes to a local OUTREACH directory in the user's home; this is consistent with an outreach tool. There are no hidden credential accesses. Confirm that the hardcoded SCRAPE_SCRIPT path points to an expected/trusted script on your system.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistent privileges. It creates and writes files under the user's ~/StudioBrain directory (its own data), which is normal for this kind of tool. Autonomous model invocation is allowed (default) but does not by itself indicate risk.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cold-email-generator
  3. After installation, invoke the skill by name or use /cold-email-generator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of cold-email-generator skill. - Automatically scrapes business websites to gather real context for each lead. - Generates concise, personalized cold emails (not templates), pitching Gracie AI Receptionist. - Supports single business mode, batch processing from a lead list, and email output saving. - Integrates with Ollama (llama3.2) for email generation and requires Scrapling for scraping. - Output: prints to terminal or saves to organized text files for outreach campaigns.
Metadata
Slug cold-email-generator
Version 1.0.0
License
All-time Installs 2
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Cold Email Generator?

Generates personalized, concise cold emails pitching Gracie AI Receptionist by scraping business websites for relevant details. It is an AI Agent Skill for Claude Code / OpenClaw, with 319 downloads so far.

How do I install Cold Email Generator?

Run "/install cold-email-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Cold Email Generator free?

Yes, Cold Email Generator is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Cold Email Generator support?

Cold Email Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Cold Email Generator?

It is built and maintained by JayJJimenez (@jayjjimenez); the current version is v1.0.0.

💬 Comments