claude-lead-finder
CLAUDE.md0 starsChanged 38 days agoMITView on GitHub
Local lead-generation tool. Three discovery sources (Google Places API, browser scrape, OpenStreetMap), email extraction, deterministic scoring, interactive map UI. The .claude/commands/ directory has slash commands for Claude Code: Plain language works too — "find electricians near Denver with email" triggers the skill. This tool makes zero LLM/AI calls. All logic is deterministic Python using stdlib only.
In this repositoryOne other file it gives its agents.
- lead-finderSkill
The file
Files
claude-lead-finder
Local lead-generation tool. Three discovery sources (Google Places API, browser scrape, OpenStreetMap), email extraction, deterministic scoring, interactive map UI.
Running
- Web UI:
python server.py→ http://localhost:9100 - CLI:
python scripts/find_businesses.py "City, ST" category - Web scraper: built-in, no setup needed (scrapes Google directly)
Commands
The .claude/commands/ directory has slash commands for Claude Code:
| Command | What it does |
/lead-find | Find and qualify businesses by trade and location |
/lead-batch | Run multiple searches from a keywords file |
/lead-setup | Health-check all discovery sources |
/lead-jobs | List cached search results |
Plain language works too — "find electricians near Denver with email" triggers the skill.
Key files
scripts/find_businesses.py— main search (all 3 sources, dedup, scoring, email)scripts/_scraper.py— direct Google web/Maps scraper (stdlib only)scripts/_common.py— shared helpers (HTTP, geocoding, email extraction)scripts/check_presence.py— social media presence checkerserver.py— local web server with SSE streaming + settings APImap.html— interactive map UI (Leaflet + results table + export)
No AI calls
This tool makes zero LLM/AI calls. All logic is deterministic Python using stdlib only.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.