lead-finder
Skill0 starsChanged 38 days agoMITView on GitHub
Find and qualify local businesses by trade and location. Three discovery sources (Google Places API, web scraper, OpenStreetMap), multi-signal deduplication, email extraction, deterministic scoring, and an interactive results browser. Triggers on requests like "find dentists in Denver" or "build a lead list of electricians near Folsom, CA". Works with Claude Code, Cursor, Codex CLI, Windsurf, Cline, Aider, or any assistant that can run Python scripts and read JSON output.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- aurelioagency/skillstheir own version, first seen Nov 1, 2026
- Big-LAORE/Biblioth-que-de-skillstheir own version, first seen Nov 1, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- anthropics/knowledge-work-plugins★ 35ksame name
- aurelioagency/skills★ 1same name
- Big-LAORE/Biblioth-que-de-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 95
Start at depth 5 and raise only when needed.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lead Finder
Tested Python scripts in scripts/ do the actual work — run them and present their
output. Do not try to find businesses by reasoning or web search alone.
This skill is portable: copy the skills/lead-finder/ folder into any project's
.claude/skills/ directory and it will auto-trigger on lead-finding requests.
Commands
| Command | Action |
/lead-find <trade> in <city> | Find and qualify businesses, return a scored table and results browser |
/lead-batch <file> [--city "City"] | Run many searches as one job |
/lead-setup | Health-check all discovery sources |
/lead-jobs | List cached search results |
Plain language works too. The skill triggers on requests like:
- "find electricians near Folsom, CA"
- "build me a lead list of dentists in Denver, CO"
- "pull Google Maps listings for plumbers in Phoenix"
- "search for coffee shops in Hamilton, Ontario with email"
Discovery sources (best available wins)
| Priority | Source | Needs | Speed | Coverage | ToS |
| 1 | Google Places API | GOOGLE_PLACES_API_KEY | ~2 s | Excellent | ✅ Compliant |
| 2 | Web scraper (Playwright / stdlib) | Nothing (built-in) | 5–15 s | Good | ⚠️ Violates Google ToS |
| 3 | OpenStreetMap | Nothing | 5–30 s | Sparse | ✅ Free / open |
--source auto (default) tries them in order. Force one with --source api|scrape|osm.
Finding businesses
python scripts/find_businesses.py "<place>" <category> [options]
python scripts/find_businesses.py --query "free text" "<place>" [options]
python scripts/find_businesses.py --list-categories17 built-in categories: restaurant, salon, gym, dentist, clinic, electrician, plumber,
trades, auto, lawyer, realestate, accountant, insurance, cleaner, petcare, photographer,
tutor. Free-text --query works for anything else (needs Google API or browser scraper).
Key flags:
--mode no_website(default) |has_website|both--source auto|api|scrape|osm--depth N— browser scrape depth (default 5, more = slower + more results)--limit N— max results (default 20)--radius N— metres (default 8000)--no-email— skip email extraction (faster)--review— open interactive results browser--include-chains— include franchise branches
Output is JSON to stdout. Every result carries score (0–100) and reasons.
Checking presence
python scripts/check_presence.py "<business name>" [website]Scans the business's own website for social/directory links. Returns {platform: url}.
Presenting results
- Summarise: total found, with email, score ≥ 70.
- For top leads, explain why (the
reasonsfield). - Offer to check social presence of specific businesses.
- Offer to export as JSON or CSV.
Responsible use
The web scraper fetches Google search and Maps pages directly when --source scrape.
- Start at depth 5 and raise only when needed.
- Watch for empty results — it means Google is rate-limiting. Wait a few minutes.
- Suggest
GOOGLE_PLACES_API_KEYfor production use. - For large requests, flag the risk, then proceed.
- Refuse only clearly abusive use (mass scraping, reselling raw data).
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.