Skip to content
mcp/skillhub

Agent Skill

Google Maps Scraper skill

google-maps-scrapergosom/google-maps-scraperskills/google-maps-scraper/SKILL.md

Find businesses, leads, emails, reviews, ratings, and contact details from Google Maps. Use for requests such as "find dentists in Berlin", "scrape Google Maps", "get local business leads", or "collect Google Maps reviews". Runs the open-source scraper locally with Docker and guides nontechnical users through setup, monitoring, and results.

6.7kMIT

always on

76 tokname + description

once used

1,324 tokSKILL.md body

bundled files

158 scripts

repo stars

6.7kGitHub

Install the Google Maps Scraper skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/gosom/google-maps-scraper --skill google-maps-scraper

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/gosom/google-maps-scraper.git /tmp/google-maps-scraper
mkdir -p ~/.claude/skills
cp -R /tmp/google-maps-scraper/skills/google-maps-scraper ~/.claude/skills/google-maps-scraper

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description76 tok
When the agent uses itThe SKILL.md instructions1,324 tok
Only if opened15 bundled files (31 KB)varies

Until it is used, google-maps-scraper costs about 18× less than the median MCP server we measured (1,362 tokens on every turn). Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Pre-approved tools (allowed-tools): Bash(node:*), Bash(bash:*), Bash(docker:*), Read, Write. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Google Maps Scraper
  • Guardrails
  • Workflow
  • 0. Refresh the workflow
  • 1. Understand the request
  • 2. Offer the proxy choice
  • 3. Configure credentials safely
  • 4. Prepare queries and validate locally
  • 5. Run and monitor the full crawl
  • 6. Present and continue working with results
  • Reference routing