skill-gemini-google-maps-tool
Query Gemini with Google Maps grounding
What this skill does
# When to use
- When you need location-aware AI responses about places
- When you need recommendations for restaurants, hotels, attractions
- When you need accurate, up-to-date information from Google Maps
# Gemini Google Maps Tool Skill
## Purpose
Comprehensive guide for using gemini-google-maps-tool, a CLI and Python library that connects Gemini to Google Maps' database of 250+ million places worldwide for location-aware responses with accurate, up-to-date information.
## When to Use This Skill
**Use this skill when:**
- Querying for location-based recommendations (restaurants, hotels, attractions)
- Generating itineraries with place-specific information
- Building applications that need location-aware AI responses
- Integrating Google Maps data into AI workflows
- Creating travel, food, or local business applications
**Do NOT use this skill for:**
- General Gemini queries without location context
- Tasks that don't involve places or geographical information
- Direct Google Maps API queries (this uses Gemini with Maps grounding)
## CLI Tool: gemini-google-maps-tool
A production-ready CLI and Python library for querying Gemini with Google Maps grounding.
### Installation
```bash
# Install globally with uv tool
uv tool install gemini-google-maps-tool
# Or from source
git clone https://github.com/dnvriend/gemini-google-maps-tool.git
cd gemini-google-maps-tool
uv tool install .
```
### Prerequisites
- Python 3.14+
- [uv](https://github.com/astral-sh/uv) package manager
- Gemini API Key from [Google AI Studio](https://aistudio.google.com/app/apikey)
### Quick Start
```bash
# Set API key
export GEMINI_API_KEY="your-api-key"
# Basic query
gemini-google-maps-tool query "Best coffee shops in Amsterdam"
# With location context
gemini-google-maps-tool query "Italian restaurants nearby" \
--lat-lon "52.37,4.89"
# Markdown output with sources
gemini-google-maps-tool query "Museums in Paris" --text
```
## Progressive Disclosure
<details>
<summary><strong>๐ Core Commands (Click to expand)</strong></summary>
### query - Query Gemini with Google Maps Grounding
Query Gemini with Google Maps integration for location-aware information about places, businesses, directions, and attractions.
**Usage:**
```bash
gemini-google-maps-tool query "QUERY" [OPTIONS]
```
**Arguments:**
- `QUERY`: The search query (required unless using --stdin)
- `--lat-lon LAT,LON`: Location coordinates in format "lat,lon" (e.g., "37.78193,-122.40476")
- `--model {flash|flash-lite}`: Model selection
- `flash`: gemini-2.5-flash (more powerful, higher cost)
- `flash-lite`: gemini-2.5-flash-lite (default, faster, cost-effective)
- `-v, --verbose`: Enable INFO logging (operation-level details)
- `-vv`: Enable DEBUG logging (detailed API calls, validation)
- `-vvv`: Enable TRACE logging (full HTTP traces, library internals)
- `--text` / `-t`: Output markdown text instead of JSON
- `--stdin` / `-s`: Read query from stdin
**Examples:**
```bash
# Basic query
gemini-google-maps-tool query "Best coffee shops in Amsterdam"
# With location context
gemini-google-maps-tool query "Italian restaurants nearby" \
--lat-lon "52.37,4.89"
# Using different model
gemini-google-maps-tool query "Plan a day in NYC" --model flash
# Markdown output with sources
gemini-google-maps-tool query "Best museums in Paris" --text
# Verbose mode with grounding metadata
gemini-google-maps-tool query "Sushi restaurants" -v
# Debug mode with full details
gemini-google-maps-tool query "Hotels in London" -vv
# Trace mode with HTTP details
gemini-google-maps-tool query "Attractions in Rome" -vvv
# Reading from stdin (for pipelines)
echo "Best bakeries in San Francisco" | \
gemini-google-maps-tool query --stdin
# Pipeline with jq
gemini-google-maps-tool query "Coffee shops" | \
jq '.response_text'
```
**Output Formats:**
JSON (default):
```json
{
"response_text": "Here are some great coffee shops...",
"grounding_metadata": {
"grounding_chunks": [
{
"title": "Blue Bottle Coffee",
"uri": "https://maps.google.com/?cid=...",
"place_id": "places/ChIJ..."
}
]
}
}
```
Markdown (with --text):
```markdown
Here are some great coffee shops...
---
## Sources
1. [Blue Bottle Coffee](https://maps.google.com/?cid=...)
2. [Philz Coffee](https://maps.google.com/?cid=...)
```
---
### completion - Generate Shell Completion Scripts
Generate shell completion scripts for Bash, Zsh, or Fish to enable tab-completion for commands and options.
**Usage:**
```bash
gemini-google-maps-tool completion {bash|zsh|fish}
```
**Arguments:**
- `SHELL`: Shell type (required) - bash, zsh, or fish
**Examples:**
```bash
# Bash - temporary (current session)
eval "$(gemini-google-maps-tool completion bash)"
# Bash - persistent
echo 'eval "$(gemini-google-maps-tool completion bash)"' >> ~/.bashrc
# Zsh - temporary
eval "$(gemini-google-maps-tool completion zsh)"
# Zsh - persistent
echo 'eval "$(gemini-google-maps-tool completion zsh)"' >> ~/.zshrc
# Fish - install to completions directory
gemini-google-maps-tool completion fish > \
~/.config/fish/completions/gemini-google-maps-tool.fish
# File-based (better performance)
gemini-google-maps-tool completion bash > \
~/.gemini-google-maps-tool-complete.bash
echo 'source ~/.gemini-google-maps-tool-complete.bash' >> ~/.bashrc
```
**Output:**
Shell-specific completion script that can be evaluated or saved to a file.
</details>
<details>
<summary><strong>โ๏ธ Advanced Features (Click to expand)</strong></summary>
### Multi-Level Verbosity Logging
Progressive detail control for debugging and monitoring:
- **No flag (default)**: WARNING level - only critical issues
- **`-v`**: INFO level - high-level operations, important events
- **`-vv`**: DEBUG level - detailed operations, API calls, validation steps
- **`-vvv`**: TRACE level - full request/response, library internals, HTTP traces
**Examples:**
```bash
# INFO: See which files are processed
gemini-google-maps-tool query "Best restaurants" -v
# DEBUG: See API call details and validation
gemini-google-maps-tool query "Hotels nearby" -vv
# TRACE: See full HTTP requests/responses
gemini-google-maps-tool query "Museums" -vvv
```
---
### Google Maps Grounding
**What is it?**
Google Maps grounding connects Gemini to Google Maps' database of 250+ million places worldwide, providing:
- Location-aware responses with accurate, up-to-date information
- Personalized recommendations tailored to specific areas
- Automatic citation generation with structured sources
- Seamless integration via Gemini's API
**Grounding Metadata:**
With `-v` or `--text`, responses include:
- **Grounding Chunks**: Google Maps sources (title, URI, place_id)
- **Grounding Supports**: Text segments linked to sources
- **Widget Context Token**: For interactive maps integration
**Example:**
```bash
gemini-google-maps-tool query "Best pizza in Brooklyn" -v
```
Returns JSON with:
```json
{
"response_text": "...",
"grounding_metadata": {
"grounding_chunks": [
{
"title": "Roberta's Pizza",
"uri": "https://maps.google.com/?cid=...",
"place_id": "places/ChIJ..."
}
],
"grounding_supports": [...],
"google_maps_widget_context_token": "..."
}
}
```
---
### Location Context
Provide location coordinates for personalized, location-aware responses:
**Format:** `--lat-lon "latitude,longitude"`
**Examples:**
```bash
# Amsterdam center
gemini-google-maps-tool query "Coffee shops nearby" \
--lat-lon "52.37,4.89"
# San Francisco
gemini-google-maps-tool query "Italian restaurants" \
--lat-lon "37.78,-122.40"
# Tokyo
gemini-google-maps-tool query "Sushi restaurants" \
--lat-lon "35.68,139.76"
```
**Coordinate Ranges:**
- Latitude: -90 to 90
- Longitude: -180 to 180
---
### Model Selection
Choose between two Gemini models:
**flash-lite (default):**
- Model: gemini-2.5-flash-lite
- Faster, more cost-effective
- Best for simple location queries
- RecRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.