gemini-qa
Use Google Gemini CLI to answer questions about code, analyze files, or perform codebase exploration. Invoke this skill when the user asks to use Gemini, wants a second opinion from another AI, or wants to compare Claude's answer with Gemini's response.
How do I install this agent skill?
npx skills add https://github.com/funnelenvy/agents_webinar_demos --skill gemini-qaIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill acts as a bridge to the Google Gemini CLI for codebase analysis. It is considered low risk because it uses trusted external sources, though it possesses an inherent surface for indirect prompt injection via the files it processes.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Gemini Q&A
Use Google's Gemini CLI to answer questions about the codebase.
Prerequisites
Gemini CLI must be installed:
npm install -g @anthropic-ai/gemini-cli
# or follow installation at https://github.com/google-gemini/gemini-cli
Authentication must be configured (Google API key or Application Default Credentials).
Usage
Spawn the gemini-qa subagent to handle the question:
Use the Task tool to spawn the gemini-qa agent with the user's question.
The subagent will:
- Formulate a clear prompt for Gemini
- Run
gemini -p "question"in headless mode - Return Gemini's response
Direct Usage (without subagent)
If you prefer to run Gemini directly:
gemini -p "your question here"
# or
gemini "your question here"
Command Options
- Basic query:
gemini -p "question" - Positional:
gemini "question" - Pipe input:
cat file.txt | gemini -p "summarize this" - JSON output:
gemini -p "question" --output-format json - File reference:
gemini -p "@src/file.ts explain this"
File References with @
Gemini supports @ syntax to include file context:
# Reference a specific file
gemini -p "@src/auth.ts Explain this module"
# Reference a directory
gemini -p "@src/ Summarize all code here"
Common Use Cases
- Code explanation: "What does this function do?"
- Architecture questions: "How is the database layer structured?"
- Finding patterns: "Where is error handling implemented?"
- Code review: "Review this file for potential issues"
- Comparison: Get a second opinion on a code question
Notes
- Use
-pflag for headless (non-interactive) mode - Gemini is git-aware and respects
.gitignorefor directory references - For complex questions, use the subagent for better context isolation
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/funnelenvy/agents_webinar_demos/gemini-qa">View gemini-qa on skillZs</a>