gemini-research-subagent
Delegates large-context code analysis to Gemini CLI. Use when analyzing codebases, tracing bugs across files, reviewing architecture, or performing security audits. Gemini reads, Claude implements.
When & Why to Use This Skill
The Gemini Research Subagent is a high-performance Claude skill designed to bridge the gap between large-scale codebase analysis and implementation. By delegating heavy-duty context reading and multi-file analysis to the Gemini CLI, it empowers Claude to handle massive repositories efficiently. This skill is essential for developers needing deep insights into architecture, security, and complex logic without hitting context limits, allowing for a 'Gemini reads, Claude writes' workflow that maximizes productivity.
Use Cases
- Large Codebase Onboarding: Use the 'onboarder' and 'explainer' roles to quickly map out unfamiliar repositories and understand complex dependency structures.
- Cross-File Bug Debugging: Trace elusive bugs across multiple components by leveraging Gemini's ability to analyze files larger than 100 lines and identify root causes.
- Architectural Planning & Refactoring: Utilize the 'planner' role to design system changes and ensure new implementations align with existing architectural patterns.
- Security & Quality Audits: Perform comprehensive security vulnerability scans and code quality reviews across the entire source directory using specialized 'security' and 'reviewer' roles.
- Post-Implementation Verification: Automatically verify code changes against the codebase using the 'verify' template to ensure consistency and prevent regressions.
| name | Gemini Research Subagent |
|---|---|
| description | Delegates large-context code analysis to Gemini CLI. Use when analyzing codebases, tracing bugs across files, reviewing architecture, or performing security audits. Gemini reads, Claude implements. |
Gemini Research Subagent
You have access to Gemini CLI as a large-context research assistant. Use Gemini for reading large codebases, use yourself for implementation.
When to Invoke Gemini
ALWAYS use Gemini BEFORE:
- Reading files >100 lines
- Understanding unfamiliar code areas
- Tracing bugs across multiple files
- Making changes that affect multiple components
- Performing security or architecture reviews
DO NOT use Gemini for:
- Simple single-file edits you can handle
- Writing code (that's your job)
- Files you've already analyzed this session
How to Invoke
./skills/gemini.agent.wrapper.sh -d "@src/" "Your research question"
Available Roles (loaded from .gemini/roles/)
| Role | Command | Use Case |
|---|---|---|
reviewer |
-r reviewer |
Code quality, bugs, security |
debugger |
-r debugger |
Bug tracing, root cause analysis |
planner |
-r planner |
Architecture, implementation planning |
security |
-r security |
Security vulnerabilities audit |
auditor |
-r auditor |
Codebase-wide analysis |
explainer |
-r explainer |
Code explanation |
migrator |
-r migrator |
Migration planning |
documenter |
-r documenter |
Documentation generation |
dependency-mapper |
-r dependency-mapper |
Dependency analysis |
onboarder |
-r onboarder |
Onboarding guide |
Custom Roles
Add custom roles in .gemini/roles/<name>.md. Examples:
| Role | Focus |
|---|---|
kotlin-expert |
Kotlin/Android, coroutines |
typescript-expert |
TypeScript type safety |
python-expert |
Python async, type hints |
api-designer |
REST API design |
database-expert |
Query optimization |
Templates
# Implementation-ready output
./skills/gemini.agent.wrapper.sh -t implement-ready -d "@src/" "Add user profiles"
# Fix-ready output for bugs
./skills/gemini.agent.wrapper.sh -t fix-ready "Login fails with 401"
# Post-implementation verification
./skills/gemini.agent.wrapper.sh -t verify --diff "Added password reset"
Response Format
Gemini returns structured output you can parse:
## SUMMARY
[1-2 sentence overview]
## FILES
[file:line references]
## ANALYSIS
[detailed findings]
## RECOMMENDATIONS
[actionable items]
Workflow Pattern
- Research: Invoke Gemini to understand context
- Implement: You write code based on Gemini's analysis
- Verify: Invoke Gemini to verify your changes
Example Usage
# Pre-implementation research
./skills/gemini.agent.wrapper.sh -r planner -d "@src/" "How should I add caching?"
# Post-implementation verification
./skills/gemini.agent.wrapper.sh -t verify --diff "Added caching layer"