gemini-consultant
Get a second opinion from Gemini 3 Pro with Google Search grounding and vision. Use when you need real-time web information, want to verify facts, need a different perspective on a technical question, want to consult another AI model, or need to analyze images.
When & Why to Use This Skill
The Gemini Consultant skill empowers Claude agents with a 'second opinion' from Google's Gemini 3 Pro, featuring real-time Google Search grounding and advanced vision capabilities. It is specifically designed to handle massive context dumps, allowing for deep-dive technical analysis, cross-model verification, and up-to-date web research to solve complex engineering challenges that require a fresh perspective.
Use Cases
- Complex Debugging: Resolve stubborn 'RecursionErrors' or logic flaws by providing the model with exhaustive context, including source code, related imports, and full error tracebacks for a comprehensive root-cause analysis.
- Architecture & Security Audits: Perform high-level reviews of authentication flows, database schemas, and system architectures by feeding multiple configuration and route files into the model's large context window.
- Real-time Technical Research: Use Google Search grounding to fetch the latest documentation, library versions, or breaking changes in fast-moving ecosystems like Next.js or AI frameworks.
- Visual Analysis & UX Feedback: Analyze UI screenshots, architecture diagrams, or wireframes using Gemini's vision capabilities to identify design inconsistencies or accessibility issues.
- Cross-Model Verification: Get a critical second opinion on Claude's own code generation or logic to ensure higher reliability and catch edge cases that a single model might overlook.
| name | gemini-consultant |
|---|---|
| description | Get a second opinion from Gemini 3 Pro (gemini-3-pro-preview). Accepts text, code, and images as INPUT. Returns TEXT analysis, advice, and feedback. Use for code review, analyzing screenshots, UX feedback, debugging, architecture review, or web search. |
| allowed-tools | Bash(uv:*), Read |
Gemini Consultant
Get a second opinion from Google's Gemini 3 Pro (gemini-3-pro-preview) with real-time Google Search grounding.
CRITICAL: GEMINI IS BLIND. It knows nothing about your current session, file system, conversation history, or previous errors unless you explicitly force-feed it that data.
The "Dump Everything" Rule
The -c/--context argument is effectively unlimited. To get a useful answer, you must dump EVERYTHING relevant into the context.
- Quantity: We are talking about 10, 100, or 500+ lines of context.
- Scope: Include the file in question, all related files (imports, types, configs), the full error traceback, your current hypothesis, and a summary of what you have already tried.
- History: If you are deep in a debugging session, dump the relevant parts of the conversation history into the context.
If you think a file is even tangentially related, INCLUDE IT.
Prerequisites
GEMINI_API_KEY environment variable must be set.
Usage
uv run /path/to/skills/gemini-consultant/consult.py "Detailed Question" -c "MASSIVE CONTEXT STRING"
Parameters
| Parameter | Description |
|---|---|
question |
The prompt. Be specific. "Given error X and code Y (in context), why is logic Z failing?" |
-c, --context |
THE DATA DUMP. Concatenate everything here. Code, logs, history, configs. Can be used multiple times. |
-i, --image |
Image file paths (screenshots, diagrams). |
--media-resolution |
low, medium (default), high, ultra_high. |
--no-search |
Disable web search (pure code logic). |
--thinking |
low or high (default). Use high for code. |
Examples
BAD (Lazy = Failure)
# WRONG: Context is missing.
uv run consult.py "Why is this crashing?" -c "Error: 500 Internal Server Error"
# WRONG: Single file provided, ignoring dependencies.
uv run consult.py "Fix this function." -c "$(cat src/broken_file.py)"
GOOD (Exhaustive = Success)
NOTE: Real-world usages are usually 10-100x longer than the snippets below.
# CORRECT: Providing File, Imports, Types, and Errors
uv run consult.py "I am getting a RecursionError in the serialization logic. Analyze the relationship between the Model and the Schema." \
-c "FILE: src/models.py
$(cat src/models.py)
FILE: src/schemas.py
$(cat src/schemas.py)
FILE: src/config/db_settings.py
$(cat src/config/db_settings.py)
ERROR LOG:
$(cat logs/error_dump.txt)
PREVIOUS ATTEMPTS:
I tried removing the circular reference in schema.py line 40 but it broke the API validation."
# CORRECT: Architecture review with full project scope
uv run consult.py "Review this authentication flow for security flaws." \
-c "MIDDLEWARE: $(cat src/middleware/auth.ts)
MODELS: $(cat src/models/user.ts)
ROUTES: $(cat src/routes/auth.ts)
CONFIG: $(cat src/config/security.ts)
TYPES: $(cat src/types/express.d.ts)"
Web Search (No Code Context Needed)
uv run consult.py "What is the latest version of Next.js and what are its new features?"