How do I install the Consult LLM skill?

Run npx skillmds@latest add allyoushawn/consult-llm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Consult LLM safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Consult LLM?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Consult LLM free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Consult LLM?

allyoushawn (@allyoushawn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Consult LLM by allyoushawn — Agent Skill

Name: Consult LLM
Author: allyoushawn

Consult LLM

Use when the user wants a second opinion from Gemini or OpenAI/ChatGPT, asks to "consult" another model, or wants to compare responses across models. This is the interactive MCP chat path for a second opinion or model comparison; to run a structured review gate over code, diffs, plans, or large doc corpora through a headless CLI, use cli-review instead.

allyoushawn 52e258c 2.2 KB Updated Sep 17, 2026

File contents

consult-llm

You have access to two MCP tools for consulting other LLMs:

mcp__chat-gemini__chat-with-gemini — sends a message to Google Gemini
mcp__chat-openai__chat-with-openai — sends a message to OpenAI (GPT)

When This Skill Applies

Use this skill when the user:

Asks to "consult", "ask", or "check with" another LLM (Gemini, GPT, OpenAI, ChatGPT)
Wants a second opinion from a different model
Says "what does Gemini think", "ask GPT", "get another model's take", etc.
Wants to compare responses across models

How to Use

Selecting the right model

If the user specifies "Gemini" or "Google" → use mcp__chat-gemini__chat-with-gemini
If the user specifies "GPT", "OpenAI", or "ChatGPT" → use mcp__chat-openai__chat-with-openai
If unspecified or user wants both → consult both in parallel

Crafting the prompt

Send the user's question or context as-is, or distill it into a clear, self-contained query
If you need to include code or context, include enough for the other model to give a useful answer
Do not include internal Claude Code instructions or system context in the query

Presenting results

Quote the other model's response clearly, labeled with which model it came from
Add your own synthesis or comparison if the user asked for a second opinion
If both models were consulted, highlight agreements and disagreements

Example Invocations

User: "What does Gemini think about this regex?"
→ call mcp__chat-gemini__chat-with-gemini with the regex and context

User: "Ask GPT and Gemini both — which sorting algorithm should I use here?"
→ call both tools in parallel, then compare their answers

User: "Get a second opinion on my architecture"
→ pick one or both models, send the architecture description, synthesize the feedback

---name: consult-llmdescription: Use when the user wants a second opinion from Gemini or OpenAI/ChatGPT, asks to "consult" another model, or wants to compare responses across models. This is the interactive MCP chat path for a second opinion or model comparison; to run a structured review gate over code, diffs, plans, or large doc corpora through a headless CLI, use cli-review instead.---# consult-llmYou have access to two MCP tools for consulting other LLMs:- `mcp__chat-gemini__chat-with-gemini` — sends a message to Google Gemini- `mcp__chat-openai__chat-with-openai` — sends a message to OpenAI (GPT)## When This Skill AppliesUse this skill when the user:- Asks to "consult", "ask", or "check with" another LLM (Gemini, GPT, OpenAI, ChatGPT)- Wants a second opinion from a different model- Says "what does Gemini think", "ask GPT", "get another model's take", etc.- Wants to compare responses across models## How to Use### Selecting the right model- If the user specifies "Gemini" or "Google" → use `mcp__chat-gemini__chat-with-gemini`- If the user specifies "GPT", "OpenAI", or "ChatGPT" → use `mcp__chat-openai__chat-with-openai`- If unspecified or user wants both → consult both in parallel### Crafting the prompt- Send the user's question or context as-is, or distill it into a clear, self-contained query- If you need to include code or context, include enough for the other model to give a useful answer- Do not include internal Claude Code instructions or system context in the query### Presenting results- Quote the other model's response clearly, labeled with which model it came from- Add your own synthesis or comparison if the user asked for a second opinion- If both models were consulted, highlight agreements and disagreements## Example Invocations```User: "What does Gemini think about this regex?"→ call mcp__chat-gemini__chat-with-gemini with the regex and contextUser: "Ask GPT and Gemini both — which sorting algorithm should I use here?"→ call both tools in parallel, then compare their answersUser: "Get a second opinion on my architecture"→ pick one or both models, send the architecture description, synthesize the feedback```

Frequently asked questions