# Consult LLM

> Use this tool when you need to escalate complex problem-solving tasks beyond the capabilities of primary AI assistants, such as advanced reasoning, code review, or debugging. It accepts markdown files, code files, and git diff output as inputs and returns detailed responses from powerful language models like OpenAI's o3 or Google's Gemini 2.5 Pro. Ideal for scenarios requiring expert-level guidance, it provides a unified interface for multiple API providers and tracks costs, making it suitable for tasks that demand more advanced capabilities.

Canonical page: https://skillsregistry.net/skills/raine-consult-llm  
JSON: https://api.skillsregistry.net/v1/skills/raine-consult-llm

## Description

This MCP server enables AI assistants to consult more powerful language models (OpenAI's o3, Google's Gemini 2.5 Pro, and DeepSeek Reasoner) for complex problem-solving tasks that exceed the capabilities of the primary assistant. The implementation accepts markdown files as prompts along with relevant code files as context, optionally including git diff output to show uncommitted changes, then forwards the combined prompt to the specified model and returns the response with detailed cost tracking. It's particularly valuable for scenarios requiring advanced reasoning, code review, architecture decisions, or complex debugging where the primary assistant needs to escalate to more capable models, with comprehensive logging and support for multiple API providers through a unified interface.

## Trust

- **Trust score (0–1):** 0.48
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/raine-consult-llm)
- **Repository:** <https://github.com/raine/consult-llm>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "raine-consult-llm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/raine-consult-llm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/raine-consult-llm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt