# Meta-Prompting

> Use this tool when you need to enhance language models with dynamic multi-agent capabilities for complex problem-solving, breaking down tasks into manageable subtasks and executing them through collaborative workflows. It solves problems requiring structured multi-perspective reasoning, such as architectural decisions and building AI assistants, by providing a Conductor and specialized Experts within a single model. The tool takes in complex problems as input and outputs robust solutions through guided system prompts, making it ideal for use cases involving task-agnostic scaffolding and self-critique.

Canonical page: https://skillsregistry.net/skills/tisu19021997-meta-prompting  
JSON: https://api.skillsregistry.net/v1/skills/tisu19021997-meta-prompting

## Description

This MCP server implements the Meta-Prompting technique from the paper 'Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding', transforming a standard language model into a dynamic multi-agent system where the LM adopts two key roles: a Conductor that analyzes complex problems and breaks them into subtasks, and specialized Experts that execute each subtask. Built with Python using FastMCP and supporting multiple LLM providers (OpenAI, Anthropic, Google), the implementation simulates collaborative workflows within a single model through guided system prompts, allowing the model to reason, act, and self-critique for more robust solutions. The server provides tools for meta_model_prompt activation and expert_model consultation, with a fallback mechanism for clients that don't support ctx.sample(), making it valuable for complex problem-solving workflows, architectural decisions, and building AI assistants that benefit from structured multi-perspective reasoning without the overhead of managing separate model instances.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/tisu19021997-meta-prompting)
- **Repository:** <https://github.com/tisu19021997/meta-prompt-mcp-server>

## 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": "tisu19021997-meta-prompting"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tisu19021997-meta-prompting` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tisu19021997-meta-prompting/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