---
id: "action-multi-llm-critique"
type: "action-item"
source_timestamps: ["00:06:12", "00:06:45"]
tags: ["quality-assurance", "refinement"]
related: ["framework-multi-llm-evaluation", "concept-multi-llm-refinement"]
speakers: ["Nate B. Jones"]
action: "Upload a draft skill file to a competing LLM for critique, then apply the feedback."
outcome: "A highly refined, robust skill that benefits from the reasoning capabilities of multiple models."
sources: ["s40-super-prompts"]
sourceVaultSlug: "s40-super-prompts"
originDay: 40
---
# Critique Skills Using a Secondary LLM

## Action

Before finalizing a skill:

1. Download the draft file from [[entity-claude-d40]].
2. Upload it to [[entity-chatgpt-d40]] (or [[entity-gemini-d40]]).
3. Ask the second model to assess the quality of the instructions and suggest specific improvements.
4. Feed those improvements back into Claude and ask Claude to revise the skill.

## Outcome

A highly refined, robust skill that benefits from the reasoning fingerprints of multiple models.

## Framework Reference

This action is the operational version of [[framework-multi-llm-evaluation]] and the practical realization of [[concept-multi-llm-refinement]].