How do I install Skeptical Analyst?

Install Skeptical Analyst with a single command: npx mdskills install mdskills/skeptical-analyst-persona. This downloads the skill files into your project and your AI agent picks them up automatically.

What platforms support Skeptical Analyst?

Skeptical Analyst works with Claude Code, Openai, Gemini. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.

← Back to prompts

Skeptical Analyst

Name: Skeptical Analyst: AI Agent Skill
Brand: mdskills
Availability: InStock
Author: mdskills

Official

Persona for a research-desk analyst who assumes every claim is wrong until proven. Interrogates data, checks methodology, flags survivorship bias and confounders before offering a conclusion.

by mdskills

npx mdskills install mdskills/skeptical-analyst-persona

Senior Code Reviewer

Persona for a staff-level code reviewer who focuses on correctness, security, and long-term maintainability. Refuses to bikeshed style unless the style choice hides a real bug.

Improve This Prompt

Meta-prompt: takes an existing prompt and returns a tightened version. Removes vague instructions, adds output shape, converts negatives to positives, and flags any missing context.

Generate Prompt from Example

Meta-prompt: given a desired output example, works backward to produce a prompt that would reliably generate that output. Useful for reverse-engineering prompts from products you like.

Summarize Meeting Notes

Task prompt that turns raw meeting notes into a structured summary — decisions, action items with owners, open questions, and a one-line TL;DR.

Prompt details

Scope: Persona
Character / role the model plays
Recommended model: Claude Opus

Are you @mdskills? Sign in with GitHub to claim this listing.

SKILL.md

1You are a research-desk analyst. Your default assumption is that any claim you are presented with is wrong or incomplete. You interrogate:
2 
3- **Data quality** — where did this come from, how was it sampled, what's missing?
4- **Methodology** — is the technique appropriate for the question?
5- **Confounders** — what else could explain the observed pattern?
6- **Survivorship bias** — are we only seeing the winners?
7- **Base rates** — is the "significant" effect large relative to background variance?
8 
9You only offer a conclusion after you've addressed these. If the evidence doesn't support a strong claim, say so plainly. Do not soften your uncertainty with hedges.

Full transparency — inspect the skill content before installing.

Senior Code Reviewer

Prompt

Persona for a staff-level code reviewer who focuses on correctness, security, and long-term maintainability. Refuses to bikeshed style unless the style choice hides a real bug.

by mdskills

Improve This Prompt

Prompt

Meta-prompt: takes an existing prompt and returns a tightened version. Removes vague instructions, adds output shape, converts negatives to positives, and flags any missing context.

by mdskills

Generate Prompt from Example

Prompt

Meta-prompt: given a desired output example, works backward to produce a prompt that would reliably generate that output. Useful for reverse-engineering prompts from products you like.

by mdskills

Summarize Meeting Notes

Prompt

Task prompt that turns raw meeting notes into a structured summary — decisions, action items with owners, open questions, and a one-line TL;DR.

by mdskills

Classify User Intent

Prompt

Task prompt that classifies a user message into one of a fixed set of intents. Returns strict JSON. Good template for building fast intent routers.

by mdskills

Sentiment Analysis (few-shot)

Prompt

Three-example few-shot prompt for sentiment classification. Handles positive / negative / neutral with reasoning. Template you can extend for domain-specific classes.

by mdskills

Skeptical Analyst

Prompt details

Related

Senior Code Reviewer

Improve This Prompt

Generate Prompt from Example

Summarize Meeting Notes

Classify User Intent

Sentiment Analysis (few-shot)