critical-peer

Verify claims and challenge anti-patterns with concrete improvements.

3|1|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/jagreehal/jagreehal-claude-skills --skill critical-peer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critical-peer
Source: https://github.com/jagreehal/jagreehal-claude-skills/tree/main/skills/critical-peer
Command: npx skills add https://github.com/jagreehal/jagreehal-claude-skills --skill critical-peer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enforces professional skepticism, pattern enforcement, and coaching in Claude-style conversations, ensuring verification before agreement, immediate challenge of anti-patterns, and proposing concrete improvements instead of asking.

Core Features & Use Cases

  • Verify claims before agreeing by inspecting evidence and citing patterns.
  • Challenge pattern violations with actionable refactors and precise language.
  • Propose improvements rather than asking for preferences, with concise, factual output.
  • Follow a research-first approach to ground responses in evidence and sources.

Quick Start

Instruct the assistant to verify a claim, identify any pattern violations, and propose concrete improvements in a concise, literal manner.

Frequently Asked Questions about critical-peer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce professional skepticism and verify claims during a code review?

Enforce professional skepticism during a code review by instructing the assistant to inspect evidence, cite patterns, and challenge anti-patterns with actionable refactors. This ensures claims are verified before agreement and concise, literal responses are generated.

What is the best way to challenge anti-patterns in design discussions?

The best way to challenge anti-patterns in design discussions is to verify claims against established patterns and propose concrete improvements rather than asking for preferences. This approach yields concise, factual output grounded in research-first reasoning.

How do I get concise, evidence-based critique for QA conversations?

Get concise, evidence-based critique for QA conversations by applying pattern-based coaching that verifies claims before agreeing. This method immediately challenges pattern violations and proposes specific, actionable improvements.

Can I use pattern enforcement to propose improvements instead of asking for preferences?

Yes, you can use pattern enforcement to propose concrete improvements instead of asking for preferences. It enforces a research-first approach to ground responses in evidence, challenge anti-patterns, and deliver concise, literal outputs.

When do I need professional skepticism in Claude outputs?

You need professional skepticism in Claude outputs during code reviews, design discussions, and QA conversations. It ensures verification before agreement, immediately challenges anti-patterns, and proposes concrete improvements.

Does this approach require any specific dependencies or components to function?

No, this approach requires no specific dependencies or components to function. It operates by enforcing professional skepticism and pattern-based coaching directly within the conversation to verify claims and propose actionable refactors.