Challenge That

Force critical evaluation of proposals, requirements, or decisions by analyzing from multiple adversarial perspectives. Triggers on: accepting a proposal without pushback, 'sounds good', 'let's go with', design decisions with unstated tradeoffs, unchallenged assumptions, premature consensus. Invoke with /challenge-that.

365 stars 47 forksSoftware Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add NTCoding/claude-skillz

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NTCoding/claude-skillz --skill challenge-that
Manual install
git clone --depth 1 https://github.com/NTCoding/claude-skillz.git /tmp/claude-skillz
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skillz/challenge-that ~/.claude/skills/challenge-that

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Challenge That

Force critical evaluation by analyzing from multiple adversarial perspectives.

## When to Use

Invoke `/challenge-that` when:
- Claude accepted a proposal without critical evaluation
- You want to stress-test a decision before committing
- Requirements feel under-examined
- Something seems off but you can't articulate why

## The Five Hats

Each perspective challenges from a different angle:

| Hat | Focus | Key Questions |
|-----|-------|---------------|
| 🔴 **Skeptic** | Evidence & proof | "What evidence supports this? Has this been validated? Are we guessing?" |
| 🟡 **Pragmatist** | Cost/benefit | "Is this the simplest fix? What's the maintenance burden? Is it worth it?" |
| 🟢 **Edge Case Hunter** | Failure modes | "What breaks this? What's the worst case? What did we miss?" |
| 🔵 **Structural Critic** | Architecture | "Is this the right location? Does it fit the existing design? Will it cause problems elsewhere?" |
| 🟣 **Root Cause Analyst** | Problem diagnosis | "Is the problem correctly identified? Are we treating symptoms? What's the actual cause?" |

## Behavior

When `/challenge-that` is invoked:

1. Identify what was just accepted/proposed
2. State it clearly: "Challenging: [the proposal/decision]"
3. Analyze from each of the five perspectives
4. Synthesize into actionable concerns
5. Ask: "Which concerns should we address before proceeding?"

## Output Format
Read the full skill on GitHub

Details

Skill name
challenge-that
Path
challenge-that/SKILL.md
Repo updated
24 March 2026

FAQ

What does the Challenge That skill do?

Force critical evaluation of proposals, requirements, or decisions by analyzing from multiple adversarial perspectives. Triggers on: accepting a proposal without pushback, 'sounds good', 'let's go with', design decisions with unstated tradeoffs, unchallenged assumptions, premature consensus. Invoke with /challenge-that.

How do I install the Challenge That skill?

Claude Code plugin: /plugin marketplace add NTCoding/claude-skillz. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Challenge That popular?

It lives in NTCoding/claude-skillz, which has 365 GitHub stars and 47 forks.

Related skills

Architect Refine Critique

365

NTCoding/claude-skillz

Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design.

Software Development47

Concise Output

365

NTCoding/claude-skillz

Enforces brevity and signal-over-noise in all outputs. Eliminates verbose explanations, filler phrases, and unnecessary elaboration. Triggers on: every response (governs output length and density when loaded).

Other47

Confidence Honesty

365

NTCoding/claude-skillz

Force honest confidence assessment before claiming conclusions. Triggers on 'root cause identified', 'problem identified', 'complete clarity'. Express confidence as percentage, explain what's stopping 100%, validate assumptions before presenting.

Other47

Design Doc Mermaid

186

SpillwaveSolutions/design-doc-mermaid

Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code. Default for GitHub wiki. Use when asked to create a diagram, generate mermaid, document architecture, or convert code to diagram. PlantUML is only for leftover types. Confluence needs PNG/SVG as well as the fence.

Software Development24

Dspy Fundamentals

280

intertwine/dspy-agent-skills

Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought, and save/load. Use this when starting any new DSPy project or when fixing non-idiomatic DSPy code (hard-coded prompts, ad-hoc string templates, untyped outputs, non-serializable classes).

Software Development24

Codebase Cleanup Tech Debt

514

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

Software Development146

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.