Skip to main content
skill CX Codex

devils-advocate · pedrohcgs — Claude Code skill: what it does, how to install

Challenges lecture decks from a skeptical student's perspective with five to seven targeted critiques on narrative flow and cognitive load.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pedrohcgs/claude-code-my-workflow --skill devils-advocate -a claude-code
Open on GitHub

What devils-advocate does

The skill stress-tests slide decks and lecture notes before class. It looks for gaps in intuition, prerequisite jumps, and confusing notation. The review remains lighter than /pedagogy-review, focusing on where students might get stuck.

The assistant operates strictly read-only using Read, Grep, and Glob. It cannot modify your slides because Edit and MultiEdit tools are blocked. The skill inspects your deck, reads notation rules in .claude/rules/, and checks neighboring lectures for narrative continuity.

The generated report highlights affected slide numbers, severity rankings, and concrete resolution steps. It concludes with an actionable verdict separating essential pre-class changes from optional refinements.

What it helps with

  • catch conflicting mathematical notation across lecture files
  • pinpoint slides carrying too much cognitive load
  • spot missing intuitive examples before formal proofs
  • verify prerequisites and narrative continuity across lectures

Example prompts for the agent

  • Play devil's advocate for lecture-04.md
  • Poke holes in the pedagogical design of ml-foundations.deck
  • What would a skeptical student ask about linear-algebra-recap.md?

How to install devils-advocate

1Skills CLI (Vercel)

npx skills add pedrohcgs/claude-code-my-workflow --skill devils-advocate -a claude-code

2Manually: put the files in place

~/.claude/skills/devils-advocate/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/devils-advocate/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about devils-advocate

How do I install devils-advocate in Claude Code?

Run npx skills add pedrohcgs/claude-code-my-workflow --skill devils-advocate -a claude-code. The skill installs into ~/.claude/skills/devils-advocate/SKILL.md.

Can devils-advocate overwrite presentation files?

No. The skill configuration explicitly disables Edit and MultiEdit, restricting file access to read-only operations.

What categories of challenges does the skill generate?

It targets 5 to 7 specific questions across ordering, prerequisites, notation conflicts, alternative explanations, and cognitive load.

Source text

SKILL.md · MIT
---
name: devils-advocate
description: Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force rethinking. Lighter than `/pedagogy-review`.
argument-hint: "[Lecture filename]"
allowed-tools: ["Read", "Grep", "Glob"]
disallowed-tools: ["Edit", "MultiEdit"]
---

# Devil's Advocate Review

Critically examine a slide deck and challenge its design with 5-7 specific pedagogical questions.

**Philosophy:** "We arrive at the best possible presentation through active dialogue."

---

## Setup

1. **Read the target file** (the lecture being challenged)
2. **Read the knowledge base** in `.claude/rules/` for notation conventions and narrative arc
3. If applicable, **read adjacent lectures** for narrative continuity

---

## Challenge Categories

Generate 5-7 challenges from these categories:

### 1. Ordering Challenges
> "Could students understand this better if we showed X before Y?"

### 2. Prerequisite Challenges
> "Do students have the background for this notation at this point?"

### 3. Gap Challenges
> "Should we include an intuitive example before this formal proof?"

### 4. Alternative Presentation Challenges
> "Here are 2 other ways to visualize/present this concept."

### 5. Notation Conflict Challenges
> "This symbol conflicts with earlier lecture usage."

### 6. Cognitive Load Challenges
> "This slide has too many new symbols. Can we split?"

### 7. Book Vision Challenges
> "If this becomes a book chapter, does this section stand alone?"

---

## Output Format

```markdown
# Devil's Advocate: [Lecture Title]

## Challenges

### Challenge 1: [Category] — [Short title]
**Question:** [The specific pedagogical question]
**Why it matters:** [What could go wrong]
**Suggested resolution:** [Specific action]
**Slides affected:** [Numbers or titles]
**Severity:** [High / Medium / Low]

[Repeat for 5-7 challenges]

## Summary Verdict
**Strengths:** [2-3 things done well]
**Critical changes:** [0-2 changes before teaching]
**Suggested improvements:** [2-3 nice-to-have changes]
```

---

## Principles

- **Be specific:** Reference exact slides and notation
- **Be constructive:** Every challenge has a suggested resolution
- **Be honest:** If the deck is good, say so
- **Prioritize:** Notation conflicts > missed metaphors
- **Think like a student:** Where do they get lost?

© pedrohcgs · MIT · pedrohcgs/claude-code-my-workflow

Similar skills

All skills for Writing and docs →

devils-advocate by other authors comes first.

From the same set56

grant-proposal Turns an existing research spec into a structured grant proposal draft. Use it to prepare an application for NSF, NIH, ERC, or a foundation. CX Codex +1 ★ 1,671repo stars disclosure-check Pre-screens tables, figures, and logs for statistical disclosure risks before export from secure data enclaves. Catches small cell counts, dominance issues, and PII leaks. CX Codex +1 ★ 1,671repo stars differential-audit Audits two implementations of the same logic, tracking differences in outputs, warnings, and failures. Useful for language ports, research replication, refactors, and release checks. CX Codex +1 ★ 1,671repo stars diagnose Walks a failing run from a stable reproduction to a minimal example, ranked hypotheses and a fix. Built for research code. CX Codex +1 ★ 1,671repo stars deploy This skill renders Quarto slides as HTML and syncs the output to docs/ for GitHub Pages. Use it when edited slides are ready to publish. CX Codex +1 ★ 1,671repo stars deep-audit Splits a theory, proof, paper or codebase into components, fans out independent skeptics and fixes every confirmed defect. Built for when one review pass is not enough. CX Codex +1 ★ 1,671repo stars data-management-plan Generates funder-compliant Data Management Plans for NSF, NIH, ERC, and Horizon Europe proposals. Useful when drafting grant applications or planning project data workflows. CX Codex +1 ★ 1,671repo stars data-analysis This skill runs an R analysis workflow from data inspection to regressions and publication-ready tables and figures. Use it when a dataset needs empirical analysis. CX Codex +1 ★ 1,671repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor