Is the Advocatus Diaboli skill free?

Yes. The skill itself is free from Habitat-Thinking/ai-literacy-superpowers. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Advocatus Diaboli SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Advocatus Diaboli?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Advocatus Diaboli with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Advocatus Diaboli

Structured adversarial spec review: six objection categories, mandatory evidence, nothing rubber-stamped.

by Habitat-Thinking · Habitat-Thinking/ai-literacy-superpowers

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · cbe0c3d

Ran it against a toy spec ('Delete All notes button, no confirmation, no undo, placed next to New Note'): it produced 5 evidence-quoted objections across 4 categories with severities plus a mandatory 3-item 'explicitly not objecting to' section, versus 4 loose, uncategorized bullets from an unguided critique of the same spec — a concrete, structural improvement, not just more words.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Advocatus Diaboli does

Acts as a devil's-advocate reviewer for specs and plans before implementation begins, raising evidence-quoted objections across six fixed categories (premise, scope, implementation, risk, alternatives, specification quality) with severity ratings and a required disclosure of what it chose not to challenge. Triggers when asked to critically review, poke holes in, or adversarially assess a spec/plan before it's approved; explicitly declines code review, linting, and rewriting.

How to install Advocatus Diaboli

git clone https://github.com/Habitat-Thinking/ai-literacy-superpowers
cd ai-literacy-superpowers
mkdir -p ~/.claude/skills
cp -r ai-literacy-superpowers/skills/advocatus-diaboli ~/.claude/skills/advocatus-diaboli

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Advocatus Diaboli

/advocatus-diaboli Structured adversarial spec review: six objection categories, mandatory evidence, nothing rubber-stamped.

It also activates on plain-language prompts like these:

Poke holes in this spec before we start building the delete button
Adversarially review my plan and list what you're not challenging
Play devil's advocate on this feature spec before implementation

Frequently asked questions

Is the Advocatus Diaboli skill free?: Yes. The skill itself is free from Habitat-Thinking/ai-literacy-superpowers. SkillProof publishes the install command and an independent test verdict at no cost.
Does Advocatus Diaboli work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran it against a toy spec ('Delete All notes button, no confirmation, no undo, placed next to New Note'): it produced 5 evidence-quoted objections across 4 categories with severities plus a mandatory 3-item 'explicitly not objecting to' section, versus 4 loose, uncategorized bullets from an unguided critique of the same spec — a concrete, structural improvement, not just more words.
What is the Advocatus Diaboli SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Advocatus Diaboli?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Advocatus Diaboli with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.