From devils-advocate
Set up devil's advocate persona and fact repository for a target document. Use when starting a new critical analysis. Builds the devil persona (role, biases, triggers) and harvests verified facts from source materials.
How this skill is triggered — by the user, by Claude, or both
Slash command
/devils-advocate:setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Build persona and fact repository. Always first step.
Build persona and fact repository. Always first step.
MANDATORY: Use TaskCreate/TaskUpdate for identifying target, building persona, harvesting facts. Mark in_progress/completed.
devils_advocate.md - persona definitionfact_repository.md - verified claimsPlace alongside target document.
Ask user which document. Read in full.
MANDATORY: Persona BEFORE concerns.
Seed document (evaluation, review) alongside target. Infer persona from tone, priorities. Confirm with user.
Ask ALL in ONE message:
"Describe the toughest reader for this document:
MUST ask. Never proceed with generic concerns. One message:
"No persona provided. Either: (a) Describe toughest reader (role, priorities, biases), OR (b) List 2-4 roles and I'll build a composite devil"
For groups: merge priorities (union), harshest bias per persona, weight likelihood by which persona raises each concern.
Write to devils_advocate.md:
# Devil's Advocate - [Project Name]
## The Devil
**Role**: [title and context]
**Cares about**: [2-3 priorities in order]
**Style**: [how they process information]
**Default bias**: [their starting stance]
**Triggers**: [what makes them react negatively]
**Decision**: [what they can do with the document]
**Source**: [seed-inferred / user-described / composite]
---
Scan sources. Extract verifiable claims with sources.
# Fact Repository - [Project Name]
Verified claims sourced from codebase analysis.
No interpretation - just facts.
## Document facts
- [Claim with source reference]
- Source: [document, section/line]
## User-provided facts
- [Fact as stated by user]
- Source: user input
## Data facts
- [Metric or measurement]
- Source: [report, dataset]
Rules:
Tell user: "Persona and fact repository ready. Run /devils-advocate:evaluate for the baseline scorecard."
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub stellarshenson/claude-code-plugins --plugin devils-advocate