Ada Devils Advocate — Testing & QA agent for Claude Code
Use for a rigorous adversarial second opinion - stress-test a decision, design, or plan, poke holes, weigh trade-offs, or score outputs as LLM-as-a-judge.
How to install Ada Devils Advocate
Installs to ~/.claude/agents/bigbenjoman-desk-skills-ada-devils-advocate.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bigbenjoman/desk-skills/HEAD/agents/ada-devils-advocate.md -o ~/.claude/agents/bigbenjoman-desk-skills-ada-devils-advocate.md Restart Claude Code, or start a new session, for it to be picked up.
What Ada Devils Advocate does
name: ada-devils-advocate description: "Use for a rigorous adversarial second opinion - stress-test a decision, design, or plan, poke holes, weigh trade-offs, or score outputs as LLM-as-a-judge. Trigger on 'devil's advocate', 'challenge this', 'second opinion', 'poke holes', or 'judge/score this'." model: opus color: red memory: user
You are Ada, a ruthlessly analytical devil's advocate and LLM-as-a-Judge. Named after Ada Lovelace — you combine rigorous logic with creative contrarianism
Alternatives in Testing & QA
- Testing Expert — Use this agent for Output.ai testing strategies including Vitest configuration, Temporal workflow testing, LLM 434 ★
- Provider Tester — Use this agent when you need to test, debug, or validate LLM provider configurations 175 ★
- Critical Thinking — Critical thinking mode that challenges assumptions and probes reasoning 100 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Council Devil
Council seat (standard tier): devil's advocate. Attacks a plan, draft, template or motion standard before it i
Iron Man
System architect that writes technical specs, designs architecture, creates ADRs, and evaluates design trade-o
Crav1 Review Architecture Agent
Subagent. Independent architecture critic for idea bundles, diagrams, and ADRs. Use after ideas-to-spec drafts
AI Prompt Architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/decisions/ADR-{
AI Agent Eval Writer
Use this agent when you need to write evaluation tests for AI agents using Evalite or Autoevals frameworks. Th
Spec Kit Partner
A truly conversational, adaptive, and agentic subagent that partners with humans to co-create rigorous, multi-
Related Skills
Challenge Assumptions
Stress-test assumptions with Devil's Advocate
Gut
Stress-test an idea before committing to it. Blunt devil's advocate.
Devils Advocate
REQUIRED after completing ANY spec or plan. You MUST challenge assumptions — unchallenged plans fail in produc