home / skills / danielmiessler / personal_ai_infrastructure / redteam

This skill conducts parallel adversarial analysis with 32 perspectives to synthesize steelman arguments and strong refutations for robustness.

npx playbooks add skill danielmiessler/personal_ai_infrastructure --skill redteam

Review the files below or copy the command above to add this skill to your agents.

Files (5)
SKILL.md
3.2 KB
---
name: RedTeam
description: Adversarial analysis with 32 agents. USE WHEN red team, attack idea, counterarguments, critique, stress test. SkillSearch('redteam') for docs.
---

## Customization

**Before executing, check for user customizations at:**
`~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/RedTeam/`

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

# RedTeam Skill

Military-grade adversarial analysis using parallel agent deployment. Breaks arguments into atomic components, attacks from 32 expert perspectives (engineers, architects, pentesters, interns), synthesizes findings, and produces devastating counter-arguments with steelman representations.


## Voice Notification

**When executing a workflow, do BOTH:**

1. **Send voice notification**:
   ```bash
   curl -s -X POST http://localhost:8888/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow from the RedTeam skill"}' \
     > /dev/null 2>&1 &
   ```

2. **Output text notification**:
   ```
   Running the **WorkflowName** workflow from the **RedTeam** skill...
   ```

**Full documentation:** `~/.claude/skills/CORE/SkillNotifications.md`

## Workflow Routing

Route to the appropriate workflow based on the request.

**When executing a workflow, output this notification directly:**

```
Running the **WorkflowName** workflow from the **RedTeam** skill...
```

| Trigger | Workflow |
|---------|----------|
| Red team analysis (stress-test existing content) | `Workflows/ParallelAnalysis.md` |
| Adversarial validation (produce new content via competition) | `Workflows/AdversarialValidation.md` |

---

## Quick Reference

| Workflow | Purpose | Output |
|----------|---------|--------|
| **ParallelAnalysis** | Stress-test existing content | Steelman + Counter-argument (8-points each) |
| **AdversarialValidation** | Produce new content via competition | Synthesized solution from competing proposals |

**The Five-Phase Protocol (ParallelAnalysis):**
1. **Decomposition** - Break into 24 atomic claims
2. **Parallel Analysis** - 32 agents examine strengths AND weaknesses
3. **Synthesis** - Identify convergent insights
4. **Steelman** - Strongest version of the argument
5. **Counter-Argument** - Strongest rebuttal

---

## Context Files

- `Philosophy.md` - Core philosophy, success criteria, agent types
- `Integration.md` - Skill integration, FirstPrinciples usage, output format

---

## Examples

**Attack an architecture proposal:**
```
User: "red team this microservices migration plan"
--> Workflows/ParallelAnalysis.md
--> Returns steelman + devastating counter-argument (8 points each)
```

**Devil's advocate on a business decision:**
```
User: "poke holes in my plan to raise prices 20%"
--> Workflows/ParallelAnalysis.md
--> Surfaces the ONE core issue that could collapse the plan
```

**Adversarial validation for content:**
```
User: "battle of bots - which approach is better for this feature?"
--> Workflows/AdversarialValidation.md
--> Synthesizes best solution from competing ideas
```

---

**Last Updated:** 2025-12-20

Overview

This skill performs military-grade adversarial analysis using a 32-agent ensemble to stress-test arguments, designs, and decisions. It decomposes input into atomic claims, runs parallel adversarial inspection, synthesizes convergent insights, and returns both a steelman and a forceful counter-argument. The output highlights the most critical failure modes and actionable mitigation ideas.

How this skill works

The workflow first decomposes the target into atomic components and assigns 32 specialized agents to examine strengths and weaknesses in parallel. Agents cover perspectives such as engineers, architects, pentesters, product, and junior reviewers. A synthesis step identifies convergent findings, then the skill produces an optimized steelman (strongest framing) and a prioritized counter-argument (deepest rebuttal) for each key point.

When to use it

  • Stress-test architecture proposals, security designs, or migration plans
  • Critique business decisions, pricing changes, or go-to-market strategies
  • Surface hidden failure modes before launch or funding reviews
  • Run adversarial validation to compare competing proposals
  • Prepare rebuttals and counterpoints for debates or stakeholder meetings

Best practices

  • Provide the full context, goals, and constraints up front to focus the analysis
  • Supply diagrams, excerpts, or short briefs so decomposition yields accurate atomic claims
  • Specify which perspective weightings matter (security, cost, speed, UX) if you care about trade-offs
  • Request an emphasis on mitigation steps if you need actionable fixes, not just criticism
  • Allow time for the full ParallelAnalysis workflow to run; it yields richer synthesis than a single-pass review

Example use cases

  • Red-team a microservices migration plan to reveal the one failure mode that could collapse the project
  • Critique a proposed 20% price increase and surface the single vulnerability that undermines adoption
  • Run a battle-of-bots adversarial validation to synthesize the strongest implementation approach from competing proposals
  • Use the steelman+counter-argument output to prepare investor Q&A or board briefing materials

FAQ

How long does a typical analysis take?

Complex inputs with detailed context typically take longer; expect richer parallel analyses to need more processing time than a quick critique. Provide concise inputs for faster runs.

Can I customize agent priorities or preferences?

Yes. You can specify perspective weightings and priorities in your request so the ensemble emphasizes security, cost, UX, or other trade-offs.

What output formats are produced?

The skill returns a decomposed claim list, synthesized convergent findings, an 8-point steelman per major claim, and an 8-point counter-argument with prioritized mitigations.