Deliberation Debate Red Teaming

Challenges plans, designs, and decisions from multiple adversarial perspectives to surface blind spots, hidden assumptions, and vulnerabilities before they cause real damage. Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, or when groupthink or confirmation bias may be hiding risks.

200 stars 25 forksSecurity Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill deliberation-debate-red-teaming
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/deliberation-debate-red-teaming ~/.claude/skills/deliberation-debate-red-teaming

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Deliberation, Debate & Red Teaming

## Workflow

Copy this checklist and track your progress:

```
Deliberation & Red Teaming Progress:
- [ ] Step 1: Define the proposal and stakes
- [ ] Step 2: Assign adversarial roles
- [ ] Step 3: Generate critiques and challenges
- [ ] Step 4: Synthesize findings and prioritize risks
- [ ] Step 5: Recommend mitigations and revisions
```

**Step 1: Define the proposal and stakes**

Ask user for the plan/decision to evaluate (specific proposal, not vague idea), stakes (what happens if this fails), current confidence level (how certain are they), and deadline (when must decision be made). Understanding stakes helps calibrate critique intensity. See [Scoping Questions](#scoping-questions).

**Step 2: Assign adversarial roles**

Identify critical perspectives that could expose blind spots. Choose 3-5 roles based on proposal type (security, legal, operations, customer, competitor, etc.). Each role has different incentives and concerns. See [Adversarial Role Types](#adversarial-role-types) and [resources/template.md](resources/template.md) for role assignment guidance.

**Step 3: Generate critiques and challenges**

For each role, generate specific critiques: What could go wrong? What assumptions are questionable? What edge cases break this? Be adversarial but realistic (steelman, not strawman arguments). For advanced critique techniques → See [resources/methodology.md](resources/methodology.md) for red team attack patterns.
Read the full skill on GitHub

Details

Skill name
deliberation-debate-red-teaming
Path
skills/deliberation-debate-red-teaming/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Deliberation Debate Red Teaming skill do?

Challenges plans, designs, and decisions from multiple adversarial perspectives to surface blind spots, hidden assumptions, and vulnerabilities before they cause real damage. Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, or when groupthink or confirmation bias may be hiding risks.

How do I install the Deliberation Debate Red Teaming skill?

Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Deliberation Debate Red Teaming popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/claude

Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.

Testing & QA25

Academic Letter Architect

200

lyndonkl/claude

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Research & Science25

Adr Architecture

200

lyndonkl/claude

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Software Development25

Dependency Updater

213

TerminalSkills/skills

Audit project dependencies for outdated packages, security vulnerabilities, and breaking changes. Use when someone asks to "check for outdated packages", "audit dependencies", "find vulnerable dependencies", "plan dependency upgrades", "detect breaking changes", or "update npm packages safely". Analyzes package.json/lock files, cross-references changelogs, and produces ordered upgrade plans.

Security34

Conf Preference Elicitation

200

lyndonkl/claude

Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it

Security25

Dns Record Analyzer

213

TerminalSkills/skills

Audits and troubleshoots DNS records for domains including A, AAAA, CNAME, MX, TXT, SPF, DKIM, DMARC, CAA, and NS records. Use when someone needs to verify DNS configuration, debug DNS propagation issues, check email authentication records, or audit domain security. Trigger words: DNS records, dig, nslookup, SPF, DKIM, DMARC, MX records, DNS propagation, nameservers, CAA, domain configuration.

Security34

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.