Run multi-agent AI sessions using structured thinking methods like Six Thinking Hats, Adversarial Debate, Disney Creative Strategy, Pre-Mortem, TRIZ, Polarity Management, and others to explore problems from diverse perspectives, generate creative solutions, anticipate failures, and perform meta-cognitive checks for biases, framing, and blind spots.
Analogical Transfer — strip a problem to its abstract structure, find distant-domain analogs, transfer operating principles back
Bias Check — surface cognitive biases that make you trust the result too easily
Adversarial Debate — structured multi-round debate with judge verdict
Disney Creative Strategy — Dreamer, Realist, Critic cycle
First Principles Decomposition — separate necessity from convention through recursive 'why' questioning
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Structured thinking methods as multi-agent sessions for Claude Code.
Facilitation techniques from the real world — Six Thinking Hats, Adversarial Debate, Disney Creative Strategy, Pre-Mortem Analysis, Polarity Management, TRIZ, W³, Troika Consulting, Wise Crowds, First Principles Decomposition, Analogical Transfer, Morphological Box, and Futures Cone — each powered by specialized AI agents that take on distinct roles and build on each other's insights. Plus three meta-cognitive modules that reflect on your thinking itself.
No code. No build steps. Just Markdown files that orchestrate multi-agent thinking sessions.
Five perspectives, one at a time. Facts first, then feelings, creativity, opportunities, and risks — in that order. The Blue Hat orchestrator chooses the sequence based on your topic (exploratory, reactive, or cautious) and synthesizes at the end. The separation is the point: mixing perspectives produces muddy thinking, separating them produces clarity.
/libertee:six-hats "Should we adopt a microservices architecture?"
A structured 3-round debate where Pro and Contra must never agree. Each round escalates — opening statements, rebuttals, final arguments — then a Judge delivers the verdict. The agents are instructed to maintain their positions and counter every argument. This prevents the common AI pattern of politely converging and produces genuinely useful tension. Use --personas to cast specific figures into the roles.
/libertee:debate "Remote work is superior to office work"
/libertee:debate "Remote work is superior to office work" --personas "Sherlock Holmes, Dr. Watson"
Three rooms, three mindsets. The Dreamer paints a bold vision without limits. The Realist takes that vision and builds a concrete plan — assuming it IS possible. The Critic stress-tests the plan (not the dream). Disney's genius was separating these modes into different rooms. We separate them into different agents.
/libertee:disney "What if we completely rethought our onboarding?"
"Imagine it failed. Spectacularly. Now tell me why." The Doom Analyst generates vivid failure scenarios, then reality-checks which ones are already showing early signs. The Facilitator turns it into a prevention plan with the uncomfortable truth nobody wants to hear. Research shows prospective hindsight increases risk identification by 30%.
/libertee:pre-mortem "We're launching a new product in Q3"
Not every tension is a problem to solve. Some are polarities to manage — where both sides need each other. Two Pole Advocates each map their pole's upsides AND downsides honestly. The Facilitator synthesizes into a Polarity Map with virtuous cycles, vicious cycles, warning signs, and action steps. Nobody wins. That's the point.
/libertee:polarity "Centralization vs Decentralization"
"What must we do to guarantee the worst possible outcome?" The Saboteur generates creative failure strategies with dark humor, then reality-checks which ones are already happening. Reverse brainstorming at its finest — sometimes the fastest way to improve is to stop making things worse.
/libertee:triz "Our sprint delivery reliability"
Three phases, strictly separated. First: what actually happened? (facts only, no interpretation). Then: what does it mean? (patterns and implications). Finally: what do we do now? (concrete actions). The same Reflector agent runs all three phases — the discipline is in the separation. Most teams jump straight to "Now What?" and wonder why nothing changes.
/libertee:w3 "Our last product launch"
npx claudepluginhub worksystems-design/libertee --plugin liberteeRead, write, and validate DWSD organization entities — the Dynamic Worksystems Design markdown format.
Read and write the DWSD board and flight-route DSLs — syntax reference + minimal examples bundled.
Systems Thinking support for Claude Code — explains and facilitates canonical thinking models (Causal Loop Diagrams, archetypes, more to come). Convergent counterpart to Libertee. Layer 1 (models) and Layer 2 (facilitation) cleanly separated. Co-creates .cld.md artifacts with the user.
A deterministic thinking partner that challenges assumptions and applies 150+ mental models to sharpen decisions, solve problems, and think more clearly. Features orientation detection, cognitive operations framework, and structured diagnostic workflows.
Structured thinking methods that counteract LLM reasoning biases during problem exploration — first principles, inversion, constraint manipulation, perspective forcing, analogy search, and more, with user-gated parallel subagent exploration for deep dives
A structured toolkit of thinking skills for Claude Code — covering logic, ethics, creativity, decision-making, systems thinking, communication, and more. Each skill is an invokable command that applies a specific reasoning framework to any situation.
Cognitive brainstorming protocol for Claude Code. Structures thinking through GROUND (problem discovery) -> EXPLORE (divergent) -> DECIDE (convergent) -> STRESS (stress-test) -> SHIP (artifacts) phases. Includes domain skills for technical architecture and conceptual work.
Multi-perspective council analysis. Spawns parallel cognitive perspectives to analyze questions, plans, and ideas from multiple angles with structured dialectical synthesis.
Truth-seeking sparring partner for Claude Code. Challenges claims, decisions, and documents through structured dialectical analysis.