debate
Multi-model adversarial debate where Claude defends positions against external CLI models (Gemini, Codex, Qwen). Use when facing complex decisions, wanting to expose blind spots, or needing documented reasoning for tradeoffs. Auto-triggers: "debate this", "challenge my thinking", "what am I missing", "devil's advocate", "stress test this idea", "poke holes", "second opinion", "validate this decision", "am I wrong about"
What this skill does
# Debate System ## What This Does Claude forms a position, then external AI models (Gemini, Codex, Qwen) challenge it through structured adversarial debate. Claude must defend, update, or synthesize based on valid critiques. **This is NOT Claude debating itself.** Different models = different training = different blind spots = genuine value. ## Requirements **Minimum: 1 external CLI installed and authenticated.** Run `/debate:doctor` to check system health. Supported CLIs: - `gemini` - @google/gemini-cli (free: 1000 req/day) - `codex` - @openai/codex (requires ChatGPT Plus) - `qwen` - @qwen-code/qwen-code (free: 2000 req/day) **Refuses to run with Claude-only.** Claude debating itself is theater, not debate. ## Commands | Command | Purpose | |---------|---------| | `/debate <topic>` | Full adversarial debate on any topic | | `/debate:doctor` | Check CLI health and authentication | | `/debate:adr <topic>` | Debate with formal ADR output for important decisions | ## The Hybrid Protocol 1. **Claude forms position** on the topic 2. **Parallel challenge** - All external models critique simultaneously 3. **Consensus check** - If all agree → fast exit 4. **Sequential confrontation** - If disagreement, models respond to each other 5. **Iterate** until consensus OR max rounds 6. **Assumption extraction** - Surface WHY positions differ 7. **Output** - Consensus OR structured tradeoff document ## When To Use - Complex decisions with no obvious answer - Suspecting blind spots in your thinking - Needing documented reasoning for team/future reference - Wanting genuine pushback, not "yes-man" AI - Architecture decisions, strategy, any high-stakes choice ## The Core Value **Disagreement is signal, not failure.** When models can't agree, the output isn't "we failed" - it's a structured tradeoff document exposing: - What each option assumes - When each option is correct - The hidden assumptions causing the split This transforms "who's right?" into "what would have to be true for each to be right?" ## Settings Configure in `~/.claude/debate.local.md`: ```yaml --- max_rounds: 5 timeout_per_cli: 120 save_debate_logs: true debate_log_path: "./debate-logs" adr_path: "./docs/decisions" skeptical_of_early_agreement: true --- ``` ## Universal Application Works for ANY decision: - Code architecture - Business strategy - Product features - Technical tradeoffs - Writing and content - Life decisions The protocol adapts to domain automatically.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.