critical-debater-suite

Multi-agent adversarial debate system with 4 roles (Pro, Con, Judge, Orchestrator), per-round evidence refresh, 5-element reasoning chains, and structured bilingual Markdown report output. Use this skill when the user says "debate", "start a debate", "red team this", "analyze from multiple perspectives", or provides a topic for critical examination.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "critical-debater-suite" with this command: npx skills add xwxga/critical-debater

Critical Debater Suite — Routing

When a user request matches this skill, route to the appropriate capability module.

Intent → Capability Routing

User IntentRoute To
"debate", "start a debate", "red team this", "analyze from multiple perspectives", full topic for debatecapabilities/debate.md
"search evidence", "build evidence store", "find sources"capabilities/source-ingest.md
"check freshness", "update evidence status"capabilities/freshness-check.md
"verify evidence", "cross-check sources"capabilities/evidence-verify.md
"build arguments", "construct debate turn"capabilities/debate-turn.md
"judge round", "audit round", "evaluate arguments"capabilities/judge-audit.md
"update claims", "claim ledger"capabilities/claim-ledger-update.md
"check analogy", "validate historical reference"capabilities/analogy-safeguard.md
"final report", "synthesis", "generate report"capabilities/final-synthesis.md
Mixed requestPick primary intent, chain capabilities in required order

Generic Tool Names

Use provider-agnostic names in all capability prompts:

Generic NameClaude CodeCodexGPT/OpenClaw
searchWebSearchweb_searchweb_search
fetchWebFetch-browse
spawn_roleAgentsubprocess-
readReadreadread
writeWritewritewrite

Model Tiers

TierDescription
fastCheapest, simple tasks
balancedGood reasoning at reasonable cost
deepBest reasoning, verification, causal audit

Fallback Chains

  • search: native → adapter → evidence_gap soft-failure
  • fetch: native → adapter → fetch_skipped soft-failure
  • spawn_role: native → adapter → serial role emulation

Data Contracts

All JSON schemas are defined in references/data-contracts.md. This is the single source of truth for all agent outputs.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Structured Multi-Agent Deliberation

Provides a structured multi-agent deliberation framework with role schemas (action/guardian/observer/critic), verification protocols, and stopping criteria....

Registry SourceRecently Updated
460Profile unavailable
Automation

MARL — Multi-stage Reasoning Middleware

Multi-stage multi-agent reasoning middleware that reduces LLM hallucination by 70%+. 9 specialized emergence engines for invention, creative, pharma, genomic...

Registry SourceRecently Updated
3926Profile unavailable
Automation

Multi-Agent Debate

Verify facts, reduce hallucinations, and explore multiple viewpoints through structured multi-agent debate. Multiple agents independently answer the same que...

Registry SourceRecently Updated
1140Profile unavailable
Research

Akashic Report Generator

Generate comprehensive reports on any topic using multi-agent AI collaboration. Supports market analysis, technical evaluation, strategy reports, and more.

Registry SourceRecently Updated
1040Profile unavailable