ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

debate-research

Multi-perspective structured debate for complex topics. Spawn parallel subagents with opposing stances, cross-inject arguments for rebuttal, then synthesize via neutral judge into a consensus report with recommendations and scenario matrix. Use when: (1) user asks for deep comparison, pros/cons, or X vs Y analysis, (2) user asks for multi-angle research on a controversial or complex topic, (3) user explicitly requests debate, dialectical analysis, or adversarial research. NOT for: simple factual lookups, single-perspective deep research (use academic-deep-research), or quick opinion questions.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/caius-kong/debate-research
Or

Debate Research

Input Parameters

Collect from user before starting. Only topic is required; all others have defaults.

ParamRequiredDefaultDescription
topicyesDebate subject
rolesnoProponent + Opponent2-4 role objects: {name, stance, model?}. Default: Proponent (argue for) and Opponent (argue against). Model inherits from global.
goalnoinferredWhat question to answer
audienceno"self"Who reads the report: self / team / public
decision_typeno"personal-choice"personal-choice / team-standardization / market-analysis
evidence_roundno"auto"false / true / auto (enable when topic is fact-dense)
confirm_plannotrueShow plan and wait for user OK before execution
modelnoinheritGlobal subagent model; role-level override takes priority
output_pathnonullFile path for report; null = return in conversation

Implicit parameter: language — inferred from the user's topic/conversation language. All subagent prompts output in this language.

Example User Prompt

  • Claude Code vs OpenCode (gpt-5.4, claude-4.6-sonnet)

Execution Pipeline

Phase 0 — Pre-flight

Step 0a: Model reachability check

Collect all unique models (global + per-role + judge). For each unique model, probe via sessions_spawn with a minimal one-sentence task (e.g. "Reply OK") and model: <target>. Do NOT use curl or external HTTP — all models route through OpenClaw's provider config.

If any probe fails:

  • If user explicitly specified the failed model → abort, report failure, suggest alternatives
  • If model was default-assigned → warn user, fall back to session default model, continue

Step 0b: Plan presentation (if confirm_plan: true)

Present to user:

  • Topic
  • Role × model assignment table
  • Evidence round: on/off/auto (with rationale if auto)
  • Estimated subagent call count
  • Goal / audience / decision_type interpretation

[STOP — wait for user confirmation]

If confirm_plan: false, skip directly to Phase 1.

Phase 1 — Stance Investigation (parallel)

Spawn one subagent per role, all in parallel.

Each agent receives a prompt built from:

  • Role name + stance
  • Topic
  • web_search: enabled

Required output format per agent:

Core arguments (3-5):
  - [argument] | confidence: 0.0-1.0 | source: [official-docs/community-feedback/personal-blog/academic-paper]
Opponent weaknesses (2-3)
Predicted counter-attacks (1-2)

Use sessions_spawn + sessions_yield to wait for all completions.

Error handling:

  • Agent timeout → mark output [INCOMPLETE], continue pipeline

Phase 2 — Cross Rebuttal (parallel)

Spawn one subagent per role, all in parallel.

Each agent receives:

  • Its original stance
  • All other roles' Phase 1 output (cross-injected)
  • web_search: disabled

Metadata

Stars4097
Views0
Updated2026-04-14
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-caius-kong-debate-research": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.