← Back to Skills Marketplace
212
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install critical-debater
Description
Multi-agent adversarial debate system with 4 roles (Pro, Con, Judge, Orchestrator), per-round evidence refresh, 5-element reasoning chains, and structured bi...
README (SKILL.md)
Critical Debater Suite — Routing
When a user request matches this skill, route to the appropriate capability module.
Intent → Capability Routing
| User Intent | Route To |
|---|---|
| "debate", "start a debate", "red team this", "analyze from multiple perspectives", full topic for debate | capabilities/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| "check analogy", "validate historical reference" | capabilities/analogy-safeguard.md |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 request | Pick primary intent, chain capabilities in required order |
Generic Tool Names
Use provider-agnostic names in all capability prompts:
| Generic Name | Claude Code | Codex | GPT/OpenClaw |
|---|---|---|---|
search |
WebSearch | web_search | web_search |
fetch |
WebFetch | - | browse |
spawn_role |
Agent | subprocess | - |
read |
Read | read | read |
write |
Write | write | write |
Model Tiers
| Tier | Description |
|---|---|
fast |
Cheapest, simple tasks |
balanced |
Good reasoning at reasonable cost |
deep |
Best reasoning, verification, causal audit |
Fallback Chains
- search: native → adapter →
evidence_gapsoft-failure - fetch: native → adapter →
fetch_skippedsoft-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.
Usage Guidance
This skill appears to be what it says: a debate orchestration suite that searches the web, runs LLM-based verification, and writes structured reports to a workspace. Before installing/running it, consider: (1) run it in an isolated test workspace or sandbox because it will fetch web content and write files; (2) review the local CLIs it will call — the orchestrator looks for 'claude' and 'codex' on PATH and will run them via subprocess; ensure those CLIs are trustworthy or absent if you don't want outbound model calls; (3) the skill requires internet access for searches and fetching—expect data (topic text, prompts, snippets) to leave the host to whatever runtime you use; (4) inspect scripts you rely on (especially validate-json.sh and any omitted files) and the optional cron creation before enabling scheduled refreshes; (5) be aware LLM judgments (freshness, credibility, social-media handling) are intentionally semantic and open-ended — audit outputs and the audit trail to confirm behavior matches your expectations; (6) note a minor metadata inconsistency: registry lists source/homepage as unknown/none while SKILL.md contains a GitHub homepage — if provenance matters, verify upstream source before production use.
Capability Analysis
Type: OpenClaw Skill
Name: critical-debater
Version: 2.0.0
The skill bundle implements a complex multi-agent adversarial debate system. The code and instructions are well-structured and align with the stated purpose of gathering evidence, constructing arguments, and performing judge audits. The scripts (e.g., `init-workspace.sh`, `debate_orchestrator_generic.py`) follow good security practices, such as using Python for safe JSON encoding to prevent shell injection. While the instructions in `capabilities/debate.md` suggest an optional persistence mechanism (creating a cron job for evidence refreshing), this is presented as a user-authorized feature for maintaining data freshness. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description (multi-agent adversarial debate) matches the code and SKILL.md: it reads/writes a debate workspace, ingests web sources, runs judge/audits, and synthesizes reports. It does not request unrelated credentials or system-wide config. It does require internet access and local agent CLIs (claude/codex) which are reasonable for its design.
Instruction Scope
SKILL.md and capability modules explicitly instruct web search/fetch, spawn agent roles, read/write many workspace files (evidence, claims, rounds, reports), and run included scripts. These actions are appropriate for orchestration. Two things to note: (1) LLM-driven judgments (freshness, credibility tiers, verification) are intentionally open-ended and give the agent broad semantic discretion (could produce inconsistent results or over-broad searches); (2) Phase 4 optionally creates a 6-hour cron job if the user agrees — that is persistent system activity and should be approved by the operator.
Install Mechanism
No install spec / no network download at install time; skill is instruction-plus-included scripts. Included scripts are small and straightforward (init, hash, validate, append-audit) and the Python orchestrator runs them. There are no remote installs or archive downloads embedded in the skill package.
Credentials
The skill does not request environment variables, credentials, or access to unrelated config paths. It does expect availability of bash, jq, python3, shasum and network access and will attempt to call local CLIs named 'claude' or 'codex' if present—this is consistent with its purpose but means those CLIs' behavior matters for privacy/security.
Persistence & Privilege
always:false and disable-model-invocation:false (normal). The orchestrator writes files inside its workspace and can (only with user agreement per SKILL.md) create a scheduled 6-hour cron to refresh evidence — that is the only persistence beyond workspace files. The skill does not attempt to modify other skills or global agent configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install critical-debater - After installation, invoke the skill by name or use
/critical-debater - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
Initial v2 release: 4-agent adversarial debate with per-round evidence refresh
Metadata
Frequently Asked Questions
What is 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 bi... It is an AI Agent Skill for Claude Code / OpenClaw, with 212 downloads so far.
How do I install Critical Debater Suite?
Run "/install critical-debater" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Critical Debater Suite free?
Yes, Critical Debater Suite is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Critical Debater Suite support?
Critical Debater Suite is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Critical Debater Suite?
It is built and maintained by xwxga (@xwxga); the current version is v2.0.0.
More Skills