← Back to Skills Marketplace
Multi Model Critique
by
prairiedoggg
· GitHub ↗
· v1.0.1
378
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install multi-model-critique
Description
Use multiple models in a 4-step cycle of drafting, cross-critique, revision, and synthesis to generate higher-quality answers for complex, high-stakes queries.
Usage Guidance
This skill appears to do what it says: orchestrate multiple ACP models through draft → critique → revision → synthesis. Before using it, confirm that you trust the ACP agentIds you will include (the workflow sends user content to all listed models), and ensure the run-time will not point output files to sensitive system locations. Note the templates default to Korean unless overridden. There are no requested credentials or external downloads in the package. If you will run the helper scripts locally, inspect the output directory arguments you provide and ensure the platform's sessions_spawn / sessions_send privileges are granted only to models you trust.
Capability Analysis
Type: OpenClaw Skill
Name: multi-model-critique
Version: 1.0.1
This skill bundle implements a multi-model critique workflow with strong, explicit prompt injection mitigations. The Python scripts (`scripts/build_round_prompts.py`, `scripts/run_orchestration.py`) validate and normalize user inputs (`question`, `constraints`), rejecting known prompt-injection control phrases via `DISALLOWED_PATTERNS` and wrapping user content in explicit data blocks with untrusted content warnings. The `SKILL.md` and `references/orchestration-template.md` instruct the OpenClaw agent to use legitimate internal tools (`sessions_spawn`, `sessions_send`, `sessions_history`) for orchestration, without any malicious directives for the agent itself. No evidence of data exfiltration, unauthorized execution, persistence, or obfuscation was found.
Capability Assessment
Purpose & Capability
Name/description (multi-model critique) align with the provided artifacts: orchestration templates, prompt templates, output schema, and two helper scripts. The skill requires resolving ACP agentIds and coordinating multiple models, which matches the stated goal.
Instruction Scope
SKILL.md restricts use to complex=true and describes a bounded 4-round workflow using sessions_spawn/sessions_send/sessions_history for model orchestration. It does not instruct reading unrelated system files or harvesting environment variables. The only potential surprise is a default language preference (Korean) in templates, but that's a functional choice rather than a scope creep.
Install Mechanism
No install spec is provided (instruction-only plus two small local helper scripts). No downloads, package installs, or archive extraction are present. Scripts are local utilities that read/write prompt and plan files.
Credentials
The skill declares no required environment variables, credentials, or config paths. The orchestration relies on platform ACP agentIds (expected for cross-model runs) and does not request unrelated secrets.
Persistence & Privilege
always is false and the skill does not request permanent system presence or attempt to modify other skills. Helper scripts write outputs to user-specified directories only and run_orchestration explicitly states it does not call OpenClaw tools directly.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install multi-model-critique - After installation, invoke the skill by name or use
/multi-model-critique - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Security patch: validate and sanitize untrusted question/constraints inputs, block prompt-injection control phrases, validate model/agent mapping formats, and add runtime guardrails for orchestration plan generation.
v1.0.0
Initial public release: complex=true multi-model orchestration with Plan/Execute/Review/Improve loop, cross-critique rubric scoring, output schema, and run-plan helper.
Metadata
Frequently Asked Questions
What is Multi Model Critique?
Use multiple models in a 4-step cycle of drafting, cross-critique, revision, and synthesis to generate higher-quality answers for complex, high-stakes queries. It is an AI Agent Skill for Claude Code / OpenClaw, with 378 downloads so far.
How do I install Multi Model Critique?
Run "/install multi-model-critique" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Multi Model Critique free?
Yes, Multi Model Critique is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Multi Model Critique support?
Multi Model Critique is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Multi Model Critique?
It is built and maintained by prairiedoggg (@prairiedoggg); the current version is v1.0.1.
More Skills