aris-rebuttal

Drafts grounded, venue-compliant rebuttals responding to external peer reviews.

1.1k|116|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-rebuttal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aris-rebuttal
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/aris-rebuttal
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-rebuttal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Responding to peer reviews after paper submission is stressful and error-prone: authors must cover every reviewer concern, stay within strict character limits, avoid fabricating evidence, and never overpromise. This Skill structures the entire rebuttal pipeline so no issue is dropped and every claim is grounded.

Core Features & Use Cases

  • Review Atomization and Strategy Planning: Parses raw reviews into an issue board with severity, stance, and response mode per concern, then builds a strategy plan with a character budget.
  • Safety-Gated Drafting: Enforces provenance, commitment, and coverage gates so no fabricated evidence, unapproved promises, or unanswered concerns reach the final rebuttal.
  • Stress Testing and Follow-Ups: Runs a Codex MCP critique round, produces a paste-ready text file plus an extended rich draft, and manages delta replies for follow-up reviewer rounds.
  • Use Case: After receiving three ICML reviews on OpenReview, invoke the Skill with your paper and review bundle to get an issue board, a strategy plan, and a character-limited rebuttal ready to paste.

Quick Start

Run the rebuttal workflow on my paper directory and the pasted ICML reviews to produce a paste-ready response within the venue character limit.

Frequently Asked Questions about aris-rebuttal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a rebuttal for ICML reviews?

Provide your paper source, raw reviews, and venue rules, then the workflow atomizes each reviewer concern into an issue board, builds a strategy plan with a character budget, and drafts a per-reviewer response. A paste-ready plain-text version is produced within the venue character limit.

How to respond to OpenReview reviewer comments safely?

The workflow enforces three safety gates: every factual statement needs a provenance source, every promise must be user-approved, and every reviewer concern must be answered or explicitly deferred. A Codex MCP stress test then flags unsupported claims or risky wording before finalizing.

Can the rebuttal workflow run new experiments for reviewers?

Only when AUTO_EXPERIMENT is enabled. It then generates a mini experiment plan and invokes the experiment-bridge workflow, tagging results as user-confirmed evidence. By default it pauses and presents evidence gaps for manual handling instead.

Does the rebuttal skill submit responses to OpenReview or CMT?

No. It does not submit to OpenReview, CMT, or HotCRP, and it does not edit or upload a revised PDF. It produces a paste-ready text file with an exact character count that the author submits manually.

What are the limitations of automated rebuttal drafting?

The workflow never invents experiments, numbers, derivations, or citations, so claims without existing evidence are blocked or narrowed to concessions. It also requires explicit venue rules and character limits before drafting, and follow-up rounds are capped per reviewer thread.