rebuttal

Generate venue-compliant rebuttals from reviewer feedback with provenance constraints.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/Shallow-W/llm-wiki --skill rebuttal-shallow-w
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rebuttal
Source: https://github.com/Shallow-W/llm-wiki/tree/main/.claude/skills/rebuttal
Command: npx skills add https://github.com/Shallow-W/llm-wiki --skill rebuttal-shallow-w

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reviews often arrive with multiple, overlapping concerns, and authors need a venue-compliant rebuttal that answers every issue without inventing evidence or making unapproved promises.

Core Features & Use Cases

  • Review-to-issue parsing: Normalizes and atomizes reviewer feedback into an actionable issue board with severity, priority, and response mode targets.
  • Evidence- and commitment-gated safety: Enforces provenance and commitment rules so every factual statement is traceable and every promise is approved.
  • Venue-limit drafting: Produces either a single compliant rebuttal document (shared response) or per-reviewer thread responses that are self-contained.
  • Follow-up round management: Tracks deltas across rebuttal and subsequent rounds with an auditable revision checklist.
  • Optional stress-testing: Uses Codex MCP to identify weak coverage, unsupported claims, tone issues, and backfiring phrasing—without fabricating evidence.

Quick Start

Use the rebuttal skill to draft a text-only ICML rebuttal by providing the paper path or review bundle and the target venue/limits.

Frequently Asked Questions about rebuttal

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

FAQPage Schema
How do I write an ICML rebuttal that addresses all reviewer concerns without exceeding venue limits?

Drafting an ICML rebuttal requires parsing reviewer feedback into atomized issues and generating a venue-compliant response. This process normalizes concerns into an actionable board with severity and priority, then drafts text that respects strict limits and provenance constraints.

What is the best way to manage multiple overlapping concerns in an OpenReview response?

Managing overlapping concerns in an OpenReview response involves atomizing reviewer feedback into distinct issues. Each issue is assigned a response mode and priority, ensuring every factual statement is traceable and every commitment is approved without inventing evidence.

Can I draft separate thread responses for individual reviewers instead of a single shared rebuttal document?

Yes, you can generate per-reviewer thread responses that are self-contained instead of a single shared rebuttal document. The drafting process supports both single-document and per-reviewer thread formats while enforcing coverage and commitment gates.

How do I track changes across multiple rounds of peer review rebuttals?

Tracking changes across multiple rebuttal rounds uses follow-up round management to monitor deltas. It maintains an auditable revision checklist, ensuring subsequent rounds remain compliant and properly address reviewer deltas with safety validation.

How can I stress-test my academic writing rebuttal for weak coverage or unsupported claims?

Stress-testing a rebuttal identifies weak coverage, unsupported claims, tone issues, and backfiring phrasing. This validation process checks the draft against evidence grounding rules to ensure no fabricated evidence is introduced and all claims are properly supported.

What inputs do I need to generate a peer review rebuttal?

Generating a rebuttal requires YAML-defined inputs including the paper path, review bundle, venue rules, and current stage. These inputs enforce provenance and commitment gates to produce paste-ready or thread-ready rebuttal artifacts.