nlp-rebuttal

nlp-rebuttal is a skill for Claude Code from yuangao-tum/rebuttal-skills. It costs 146 tokens per session (1,316 once invoked), scanned A, original, MIT.

A playbook for answering specific peer-review concerns in natural language processing, machine learning, and artificial intelligence papers. It covers 28 recurring concerns and provides answer templates and examples of approaches to avoid.

In plain words
What is it for?
Use it to handle concerns about novelty, baselines, experiments, data leakage, reproducibility, human evaluation, and related issues.
Why use it?
It helps authors respond to difficult reviewer comments with evidence and clear reasoning rather than vague or defensive replies.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rebuttal-skills plugin — 2 skills shipped together

Good fit Use it to handle concerns about novelty, baselines, experiments, data leakage, reproducibility, human evaluation, and related issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuangao-tum/rebuttal-skills/nlp-rebuttal
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yuangao-tum/rebuttal-skills --skill nlp-rebuttal
Clone the repo
git clone --depth 1 https://github.com/yuangao-tum/rebuttal-skills

Made for: Claude Code.

Or install rebuttal-skills, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nlp-rebuttal

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal/github.svg)](https://agentmods.dev/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal)
Your own site
<a href="https://agentmods.dev/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal"><img src="https://agentmods.dev/badge/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nlp-rebuttal

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal"><img src="https://agentmods.dev/badge/skills/yuangao-tum/rebuttal-skills/nlp-rebuttal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00146 $0.01316
Opus 5 $0.00073 $0.00658
Sonnet 5 $0.00029 $0.00263
Haiku 4.5 $0.00015 $0.00132

Measured 12d ago against content hash f3c705525ca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nlp-rebuttal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/nlp-rebuttal/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NLP Rebuttal Scenario Playbook

Translated and adapted from MLNLP-World/Paper-Rebuttal-Tips. 28 recurring reviewer-concern scenarios. Each has four parts: the concern, a bad answer that backfires, a recommended answer template, and the takeaway.

Good rebuttal = Respect + Evidence + Clarity.

How to use

  1. Classify each reviewer comment with the router below.
  2. Load ONLY the reference file(s) for the matched tips.
  3. Adapt the recommended-answer template: replace every placeholder (XXX, A/B/C, Table X) with the paper's real content and freshly computed numbers. Never ship a template verbatim.
  4. For overall response structure, ordering, and tone, use the write-rebuttal skill (itemize → brain-dump → draft → revise, the 18 tactics, the neutral-third-party test). These two skills compose: that one shapes the whole response, this one shapes each answer.

Concern router

Reviewer concern sounds like Tip Reference
"Too complex", "bag of tricks", "which component matters?" 1 innovation-theory.md
"Not novel", "similar to prior work A" 2 innovation-theory.md
"Just a combination of existing techniques" 3 innovation-theory.md
"Contributions unclear" 4 innovation-theory.md
"Motivation unclear", "why is this problem important?" 5 innovation-theory.md
"No theoretical analysis", "why does it work?" 6 innovation-theory.md
"Limitations discussion is superficial" 7 innovation-theory.md
"Related work missing/insufficient" 8 communication-writing.md
"Writing/notation unclear" 9 communication-writing.md
Reviewer misunderstood the method 10 communication-writing.md
Vague, low-quality negative review 11 communication-writing.md
Tempted to reply "we will add..." 12 communication-writing.md
"Missing/weak baselines" 13 experiments-evidence.md
"Improvements are marginal" 14 experiments-evidence.md
"Unfair experimental setup" 15 experiments-evidence.md
"Missing ablations" 16 experiments-evidence.md
"Too much computational overhead" 17 experiments-evidence.md
Asked for experiments too large for the rebuttal window 18 experiments-evidence.md
"Dataset too small" 19 experiments-evidence.md
"Generalization not shown" (few datasets/models/tasks) 20 experiments-evidence.md
"No variance / significance / seeds" 21 experiments-evidence.md
"Possible train/test leakage or contamination" 22 experiments-evidence.md
"Hyperparameter sensitivity?" ("why k=40?") 23 experiments-evidence.md
"Wrong/missing evaluation metrics" 24 experiments-evidence.md
"No human evaluation" 25 experiments-evidence.md
"Intermediate outputs never evaluated directly" 26 experiments-evidence.md
Claims "continual/online" but experiments are one-shot offline 27 experiments-evidence.md
"No code, seeds, or hyperparameters — not reproducible" 28 experiments-evidence.md

Read the full file on GitHub · 85 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 85 lines · 146 tokens per session scan A f3c705525ca7

Subscribe to this mod's changes

nlp-rebuttal is a skill published in the GitHub repository yuangao-tum/rebuttal-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 1,316 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.