# Nlp Rebuttal > Scenario playbook for answering a SPECIFIC reviewer concern in an NLP/ML/AI rebuttal — 28 concern types (novelty, simple combination, unclear motivation, weak baselines, marginal gains, missing ablations, no significance, data leakage, no human eval, reproducibility, and more), each with a bad-answer anti-pattern and a recommended-answer template. Use when drafting a reply to a concrete review co… - **Type:** Skill - **Install:** `agentstack add skill-yuangao-tum-rebuttal-skills-nlp-rebuttal` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [yuangao-tum](https://agentstack.voostack.com/s/yuangao-tum) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [yuangao-tum](https://github.com/yuangao-tum) - **Source:** https://github.com/yuangao-tum/rebuttal-skills/tree/main/skills/nlp-rebuttal ## Install ```sh agentstack add skill-yuangao-tum-rebuttal-skills-nlp-rebuttal ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # NLP Rebuttal Scenario Playbook Translated and adapted from [MLNLP-World/Paper-Rebuttal-Tips](https://github.com/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](references/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](references/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](references/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 | A single comment often maps to several tips (e.g. "marginal gains and no significance testing" = 14 + 21). Load all matches and merge their strategies into one answer. ## Cross-cutting rules (from the 28 scenarios) - **Act, don't promise** (Tip 12): run the number/analysis now and put it in the rebuttal. "We will add X in the revision" alone convinces nobody. - **Never blame the reviewer** (Tips 4, 9, 10): if they misread, the fix is a clarification plus a pointer to the line, stated neutrally. - **Answer head-on** (Tips 2, 3): name exactly where the difference or novelty lies — motivation, mechanism, role — not just that it exists. - **Evidence over adjectives** (Tips 13-28): every disputed claim gets a table, an ablation, a test, or an honest statement of infeasibility with a scaled-down proxy result (Tip 18). - **Concede real weaknesses gracefully** (Tips 7, 14, 19): bound the claim, show the trend, explain what the paper still establishes. ## Anti-patterns (never do) - Asserting all components are necessary without per-component ablation (Tip 1). - "We are the first to apply X to Y" as the whole novelty defense (Tip 3). - Repeating the introduction as the answer to a motivation question (Tip 5). - "Experiments show it works" as the answer to a theory question (Tip 6). - Calling the setup fair without matching compute/tuning budgets (Tip 15). - Dismissing a metric request instead of adding the metric (Tip 24). ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [yuangao-tum](https://github.com/yuangao-tum) - **Source:** [yuangao-tum/rebuttal-skills](https://github.com/yuangao-tum/rebuttal-skills) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-yuangao-tum-rebuttal-skills-nlp-rebuttal - Seller: https://agentstack.voostack.com/s/yuangao-tum - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.