/acmmm-author-response
Use when drafting the ACM MM (ACM Multimedia) rebuttal — turning multiple anonymous reviews into one focused, anonymous response that fixes factual errors first, adds small confirmatory cross-modal results, concedes calibratedly, and stays inside policy (anonymous, no new
$ npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill acmmm-author-response --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/acmmm-author-response
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when drafting the ACM MM (ACM Multimedia) rebuttal — turning multiple anonymous reviews into one focused, anonymous response that fixes factual errors first, adds small confirmatory cross-modal results, concedes calibratedly, and stays inside policy (anonymous, no new
SKILL.md
acmmm-author-response.SKILL.mdname: acmmm-author-response
description: Use when drafting the ACM MM (ACM Multimedia) rebuttal — turning multiple anonymous reviews into one focused, anonymous response that fixes factual errors first, adds small confirmatory cross-modal results, concedes calibratedly, and stays inside policy (anonymous, no new external links), written for the area chair who decides.
ACM MM Author Response
Use this to write the ACM Multimedia rebuttal. It is **optional and anonymous**, it must not add new external links, and its real audience is the **area chair** who will weigh it against the reviews in discussion.
Triage before writing
Sort every review point into one of three buckets:
| Bucket | Example | Response | |---|---|---| | Factual error | "No ablation of the fusion" (there is one, in §4.3) | Point to it precisely; this is your strongest move | | Fixable gap | "Missing a late-fusion baseline" | Add the small result if you can run it in time | | Judgment call | "The delta is incremental" | Reframe the significance briefly, or concede narrowly |
Lead with the factual corrections — they are the points an AC can verify and act on fastest.
Structure for the AC
Write for a reader who is skimming several rebuttals. Make it navigable:
[R1, R2 shared concern: fusion not shown to matter]
-> Table A (new): leave-one-modality-out; audio-text term = +X of the +Y total gain.
[R1 factual: "no user study"]
-> §5 reports a user study, N raters, agreement kappa; see supplement S3.
[R3 judgment: "incremental over late fusion"]
-> Our gain over the late-fusion baseline is in Table 1; the mechanism (Table A) is the novelty.
[R2 request: clarify synchronization assumption]
-> Conceded; we will state it explicitly in §3 (one sentence).
Group shared concerns once; do not repeat the same answer per reviewer.
Small confirmatory results
- Add only results you can actually produce before the deadline — a leave-one-modality-out
ablation, one requested baseline, or a small user-study extension.
- Describe new numbers in text/tables **inside** the rebuttal; you cannot add a link to an
external file, and you cannot add pages to the paper.
- Do not promise experiments you cannot show; an AC discounts unbacked promises.
Calibrated concessions
Conceding a fair minor point *raises* credibility on the points you contest. State clearly what you will change (a sentence, a clarified assumption, a moved figure) and why the core claim survives it.
Policy guardrails
Anonymous: no author names, institutions, or identifying links.
No new external links: results go in the rebuttal text/tables, not a URL.
No scope change: you cannot rewrite the contribution or add pages.
No reviewer-targeting: never argue a reviewer is unqualified or try to identify them.
Length and format discipline
- Keep the rebuttal tight and scannable; an AC reading many responses rewards structure over
volume, and a wall of text buries your best point.
- Put new evidence in a small **in-line table**, not prose — a reviewer can check a table in
seconds.
- Respect any length limit the cycle sets, and do not try to smuggle in a link to sidestep it.
Rebuttal skeleton by review type
Strong-reject-on-a-misreading: correct the fact FIRST, with an exact section/figure pointer.
Borderline-wants-a-baseline: add the baseline in a mini-table; state it is now in the paper plan.
"Fusion is incremental": show the mechanism ablation (the term that carries the gain).
"Subjective claim unproven": report the user study's N, agreement, and result inline.
Fair-minor-point: concede in one sentence and say exactly what changes.
Tone
Precise and non-defensive. Address the reviewer's underlying concern, not their wording; a rebuttal that reads as annoyed helps the negative reviewer more than you.
Output format
[Factual corrections] <ordered, with exact pointers>
[New results] <ablation/baseline/study added in-rebuttal>
[Concessions] <narrow, with the fix>
[Contested] <judgment points, reframed>
[Policy check] anonymous / no new links / no scope change — pass or fix
Read more
name: acmmm-author-response description: Use when drafting the ACM MM (ACM Multimedia) rebuttal — turning multiple anonymous reviews into one focused, anonymous response that fixes factual errors first, adds small confirmatory cross-modal results, concedes calibratedly, and stays inside policy (anonymous, no new external links), written for the area chair who decides.
ACM MM Author Response
Use this to write the ACM Multimedia rebuttal. It is **optional and anonymous**, it must not add new external links, and its real audience is the **area chair** who will weigh it against the reviews in discussion.
Triage before writing
Sort every review point into one of three buckets:
| Bucket | Example | Response | |---|---|---| | Factual error | "No ablation of the fusion" (there is one, in §4.3) | Point to it precisely; this is your strongest move | | Fixable gap | "Missing a late-fusion baseline" | Add the small result if you can run it in time | | Judgment call | "The delta is incremental" | Reframe the significance briefly, or concede narrowly |
Lead with the factual corrections — they are the points an AC can verify and act on fastest.
Structure for the AC
Write for a reader who is skimming several rebuttals. Make it navigable:
[R1, R2 shared concern: fusion not shown to matter] -> Table A (new): leave-one-modality-out; audio-text term = +X of the +Y total gain. [R1 factual: "no user study"] -> §5 reports a user study, N raters, agreement kappa; see supplement S3. [R3 judgment: "incremental over late fusion"] -> Our gain over the late-fusion baseline is in Table 1; the mechanism (Table A) is the novelty. [R2 request: clarify synchronization assumption] -> Conceded; we will state it explicitly in §3 (one sentence).
Group shared concerns once; do not repeat the same answer per reviewer.
Small confirmatory results
- Add only results you can actually produce before the deadline — a leave-one-modality-out
ablation, one requested baseline, or a small user-study extension.
- Describe new numbers in text/tables **inside** the rebuttal; you cannot add a link to an
external file, and you cannot add pages to the paper.
- Do not promise experiments you cannot show; an AC discounts unbacked promises.
Calibrated concessions
Conceding a fair minor point *raises* credibility on the points you contest. State clearly what you will change (a sentence, a clarified assumption, a moved figure) and why the core claim survives it.
Policy guardrails
Anonymous: no author names, institutions, or identifying links. No new external links: results go in the rebuttal text/tables, not a URL. No scope change: you cannot rewrite the contribution or add pages. No reviewer-targeting: never argue a reviewer is unqualified or try to identify them.
Length and format discipline
- Keep the rebuttal tight and scannable; an AC reading many responses rewards structure over
volume, and a wall of text buries your best point.
- Put new evidence in a small **in-line table**, not prose — a reviewer can check a table in
seconds.
- Respect any length limit the cycle sets, and do not try to smuggle in a link to sidestep it.
Rebuttal skeleton by review type
Strong-reject-on-a-misreading: correct the fact FIRST, with an exact section/figure pointer. Borderline-wants-a-baseline: add the baseline in a mini-table; state it is now in the paper plan. "Fusion is incremental": show the mechanism ablation (the term that carries the gain). "Subjective claim unproven": report the user study's N, agreement, and result inline. Fair-minor-point: concede in one sentence and say exactly what changes.
Tone
Precise and non-defensive. Address the reviewer's underlying concern, not their wording; a rebuttal that reads as annoyed helps the negative reviewer more than you.
Output format
[Factual corrections] <ordered, with exact pointers> [New results] <ablation/baseline/study added in-rebuttal> [Concessions] <narrow, with the fix> [Contested] <judgment points, reframed> [Policy check] anonymous / no new links / no scope change — pass or fix
Stanford REAP × CoPaper.AI · 由斯坦福实证方法论团队精选与维护 访问 copaper.ai 微信:CoPaper.AI 按 11 个主流学科板块覆盖 经管与商科 社会科学 人文学科 数学与物理科学 生命科学 医学与健康 工程与技术 计算机科学与 AI 体育科学 点击任一学科名可跳转到对应说明;每类下的代表子领域在正文总览中完整列出。下方封面墙按 venue 导航,完整分类见覆盖一览。 🧭 布局指南 · 📚 Skill Pack 一览 · ⚡ 如何使用 · 🧪 自动实证
Other skills on awesome-journal-skills.
- /aaai-artifact-evaluation
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
Open skill - /aaai-author-response
Use when drafting an AAAI author response (rebuttal) under the single short character-limited author-feedback window, the no-URL rule, no-new-results guidance, AI-generated-review handling, and the AAAI two-phase review process where Phase-2 papers receive one feedback round
Open skill - /aaai-camera-ready
Use when preparing an accepted AAAI paper for camera-ready source submission to AAAI Press, including proceedings page limits, two-column template compliance, copyright transfer, purchased extra technical pages, deanonymization, registration, oral or poster presentation, and
Open skill - /aaai-experiments
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and
Open skill - /aaai-related-work
Use when positioning an AAAI paper's novelty against archival work, contemporaneous arXiv or workshop papers, and AAAI/IJCAI/NeurIPS/ICML/ICLR neighbors across the broad AI scope, while staying inside AAAI's dual-submission and AI-as-source policy constraints and writing a
Open skill - /aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that
Open skill

