/acmmm-supplementary
Use when organizing the ACM MM (ACM Multimedia) supplementary material due after the paper deadline — deciding what belongs in the 6-8 page body versus the supplement, packaging video/audio/interactive demos that render on a reviewer's machine, keeping all assets anonymous for
$ npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill acmmm-supplementary --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-supplementary
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when organizing the ACM MM (ACM Multimedia) supplementary material due after the paper deadline — deciding what belongs in the 6-8 page body versus the supplement, packaging video/audio/interactive demos that render on a reviewer's machine, keeping all assets anonymous for
SKILL.md
acmmm-supplementary.SKILL.mdname: acmmm-supplementary
description: Use when organizing the ACM MM (ACM Multimedia) supplementary material due after the paper deadline — deciding what belongs in the 6-8 page body versus the supplement, packaging video/audio/interactive demos that render on a reviewer's machine, keeping all assets anonymous for double-blind tracks, and pointing to code and data.
ACM MM Supplementary Material
Use this to plan the ACM Multimedia supplement, which has its **own deadline after the paper** (in 2026, April 8 versus the April 1 paper deadline). For a multimedia paper the supplement is not an afterthought — it is where the video, audio, and interactive evidence lives.
Body vs. supplement split
The 6–8 page sigconf body carries the argument; the supplement carries what the argument rests on but cannot fit.
| Content | Body | Supplement | |---|---|---| | Core claim, main results table, teaser | Yes | — | | The two or three decisive media examples | Yes (stills/short) | Full clips | | Extra qualitative media across conditions | — | Yes | | Full user-study protocol and per-rater data | Summary only | Yes | | Hyperparameters, extra ablations, proofs | Pointer only | Yes | | Code / data pointers | Named | Yes |
A reviewer must be able to follow the body **without** the supplement; the supplement then *confirms* rather than *completes* the argument.
Packaging media that actually plays
The single most common ACM MM supplement failure is media a reviewer cannot open.
video: H.264/MP4, standard resolution, plays in a browser/VLC; no exotic codec
audio: WAV or MP3; label each clip with the claim it supports
demo: if interactive, provide a recorded fallback video — do not assume the reviewer runs it
size: keep within the cycle's stated limit; compress rather than omit evidence
index: a short README mapping each file to the paper claim/figure it supports
Anonymity for double-blind tracks
- Strip author names from filenames, EXIF/media metadata, and any on-screen watermark or slate.
- Remove identifying voices/faces of the authors from demo videos where they would reveal
identity, or note that they are incidental.
- Route dataset and code links through an **anonymous mirror**; a personal or lab URL is a leak.
- The Reproducibility, Open Source Software, and Dataset tracks are single-blind and do not need
this — but the main track and Brave New Ideas do.
Make the supplement legible
- Open with a one-paragraph README: what is here, and which paper claim each file supports.
- Order files to follow the paper's sections, not upload order.
- Caption every clip; an unlabeled video is not evidence a reviewer can use.
What reviewers actually open
Reviewers are time-pressed and will not download a 2 GB archive or install a codec. Design for a skim:
- Lead the index with the **two or three clips that decide the paper**, labeled by claim.
- Keep individual files small enough to stream; compress rather than omit.
- Never make the argument depend on a file the reviewer has to run or build — provide a recorded
fallback for any interactive demo.
Format and codec table
| Asset | Safe choice | Avoid | |---|---|---| | Video | H.264/MP4, standard resolution | Exotic/proprietary codecs, 4K walls of clips | | Audio | WAV or MP3, labeled | Unlabeled waveforms, lossless dumps for size's sake | | Interactive demo | Recorded MP4 fallback + optional code | Assuming the reviewer runs your app | | Appendix | PDF, same template family | A zip of loose screenshots |
Timing against the paper deadline
The supplement has its own, later deadline (April 8 vs. April 1 in 2026), which is a chance and a trap: do not defer *all* media to that week, because rendering, compressing, and anonymizing a video library takes longer than expected. Freeze the decisive clips with the paper, and use the extra days for the confirmatory extras, not the core evidence.
Pre-submission checklist
- Every media file opens with common open-source players.
- The index maps each file to a specific figure, table, or claim.
- No author identity in any filename, metadata, watermark, or link (double-blind tracks).
- The body still stands alone if the supplement were removed.
- Total size is within the current cycle's stated cap (待核实 each year).
Output format
[Split] body self-contained / body depends on supplement
[Media playability] all files open / risky: <list>
[Anonymity] clean / leaks: <list>
[Index] each file mapped to a claim / unlabeled: <list>
[Size] within cap / over
[Top fixes] <ordered before the supplement deadline>
Read more
name: acmmm-supplementary description: Use when organizing the ACM MM (ACM Multimedia) supplementary material due after the paper deadline — deciding what belongs in the 6-8 page body versus the supplement, packaging video/audio/interactive demos that render on a reviewer's machine, keeping all assets anonymous for double-blind tracks, and pointing to code and data.
ACM MM Supplementary Material
Use this to plan the ACM Multimedia supplement, which has its **own deadline after the paper** (in 2026, April 8 versus the April 1 paper deadline). For a multimedia paper the supplement is not an afterthought — it is where the video, audio, and interactive evidence lives.
Body vs. supplement split
The 6–8 page sigconf body carries the argument; the supplement carries what the argument rests on but cannot fit.
| Content | Body | Supplement | |---|---|---| | Core claim, main results table, teaser | Yes | — | | The two or three decisive media examples | Yes (stills/short) | Full clips | | Extra qualitative media across conditions | — | Yes | | Full user-study protocol and per-rater data | Summary only | Yes | | Hyperparameters, extra ablations, proofs | Pointer only | Yes | | Code / data pointers | Named | Yes |
A reviewer must be able to follow the body **without** the supplement; the supplement then *confirms* rather than *completes* the argument.
Packaging media that actually plays
The single most common ACM MM supplement failure is media a reviewer cannot open.
video: H.264/MP4, standard resolution, plays in a browser/VLC; no exotic codec audio: WAV or MP3; label each clip with the claim it supports demo: if interactive, provide a recorded fallback video — do not assume the reviewer runs it size: keep within the cycle's stated limit; compress rather than omit evidence index: a short README mapping each file to the paper claim/figure it supports
Anonymity for double-blind tracks
- Strip author names from filenames, EXIF/media metadata, and any on-screen watermark or slate.
- Remove identifying voices/faces of the authors from demo videos where they would reveal
identity, or note that they are incidental.
- Route dataset and code links through an **anonymous mirror**; a personal or lab URL is a leak.
- The Reproducibility, Open Source Software, and Dataset tracks are single-blind and do not need
this — but the main track and Brave New Ideas do.
Make the supplement legible
- Open with a one-paragraph README: what is here, and which paper claim each file supports.
- Order files to follow the paper's sections, not upload order.
- Caption every clip; an unlabeled video is not evidence a reviewer can use.
What reviewers actually open
Reviewers are time-pressed and will not download a 2 GB archive or install a codec. Design for a skim:
- Lead the index with the **two or three clips that decide the paper**, labeled by claim.
- Keep individual files small enough to stream; compress rather than omit.
- Never make the argument depend on a file the reviewer has to run or build — provide a recorded
fallback for any interactive demo.
Format and codec table
| Asset | Safe choice | Avoid | |---|---|---| | Video | H.264/MP4, standard resolution | Exotic/proprietary codecs, 4K walls of clips | | Audio | WAV or MP3, labeled | Unlabeled waveforms, lossless dumps for size's sake | | Interactive demo | Recorded MP4 fallback + optional code | Assuming the reviewer runs your app | | Appendix | PDF, same template family | A zip of loose screenshots |
Timing against the paper deadline
The supplement has its own, later deadline (April 8 vs. April 1 in 2026), which is a chance and a trap: do not defer *all* media to that week, because rendering, compressing, and anonymizing a video library takes longer than expected. Freeze the decisive clips with the paper, and use the extra days for the confirmatory extras, not the core evidence.
Pre-submission checklist
- Every media file opens with common open-source players.
- The index maps each file to a specific figure, table, or claim.
- No author identity in any filename, metadata, watermark, or link (double-blind tracks).
- The body still stands alone if the supplement were removed.
- Total size is within the current cycle's stated cap (待核实 each year).
Output format
[Split] body self-contained / body depends on supplement [Media playability] all files open / risky: <list> [Anonymity] clean / leaks: <list> [Index] each file mapped to a claim / unlabeled: <list> [Size] within cap / over [Top fixes] <ordered before the supplement deadline>
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

