Acmmm Supplementary logo

Acmmm Supplementary

CommunityPopular
brycewang-stanford
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 double-blind tracks, and pointing to code and data.

Overview

Publisherbrycewang-stanford
RepositoryAwesome-Journal-Skills
Skill nameacmmm-supplementary
Stars
1.2K
Forks
159
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by brycewang-stanford on GitHub. Read the source before you install it.

Installation

Install the Acmmm Supplementary AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/ACM-MM-Skills/skills/acmmm-supplementary
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git /tmp/Awesome-Journal-Skills
mkdir -p .claude/skills
cp -r /tmp/Awesome-Journal-Skills/ACM-MM-Skills/skills/acmmm-supplementary .claude/skills/acmmm-supplementary
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acmmm Supplementary in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Acmmm Supplementary on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Acmmm Supplementary is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.

ContentBodySupplement
Core claim, main results table, teaserYes—
The two or three decisive media examplesYes (stills/short)Full clips
Extra qualitative media across conditions—Yes
Full user-study protocol and per-rater dataSummary onlyYes
Hyperparameters, extra ablations, proofsPointer onlyYes
Code / data pointersNamedYes

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.

text
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

AssetSafe choiceAvoid
VideoH.264/MP4, standard resolutionExotic/proprietary codecs, 4K walls of clips
AudioWAV or MP3, labeledUnlabeled waveforms, lossless dumps for size's sake
Interactive demoRecorded MP4 fallback + optional codeAssuming the reviewer runs your app
AppendixPDF, same template familyA 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

text
[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>

Frequently asked questions

What does the Acmmm Supplementary AI skill do?

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.

Why use Acmmm Supplementary on TypingMind?

Because you install it once and use it with any model. Acmmm Supplementary is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Acmmm Supplementary in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/ACM-MM-Skills/skills/acmmm-supplementary. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Acmmm Supplementary?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Acmmm Supplementary?

As many as you like. As long as a model supports skills, you can use Acmmm Supplementary with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Acmmm Supplementary AI skill free?

Yes. It is published on GitHub by brycewang-stanford under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇