SkillAgentSearch skills...

acmmm-related-work

Use when building or auditing the related-work section of an ACM MM (ACM Multimedia) paper — covering the multimedia literature spread across vision, audio/speech, language, HCI/QoE, and systems, handling arXiv-speed concurrency, keeping citations double-blind, and verifying that cited "ACM MM paper…

Install / Use

npx skills add brycewang-stanford/Awesome-Journal-Skills --skill acmmm-related-work

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Supported Platforms

Universal

Tags

Our assessment of acmmm-related-work

acmmm-related-work scores 87/100 on our quality scale, 2197th of 4,702 Development & Engineering skills we index (top 47%).

Its SKILL.md is 4.8 KB long, well organised into 10 sections with 3 code examples: a solid amount of guidance for an agent.

With 1,158 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so acmmm-related-work is actively maintained.
  • Our last check on 2026-11-02 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

acmmm-related-work compared with similar skills

All 4 of these similar skills score higher than acmmm-related-work; compare them before choosing.

SkillScoreStarsUpdatedFormat
acmmm-related-work (this skill)by brycewang-stanford871.2k2mo agoSKILL.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.3ktodayCLAUDE.md
claude-howtoby luongnv8910047.4k3d agoCLAUDE.md
lobehubby lobehub10085.7ktodayMCP Server

Frequently asked questions

How do I install acmmm-related-work?
Run npx skills add brycewang-stanford/Awesome-Journal-Skills --skill acmmm-related-work. The install tabs above show the steps for each supported agent.
Which AI agents does acmmm-related-work work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is acmmm-related-work safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is acmmm-related-work still maintained?
The repository was last updated about 2 months ago, so acmmm-related-work is actively maintained.

name: acmmm-related-work description: Use when building or auditing the related-work section of an ACM MM (ACM Multimedia) paper — covering the multimedia literature spread across vision, audio/speech, language, HCI/QoE, and systems, handling arXiv-speed concurrency, keeping citations double-blind, and verifying that cited "ACM MM papers" are ACM MM and not ICMR, MMSys, CVPR, or TOMM.

ACM MM Related Work

Use this to position an ACM Multimedia paper against a literature that is unusually spread out: a cross-modal contribution touches several single-modality communities plus the multimedia venues that combine them.

The five multimedia shelves

A strong ACM MM related-work section shows command of all shelves the contribution touches, not just the author's home community:

  • Vision — the visual side (CVPR/ICCV/ECCV) your method builds on or competes with.
  • Audio/speech and music — the acoustic side (ICASSP, INTERSPEECH, ISMIR) if a stream is audio.
  • Language — the text side (ACL/EMNLP) if captions, transcripts, or descriptions matter.
  • HCI / QoE / human-centric — perception, engagement, and interaction (CHI, QoMEX) when the claim is subjective.
  • Multimedia proper — ACM MM, ICMR, MMSys, and TOMM, where these threads are combined.

Coverage vs. venue-hygiene table

| Task | What to do | Failure it prevents | |---|---|---| | Cover each modality you use | Cite the current best single-modality work per stream | "You ignored the vision literature" | | Cite the fusion lineage | Trace the cross-modal line your method extends | "No delta over existing fusion" | | Verify the venue string | Confirm each "ACM MM" cite on dblp conf/mm | Misattributing an ICMR/CVPR paper to ACM MM | | Handle concurrency | Note contemporaneous arXiv work honestly | "You missed / overclaimed novelty vs. X" | | Keep it blind | Cite your own prior work in third person | Double-blind violation |

Positioning, not listing

Do not enumerate. For each closest neighbor, state in one clause what it did and in one clause what your paper adds — and make sure the delta is cross-modal, since "we swap a better encoder" is a single-modality delta a reviewer will discount.

[Neighbor] Late-fusion audio-visual highlight scoring (VenueYear).
[Their move] Average per-modality scores.
[Our delta] Score the timing DISAGREEMENT between streams — a signal averaging cannot represent.

Concurrency under arXiv speed

Multimedia sub-areas move fast and preprint heavily. Acknowledge genuinely concurrent work (roughly same-window preprints) as concurrent rather than prior, do not claim to beat a method you did not run, and do not silently drop a close preprint — a reviewer who knows it reads the omission as evasion.

Double-blind citation hygiene

  • Cite your own earlier papers in the third person ("Prior work [X] showed..."), never "our previous paper."
  • Avoid anonymity leaks through a dataset, system name, or repository that only your group uses.
  • The single-blind tracks (Reproducibility, Open Source Software, Dataset) relax this — but the main track and Brave New Ideas do not.

Building the section in passes

Pass 1: list the modalities and sub-fields your contribution touches (the shelves).
Pass 2: for each shelf, cite the current strongest 2-3 works you build on or beat.
Pass 3: trace the FUSION lineage — the cross-modal line your method extends — as its own thread.
Pass 4: add same-window arXiv work as concurrent, not prior.
Pass 5: verify every "ACM MM" cite on dblp; convert your self-cites to third person.

A reader should finish the section able to name which prior fusion approach you improve on and why the single-modality shelves are covered but not the whole story.

The multimedia-specific omission risk

Because a cross-modal paper sits between communities, the dangerous omission is usually the other community's closest work — a vision-trained author who misses the audio or IR paper that already did half the job. Before submitting, ask a question from each shelf's perspective: "what would an audio reviewer, an IR reviewer, and a systems reviewer each say I missed?" That triage catches the omissions that sink cross-area papers.

Venue-verification pass

Before submission, spot-check every citation that claims an ACM MM placement against dblp's conf/mm edition record. The common traps: ICMR papers cited as ACM MM, TOMM journal articles cited as the conference, and CVPR/ICCV vision papers cited as multimedia. Fix the venue string or the claim that rests on it.

Output format

[Shelf coverage] vision/audio/language/HCI-QoE/multimedia — <covered / gaps>
[Fusion lineage] traced / missing
[Deltas] cross-modal and specific / single-modality or vague: <list>
[Concurrency] handled / risky omissions: <list>
[Blindness] clean / leaks: <list>
[Venue hygiene] verified / suspect cites: <list>

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryDevelopment
Updated2mo ago
Forks153

Languages

Stata

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions