Use when auditing an ACM MM (ACM Multimedia) submission for OpenReview readiness — thematic-area choice, the 6-8 page ACM sigconf budget, references-only overflow, double-blind anonymity versus the single-blind Reproducibility/Open-Source/Dataset tracks, supplementary media, dual submission, desk-reject triggers, and last-week sequencing.
SkillScore91Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 20 of 22 test cases with the skill, and 18 of 22 without it.
Without skill82%
With skill91%
Checks it passed that the model alone missed
Uses the required audit output format starting with [ACM MM readiness].
Explains that the Dataset track is single-blind and anonymizing the submission is incorrect.
Formats the analysis output using the bracketed section headers starting with [ACM MM readiness].
and 1 more in the full report
3 fixed17 passed either way1 still failing1 broke
Pass-rate lift
+9 pp
Tokens
+26%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 8/15/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
We are submitting our new benchmark audio-visual dataset to the ACM MM Dataset track. We currently have our dataset hosted on an anonymous Drive folder and removed author names from the paper, but we aren't sure if we followed the right blinding conventions for this specific track or if our OpenReview setup is complete. Please evaluate our submission readiness and output a report that lists: 1) overall readiness, 2) track and thematic area, 3) blocking checks summary, 4) cross-modal evidence risk, 5) desk-reject risk, and 6) ordered fix sequence.
What was checked, without and with the skill
Checked
Without skill
With skill
Explains that the Dataset track is single-blind and anonymizing the submission is incorrect.
Missed
Passed
Uses the required audit output format starting with [ACM MM readiness].
Missed
Passed
case-02 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md100 linessingle file
ACM MM Submission
Use this to run a pre-deadline audit of an ACM Multimedia paper. Reopen the current Call
for Technical Papers, the Topics of Interest page, each relevant track call, and the
OpenReview group before giving deadline-ready advice — ACM MM rewrites these each edition.
Submission audit
Confirm the target is the ACM MM main conference (or a specific track), not a
co-located workshop, ACM MM Asia, MMSys, or ICMR.
Choose the thematic area deliberately: it routes the paper to a reviewer pool, and a
mismatched area is a quiet source of off-topic reviews.
Apply the current ACM sigconf template with no margin, font, or spacing edits. ACM
MM 2026 used a 6–8 page body; references may spill onto up to two additional pages
that contain only references.
Enforce double-blind anonymity across the paper, appendix, supplement, code, media
assets, filenames, PDF metadata, and repository links — unless submitting to the
named single-blind tracks (Reproducibility, Open Source Software, Dataset), where the
artifact's identity is expected.
Register the abstract before the abstract deadline; the paper and the supplement have
their own later deadlines (in 2026: abstract Mar 25, paper Apr 1, supplement Apr 8, AoE).
Check concurrent-submission rules and prior-publication status; do not keep the same work
under review at another archival venue when ACM MM forbids it.
Blocking risks
Late abstract registration or paper upload.
Overlength body or a tampered sigconf template.
Identity leak in the PDF, media metadata, demo watermark, or repository link (on a
double-blind track).
Wrong track blinding — anonymizing a Dataset/Open-Source submission, or de-anonymizing a
main-track one.
Non-rendering or proprietary-format supplementary media.
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.