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.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 9/2/2026
What it changes
Passed 21 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill95%
Checks it passed that the model alone missed
Response contains the tag "[AAAI readiness]"
Response confirms that the author is compliant with the submission limit
Response orders the anonymity sweep with PDF text and metadata prioritized first
and 9 more in the full report
8 fixed13 passed either way0 still failing1 broke
Pass-rate lift
+32 pp
Tokens
+23%
Agent turns
0%
Response time
-16%
Model gemini-3.6-flashMeasured 9/2/2026v221 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
We are writing an ethics statement for our AAAI main track paper. The main technical text is exactly 7 pages, and we placed a half-page ethics statement at the top of page 8, followed by references on pages 8 and 9. Does placing the ethics statement on page 8 comply with the 7-page technical limit? Please provide a submission audit output detailing readiness, track, blocking checks, highest risk, and fix order.
What was checked, without and with the skill
Checked
Without skill
With skill
Response states that the ethics statement counts toward the 7-page technical content limit
Missed
Passed
Response identifies the submission as exceeding page limits because the ethics statement pushes technical content into page 8
Missed
Passed
case-07 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md105 linessingle file
AAAI Submission
Use this for an AAAI main technical track submission audit. Reopen the current conference page,
Author Kit, CFP, submission instructions, review process page, supplementary-material page, and
author policies before giving deadline-ready advice.
Submission audit
Confirm the target track: Main Track, AI for Social Impact, AI Alignment, or another AAAI program.
Track-specific rules can differ.
Verify OpenReview account/profile readiness, conflicts, author list, subject areas, and submission
metadata before the abstract and paper deadlines.
Check the current AAAI author kit. AAAI-27 submissions use AAAI two-column camera-ready style and
US Letter PDF, with a main PDF of at most 9 pages whose pages 8-9 are references only — 7 pages
of non-reference content. Any ethical statement counts inside those 7 pages.
Confirm double-blind compliance in the PDF, file names, references to prior work, supplement,
code/data, and metadata. Omit acknowledgments in the review version.
Upload the reproducibility checklist in its own submission field, not inside the paper PDF —
AAAI-27 moved it out of the document, and a checklist buried after the references is now a missing
checklist.
Enforce the author submission limit and author-change rules. AAAI-27 limits each author to 10
combined main-technical-track submissions (the AI Alignment and AI for Social Impact special tracks
are excluded from that count), allows no author additions after submission, and permits
modifications only until the full-paper deadline.
Check multiple-submission compliance. An AAAI submission under review cannot simultaneously be
under review at another archival venue, and AAAI-27 names the patterns it treats as violations:
cosmetic re-submission, "thin slicing" one contribution across papers, splitting results by
method/dataset/domain, and obfuscated or "alternative universe" duplicates. Papers sharing authors
may be assessed together for novelty.
Apply the current AAAI AI-use policy: editing/polishing author-written text may be allowed, but
LLM-generated manuscript text, AI authorship, and AI-generated citations are policy risks.
Blocking risks
Over-limit technical content or malformed PDF.
Missing reproducibility checklist.
Identity leakage in paper, supplement, links, code, data, or prior-work citations.
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.