aaai-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited aaai-workflow (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this as the project-management skill for an AAAI submission. Replace all dates with the current cycle's official timetable and work backwards from OpenReview cutoffs.
AAAI is a conference, not a journal: it has no standing editor-in-chief and no article-processing charge. The rotating leadership is the per-edition Program Chairs (AAAI-26: Chad Jenkins and Matthew Taylor, verified 2026-06-22), and the cost model is registration fees, not APCs — at least one author must register at the in-person rate to present. Conference organizers rotate yearly, so re-check the current CFP and conference-organizers page rather than carrying a name or contact forward.
if present.
public artifacts.
multiple-submission policy.
Because AAAI runs a two-phase review with hard OpenReview cutoffs and no second feedback round, the timeline is unforgiving. Anchor each gate to the prior one and to the official date, not a guess.
| Gate | Depends on | Slip consequence |
|---|---|---|
| Abstract deadline | title, authors, conflicts locked | cannot submit the paper |
| Paper deadline | anonymous PDF, checklist, supplement | summary reject or no entry |
| Phase-1 cut | clarity and checklist done early | no feedback, paper dies |
| Feedback round | submitted evidence only | wasted on new-results bans |
| Camera-ready | acceptance, copyright, registration | dropped from proceedings |
Treat the Phase-1 cut as the real deadline, earlier than acceptance. Before the paper deadline, a non-specialist colleague should be able to state your contribution, find the evidence, and confirm the checklist matches the paper. If they cannot, the broad-AI reviewer will not either.
A team plans to "finish experiments in rebuttal." The workflow flags this as fatal: AAAI bars new results at feedback and may cut the paper in Phase 1 before feedback exists. The critical path moves to locking evidence and the checklist a week before the paper deadline, leaving the feedback window only for clarifying already-submitted material.
[Current stage] idea / experiments / writing / submission / Phase 1 / rebuttal / accepted
[Next official deadline] <date and source, or unknown>
[Critical path] <three tasks that determine readiness>
[Risk register] <page, anonymity, checklist, supplement, policy>
[Owner map] <task -> person or role>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.