Use when reasoning about how an ACL paper travels through ACL Rolling Review and conference commitment, covering reviewer and area-chair roles, meta-reviews, the commitment decision by senior area chairs and program chairs, Findings versus main-conference outcomes, ethics review escalation, and resubmission strategy across cycles.
SkillScore55Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 12 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill55%
Checks it passed that the model alone missed
Uses the exact line label '[Stage] meta-review'.
Recommends holding for revision to update baseline comparisons.
Uses the exact line label '[Commit recommendation] hold for revision'.
and 5 more in the full report
8 fixed4 passed either way7 still failing3 broke
Pass-rate lift
+23 pp
Tokens
+57%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/15/2026v112 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
In a standard 10-week ARR cycle, at approximately which week offset is the meta-review written? Format using standardized line tags.
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies weeks 7-8 as the stage when meta-reviews are written.
Passed
Passed
Uses the exact line label '[Stage] meta-review'.
Missed
Passed
case-15 · 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.md114 linessingle file
ACL Review Process
Use this to model where an ACL paper actually is and who decides what next.
ACL decoupled reviewing from the conference: ARR produces the review package;
the conference consumes it. Confirm current mechanics at
aclrollingreview.org/reviewing, since cycle structure has changed repeatedly
(most recently to 10-week cycles in 2025).
The pipeline, stage by stage
ARR cycle intake: submission on OpenReview to a dated cycle (e.g.,
ARR January 2026); checks for format, Limitations, checklist, anonymity.
Review: at least three reviewers score and write reviews.
Author response + discussion: authors reply; reviewers discuss and may
update reviews (see acl-author-response).
Meta-review: the action editor / area chair synthesizes reviews into a
meta-review with a recommendation. Notably, ARR senior area chairs do not
make accept/reject recommendations — that authority sits with the venue.
Commitment: authors choose whether and where to send the finished
package — ACL, or another *ACL venue accepting that cycle.
Venue decision: the conference's senior area chairs and program chairs
read reviews + meta-review and decide: main conference, Findings, or reject.
Ethics branch: papers flagged during review go to an ethics committee,
which can require revisions or recommend rejection on ACL Code of Ethics
grounds independent of technical merit.
Who decides what
Actor
Controls
Cannot do
Reviewer
Review text, scores, discussion updates
Accept or reject anything
AC / action editor
Meta-review, review-issue handling
Bind the conference's decision
Author
Response, revision, where/whether to commit
Change reviews after the cycle closes
Venue SACs + PCs
Main/Findings/reject from the ARR package
Re-run the reviewing itself
Ethics committee
Ethics-based conditions or rejection
Judge technical contribution
Outcomes and what they mean
Main conference: full acceptance with a presentation slot.
Findings of ACL: peer-reviewed, Anthology-published acceptance for solid