Use when planning a CAV (Computer Aided Verification) project timeline from venue and category selection through submission, the two-stage review with early reject and rebuttal, artifact evaluation by the AEC, and the LNCS open-access camera-ready, with backward-planning offsets for a verification-tool paper and honest handling of the single-annual-deadline cycle.
SkillScore91Maintained
Automatic
◆Project Management pack
Last verified 8/15/2026
What it changes
Passed 20 of 22 test cases with the skill, and 15 of 22 without it.
Without skill68%
With skill91%
Checks it passed that the model alone missed
States that stage 1 assigns two initial reviews.
Warns that CAV uses an early-reject stage-1 filter before rebuttal.
Warns that using unpinned baseline tool versions creates reproducibility risks.
and 5 more in the full report
5 fixed15 passed either way2 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+41%
Agent turns
0%
Response time
-30%
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 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
How many peer reviews does a CAV submission receive across its review process, and how are reviews split between stage 1 and stage 2 rebuttal?
What was checked, without and with the skill
Checked
Without skill
With skill
States that stage 1 assigns two initial reviews.
Missed
Passed
States that papers passing stage 1 receive two additional reviews prior to rebuttal.
Missed
Passed
case-11 · 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.md87 linessingle file
CAV Workflow
Use this as the project-management skill for a CAV submission. Replace every date with the current
official timetable and work backward from the AoE paper deadline. CAV publishes open access in
Springer LNCS, reviews in two stages (an early-reject filter, then a rebuttal), and runs an
optional artifact evaluation after notification — plan for all three, not just accept/reject.
CAV is a conference with no standing editor-in-chief; the rotating leadership is the per-edition
Program Chairs and Steering Committee. For CAV 2026 the Program Chairs are Anthony W. Lin, Eva
Darulova, and Philipp Rümmer (verified 2026-07-09), and the venue is Lisbon, part of FLoC
2026. Chairs rotate yearly; re-check the organization page rather than carrying a name forward.
Milestones
Venue + category fit: confirm CAV over TACAS/FMCAD/VMCAI and pick the category (Regular /
Tool / Application / Industrial) (cav-topic-selection).
Evidence lock: freeze the theorem/algorithm, the benchmark set (revision pinned), the baseline
tools and versions, the resource limits, and the artifact contents.
Submission: upload the LNCS-formatted PDF in the right category, anonymized if Regular or
Application, with the artifact-intent declaration set (CAV 2026: 28 Jan 2026 AoE).
Stage-1 filter: each paper gets two reviews; weak papers are rejected early (tentative
first-round outcome ~4 Mar 2026).
Rebuttal: papers passing stage 1 get two more reviews and an author-response window (CAV 2026:
30 Mar - 2 Apr 2026).
Notification: accept/reject (CAV 2026: 17 Apr 2026); archive all reviews and versions.
Artifact evaluation (optional): register and submit to the AEC on its own deadline (CAV 2026
artifact registration: 22 Apr 2026), pursuing Available / Functional / Reusable badges.
Camera-ready: prepare the LNCS open-access final version and complete Springer metadata and
rights; present at the conference (CAV 2026: 26-29 Jul 2026, Lisbon / FLoC).
Backward plan from the submission deadline
Weeks out (heuristic)
Verification-paper milestone
10+
Technique/algorithm fixed; the soundness/completeness statement drafted
8
Tool implemented and stable; benchmark set and baseline tools/versions chosen and pinned
6
Full evaluation run under fixed resource limits; per-instance data and logs archived
4
Full draft in llncs; proofs complete (in body or clearly-marked appendix); artifact assembled
3
Internal mock review by a verification-literate reader; differential/soundness cross-check done
2
Scope and limits sharpened; related-work delta tightened; page limit met