ICLR-Skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ICLR-Skills (Plugin) 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.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
Twelve agent skills for International Conference on Learning Representations (ICLR) main-conference papers. The pack focuses on OpenReview submission readiness, double-blind public review, author discussion, revision discipline, reproducibility, artifacts, and camera-ready preparation.
Official basis checked on 2026-06-01: ICLR 2026 CFP, Author Guide, Reviewer Guide, Code of Ethics, Code of Conduct, LLM-use policy updates, poster instructions, and the OpenReview conference group. See resources/official-source-map.md for the exact source map.
iclr-submission - audit OpenReview, anonymity, page limit, reciprocal reviewing, LLM disclosure,dual-submission, and supplementary readiness.
iclr-author-response - draft concise OpenReview discussion replies and revision notes afterreviews.
iclr-camera-ready - prepare accepted-paper metadata, camera-ready files, poster assets, video,and project-page links.
iclr-artifact-evaluation - package code, data, demos, checkpoints, and instructions for anICLR-style reproducibility review, even when no separate artifact badge is promised.
iclr-reproducibility - strengthen evidence, randomization, compute disclosure, and robustness.iclr-supplementary - organize appendices, supplementary files, code, private links, anddiscussion-period revisions.
iclr-review-process - reason about review dimensions, AC/SAC roles, public comments, restrictedcomments, and final recommendations.
iclr-writing-style - revise for learning-representation contribution, clarity, and reviewernavigation.
iclr-related-work - position against concurrent OpenReview/arXiv work and adjacent ICLR claims.iclr-experiments - audit baselines, ablations, scaling, statistics, robustness, and compute.iclr-workflow - manage a calendar from topic selection through poster upload.iclr-topic-selection - decide whether a project is ICLR-shaped or should be routed elsewhere.discussion can be read as part of the scientific record.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.