ICML-Skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ICML-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.
First-party depth pack for the International Conference on Machine Learning (ICML).
This pack operationalizes ICML main-track rules and review culture: topic fit, submission readiness, author response, camera-ready, artifacts, reproducibility, supplementary material, review process, writing style, related work, experiments, and workflow routing.
| Skill | Use it for |
|---|---|
icml-topic-selection | Decide whether the paper fits ICML main track, position track, or another venue. |
icml-workflow | Plan the lifecycle from fit diagnosis through PMLR-ready camera-ready work. |
icml-submission | Audit OpenReview, LaTeX, 8-page body, anonymity, supplement, impact statement, and policy risks. |
icml-review-process | Understand reciprocal reviewing, reviewer/AC behavior, ethics, LLM-review policy, and public review records. |
icml-author-response | Draft concise rebuttals and one-round reviewer-author discussion replies. |
icml-camera-ready | Prepare accepted-paper PDF, PMLR agreement, lay summary, public artifacts, and post-conference revision. |
icml-artifact-evaluation | Package anonymized code/data and public release artifacts for ICML. |
icml-reproducibility | Strengthen reproducible experiments, code/data claims, and impact-statement support. |
icml-supplementary | Decide what belongs in the paper PDF, supplementary manuscript, code/data ZIP, or public repository. |
icml-writing-style | Rewrite claims for ICML soundness, originality, significance, clarity, and impact expectations. |
icml-related-work | Handle concurrent ICML submissions, recent papers, and close ML literature. |
icml-experiments | Stress-test baselines, ablations, seed variance, compute, and claim-to-evidence fit. |
The pack was checked against official ICML 2026 sources on 2026-06-01. ICML policies change yearly: always reopen the current CFP, Author Instructions, Peer Review FAQ, OpenReview group, and LLM-review policy before submission-ready advice.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.