Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when preparing for the review phase of an ICDM (IEEE International Conference on Data Mining) submission - planning for a venue whose tradition is NO author rebuttal, pre-answering reviewer questions inside the submitted PDF and cited artifact, and, only if the current edition opens a response window, drafting a tight anonymity-safe reply.
Use when positioning an ICDM (IEEE International Conference on Data Mining) paper's related work - lineage against prior ICDM editions and IEEE data-mining neighbors, the mechanism-contrast novelty sentence, avoiding KDD/SDM/CIKM/WSDM venue misattribution, and citing your own prior work in the third person so the section stays triple-blind-safe.
Use when drafting or revising prose for an ICDM (IEEE International Conference on Data Mining) paper - the data-regime-first register, the named-mechanism discipline, measured-scale language instead of scalability adjectives, discovery-validity sentences, triple-blind-safe self-reference, and compression into the single 10-page IEEE all-inclusive cap.
Use when responding to ICDT (International Conference on Database Theory) referees — principally the first-cycle Revise-and-resubmit round, where you return a corrected paper that closes each identified proof gap, plus any short author-comment phase, keeping the response anonymous and mapping every referee point to a concrete change in the revised PDF.
Use when positioning an ICDT (International Conference on Database Theory) paper against the database-theory literature — covering the ICDT/PODS lineage, finite model theory and complexity, delta-first positioning against the nearest prior theorem, honest treatment of overlapping bounds, and keeping self-citations anonymous under the since-2024 rule.
Use when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely, leading with the result and its data-management consequence, proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget, and the notation conventions a database-theory referee expects.
Use when revising an ICLR manuscript for learning-representation framing, OpenReview readability, contribution clarity, limitations, ethics, and reviewer navigation. Use when the core representation insight is buried, when an abstract must read well as an OpenReview snippet, or when adding a "what to verify" path so reviewers can confirm the claim under permanent public review.
Use when drafting ICML rebuttals and reviewer-author discussion replies under OpenReview double-blind constraints, where authors respond after initial reviews, reviewers may then have one additional discussion round, no revised paper can be uploaded during the period, and responses must stay anonymous. Use to triage objections by soundness, originality, significance, clarity, ethics, and reproducibility for the AC.
Use when rewriting a machine-learning paper for ICML-style claims, 8-page clarity, soundness/originality/significance framing, impact statement, lay-summary readiness, and reviewer-updateable rebuttal posture.
Use when responding to ICRA reviews in the channels that actually exist — turning decision-day reviewer comments into a disciplined camera-ready revision, writing the revise-and-resubmit response letter on the RA-L pathway, or converting an ICRA reject into a targeted IROS or RA-L resubmission — since classic ICRA offers no rebuttal.