Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when targeting Conference on Empirical Methods in Natural Language Processing (EMNLP) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for NLP flagship.
Use when targeting Conference on Lifelong Learning Agents (CoLLAs) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for continual learning.
Use when targeting Conference on Robot Learning (CoRL) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for robot learning.
Use when targeting Contemporary Accounting Research (CAR) or deciding whether an accounting manuscript fits this venue. Encodes the journal's fit, framing, method-and-evidence bar, house style, official-submission re-check, and desk-reject heuristics.
Use when designing or auditing experiments for a CoRL robot-learning paper — seeds and evaluation-episode counts, task-suite breadth, real-robot versus simulation evidence, sim-to-real gap measurement, baseline fairness across BC/RL/VLA families, generalization splits, and statistics for success-rate claims.
Use when positioning a CoRL paper against the literature — the robot-learning lineage across CoRL/RSS/ICRA, the ML-methods stream from NeurIPS/ICLR/ICML, the fast-moving VLA and foundation-model wave, classical robotics baselines, concurrent arXiv work, and PMLR citation hygiene including the year-offset trap.
Use when reasoning about how CoRL reviews a paper — the OpenReview double-anonymous pipeline, reviewer/AC/SAC hierarchy, rubric scoring with weak accept as the acceptance threshold, the first-round rejection gate before rebuttal, the reviewer-AC discussion window, decision meetings, and public reviews for accepted papers.
Use when deciding whether a project belongs at CoRL, the Conference on Robot Learning, or should be routed to ICRA, IROS, RSS, NeurIPS, ICLR, ICML, or a journal — based on whether the learned component is the contribution, what embodied evidence exists, and which reviewer community should judge the claim.
Use when designing or writing heterogeneity / conditionality analysis for a 《中国行政管理》(Chinese Public Administration, CPA) manuscript — variation across regions, administrative levels, and governance contexts. 当主结果只笼统适用、只切了一个维度、或审稿人要求差异化分析时使用。Enforces theory-guided cuts and significance-of-difference discipline for this Chinese-Public-Administration-Society journal.
Use when designing or writing the governance / policy-process mechanism analysis for a 《中国行政管理》 manuscript. Identifies how an effect is produced (implementation, attention allocation, central-local, incentives / accountability) via quantitative mediation or qualitative process evidence. 本技能服务于《中国行政管理》(Chinese Public Administration, CPA)。