微信扫一扫把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。
Strengthen the mathematical substance of research papers by proposing or implementing better proofs, sharper results, cleaner derivations, and stronger formulations. Use when Codex needs to improve th…
>-
>
Effective communication strategies for statistical methods
Local-only Socratic dialogue for research direction, framing, and method discussion.
Local-only material organization for mixed notes, interviews, reports, and project files.
Local-only conversion of research material into briefs, memos, and decision-facing reports.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l…
Core mathematical concepts and theoretical frameworks for statistics
>
>
JASA/Biometrika manuscript structure with VanderWeele notation standards
Local-only stress test for proposals, opening reports, grant drafts, and research designs.
Local-only academic polishing and transcreation from local text.
Local-only manuscript, report, and chapter review.
Explore a research question through several independent analytical perspectives and synthesize their agreements and disagreements. Use when one line of reasoning is insufficient and distinct viewpoint…
当任务是把医学指南 PDF 转成最终 Markdown，并需要先调用 PaddleOCR-VL 做 OCR/版面解析，再用 VLM 把指南中的图片、图表、算法图或流程图转换为 Mermaid，最后回填输出一个保留正文和表格的 Markdown 文件时使用。也适用于已有 PaddleOCR Markdown 但仍需抽取图片并转 Mermaid 的情况。
Drafting and reviewing the Methods section of papers involving medical imaging, radiomics, or deep learning on imaging modalities (CT, MRI, X-ray, US, WSI). Covers acquisition reporting, preprocessing…
Six-phase protocol for adapting methods across research domains
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring spec…
Local-only literature synthesis from user-provided notes, excerpts, and local files.
Local-only close reading for papers, reports, policy texts, and chapters.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabli…
Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood promp…