Skill 资源库

AI Skill 资源库

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。

personTashanworld无需 Key

multi-perspective

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…

download3deployed_codestar0
personTashanworld无需 Key

medical-guideline-ocr-mermaid

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。

download3deployed_codestar0
personTashanworld无需 Key

medical-imaging-methods

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…

download3deployed_codestar0
personTashanworld无需 Key

miles-rl-training

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…

download3deployed_codestar0
personTashanworld无需 Key

miwrite-lit

Local-only literature synthesis from user-provided notes, excerpts, and local files.

download3deployed_codestar0
personTashanworld无需 Key

model-pruning

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…

download3deployed_codestar0
personTashanworld无需 Key

music-generation

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…

download3deployed_codestar0
personTashanworld无需 Key

miwrite-ask

Local-only Socratic dialogue for research direction, framing, and method discussion.

download3deployed_codestar0
personTashanworld无需 Key

moe-training

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…

download3deployed_codestar0
personTashanworld无需 Key

napari-workflow-builder

build reproducible napari-centered bioimage analysis workflows in python using numpy, scipy, scikit-image, tifffile, pandas, matplotlib, and napari. use when the task involves interactive image inspec…

download3deployed_codestar0