Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.
Post-task merge readiness gate with a state-backed explanation report and human explainability quiz
排查 JVM / 应用 CPU 飙高（线程定位 + 代码路径分析）
使用 Arthas 的 watch/trace 获取 EagleEye traceId / 获取请求的 traceId
排查 Spring ApplicationContext / Bean / 配置注入等问题
Summarizes articles into concise digests. Useful when user asks to summarize or get key points from an article.
Build and modify Codename One cross-platform mobile apps (Java 17, Maven, ParparVM/Android/iOS/JavaScript). Use when the project contains a `common/codenameone_settings.properties`, depends on `com.codenameone:codenameone-core`, edits CSS files under `common/src/main/css/`, calls `cn1:run`, `cn1:test`, `cn1:build`, references `com.codename1.ui.*` / `com.codename1.testing.*`, or when the user asks to build a UI, write screen tests, generate screenshots, or compare to Swing/HTML.
How to use LangExtract to extract structured information from text. Use when writing code that calls lx.extract(), building extraction pipelines, defining examples, or troubleshooting alignment issues.