Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.
定向聊天室：根据话题推荐或接受用户指定的专家，模拟多角色对话。先选经过长期检验、可独立验证的理论，再选择其代表人物。聊天室进行中，用户后续输入默认继续由同一组专家讨论；用户说「结束聊天室」或输入 /dbs 时退出。触发方式：/dbs-chatroom、/定向聊天室、「定向聊天室」「结束聊天室」
dontbesilent 交互式学习。把一个课题拆成连续学习文章，根据用户在上一篇中的反馈调整下一篇的深度、角度和节奏。 触发方式：/dbs-learning、/dbs-learn、/交互式学习、「带我学一个课题」「继续下一篇」「根据我的反馈写下一篇」 Interactive learning workflow. Builds an adaptive sequence of learning articles based on user feedback. Trigger: /dbs-learning, /dbs-learn, "teach me a topic", "continue the next lesson"
Explain the Nativewind v5 architecture, CSS pipeline, and key files. Use when a contributor wants to understand how the codebase works.
Reads a GitHub issue and all its linked issues, PRs, and comments to extract requirements and context. Invoke for any request combining a GitHub issue reference (#123, owner/repo#123, or URL) with a need to understand what the issue asks for — extracting acceptance criteria, understanding scope, gathering requirements before implementation or testing, or analyzing what changed. Extracts only what is explicitly stated in the issue and its linked references — does not invent or assume. Not for writing code, running tests, or debugging.
Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to build-from-issue — maps vague ideas to concrete, buildable issues. Trigger keywords - spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration.
Search codebase and git history for keywords. Use when investigating code changes, finding where features were added, or tracking down when bugs were introduced.