Guidelines for generating clinical decision support (CDS) documents: patient cohort analyses (biomarker-stratified outcomes) and treatment recommendation reports (GRADE-graded evidence). Covers document structure, executive summary design, evidence grading (GRADE 1A–2C), statistical reporting (HR, CI, survival), and biomarker integration. Use when creating pharmaceutical research documents, clinical guidelines, or regulatory submissions.
启动可视化小说管理面板（只读 Web Dashboard），实时查看项目状态、实体图谱与章节内容。
Read, search, send, and manage emails from the MailClaw inbox via the local CLI. Use when the user asks to check emails, read messages, search inbox, find emails from a sender, review recent correspondence, or send/reply to emails.
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments.
Comprehensive analysis of BigQuery usage patterns, costs, and query performance
- 📁 examples/
- 📁 specs/
- 📄 SKILL.md
Set up or repair Entrix fitness specs in the current repository by discovering real quality signals, generating docs/fitness, and iterating with entrix validation until the result is executable. Use when the user asks to bootstrap entrix, add or split fitness dimensions, repair invalid fitness specs, or make docs/fitness actually runnable.
General conventions when creating an application design
Commit co-author trailer management
Use when a task should run through Hydra's file-contract workflow in an isolated worktree, or when an existing Hydra workflow must be inspected, retried, or cleaned up.
Use when user mentions papers, references, citations, Zotero, literature, bibliography, workspaces, or needs to search/read/export academic papers. Uses zot CLI for all operations including workspace-based RAG.
- 📁 agents/
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Invoke BEFORE starting implementation.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user preferences/identity/relationships, storing conversation events, answering questions that depend on past sessions, and any task involving `execute_kip`.
