Use when advising leaders on self-discipline, virtue maintenance, or preventing institutional decline. Applies Zhou Gong's teachings to King Cheng with models from Yin dynasty rulers like Zhong Zong, Gao Zong, and Zu Jia to identify habits that sustain or destroy long-term rule.

Use when analyzing historical power transitions through targeted action, such as Prince Guang's (King Helu) removal of King Liao. Covers legitimacy claims, agent recruitment, timing, operational security, and consolidation.

Redis patterns including caching strategies, pub/sub, streams for event processing, Lua scripts, and data structures

Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

PostgreSQL optimization including indexes, query plans, partitioning, JSONB operations, and connection pooling

Web performance optimization including bundle analysis, lazy loading, caching strategies, and Core Web Vitals

LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

Query optimization, indexing strategies, and database performance tuning for PostgreSQL and MySQL

REST API design with resource naming, pagination, versioning, and OpenAPI spec generation

在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。

为深度学习模型、网络架构、算法流程等生成标准 Draw.io (.drawio) 格式的可视化图表；支持从零生成与风格迁移两种模式。从零生成：模型架构图、流程图、感受野示意图等；风格迁移：参考图 + 内容描述/项目 → 按参考图风格生成新图。确保 XML 格式正确，可直接在 Draw.io 中打开编辑。

Generate a creative greeting for the user

Create a git commit with a summary of changes

Enforces structured, highly documented storage for code and data projects. Use when working on machine learning scripts, data processing, code creation, or script modification that should preserve clear structure and documentation.

Break down implementation plans into actionable task lists. Use after planning to create a structured task breakdown. Generates tasks.md with ordered, dependency-aware tasks.

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Single-cell RNA-seq and retained scverse workflow owner. Load .h5ad/10X data, manage AnnData metadata, plan scVI/scANVI batch-correction workflows, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis.

Estimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment-effect analyses, including robustness checks and counterfactual plots. For choosing a study design before analysis, use designing-experiments instead.

Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.