Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

The VS Code design philosophy — a shared Values→Principles→Moves vocabulary for reasoning about UI in design terms instead of raw pixels. Use when designing, building, reviewing, or giving feedback on any visual surface; when deciding a radius, spacing, type role, icon size, border, color, or motion; or when translating a "this feels off" observation into a concrete, principled fix.

Use when the user asks about Oleg Šelajev's talk "You're absolutely right, it was your home directory!" (ext live / Testkube conference, 2026) — including questions about Docker Sandboxes, running AI agents in microVM isolation, the trifecta of agent risks (sensitive data + external comms + untrusted content), why containers aren't enough for agent isolation, SBX kits, secret injection / sentinel values, prompt injection horror stories, YOLO mode agents, or applying his sandboxing workflow to the user's own agent setup.

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

用于 Java 后端面试出题；优先围绕 Java 核心、MySQL、Redis、Spring 与项目实战，追问设计取舍、故障处理和性能优化。

Simulate wave propagation — acoustic, electromagnetic, elastic, and quantum waves. FDTD, spectral methods, and absorbing boundary conditions for 1D/2D/3D wave equations with sources, scattering, and dispersion.

Train Physics-Informed Neural Networks (PINNs) using DeepXDE. Solve forward and inverse PDE problems by embedding physics equations into the neural network loss function. Supports 1D/2D/3D, time-dependent, and parametric PDEs.

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

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 like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory files.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.

数学建模竞赛工作流入口。用于启动完整建模流程：询问用户偏好，生成 plan.md 和 todo.md，并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。

How to review PRs for architectural quality — module boundaries, dependency direction, export surface, pattern consistency

Create a 1-hour Outlook follow-up meeting for pre-onboarding after a successful Docusign workflow trigger, using the employee name and agreement effective date from workflow context.

Use when the user specifies a task and a duration, and the work should be done iteratively by subagents over that time period