Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Stage and create a Conventional Commits message for the current change

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing Data Analytics report, dashboard, or inline chart export into a PDF artifact.

Build a durable analytical report with an answer-first narrative, evidence-backed findings, charts or tables, caveats, recommendations, and source context.

Choose presentation-ready color palettes and font pairings for PPT/design tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.

Implementation details for the EF Core Azure Cosmos DB provider. Use when changing Cosmos-specific code.

Use this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.

Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.

Clone shadcn implementation patterns with source-by-source parity. Use when the user says "shadcn parity", asks to mirror shadcn, copy shadcn UX/architecture/tests, or wants more than inspiration.

Always-on code-review persona. Audits changes against the project's own CLAUDE.md and AGENTS.md standards -- frontmatter rules, reference inclusion, naming conventions, cross-platform portability, and tool selection policies.

TypeScript expert for type system, generics, utility types, and strict mode patterns

Prometheus monitoring expert for PromQL, alerting rules, Grafana dashboards, and observability

Nginx configuration expert for reverse proxy, load balancing, TLS, and performance tuning

Jira project management expert for issues, sprints, workflows, and reporting

Helm chart expert for Kubernetes package management, templating, and dependency management

用于把当前会话沉淀为可复用的 workspace skill。当用户希望把当前对话、工作流或排错路径写成 SKILL.md 时触发。触发表达包括「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」以及任何 /make-skill <focus> 调用。

Use this skill when sedimenting a session into a reusable workspace skill. Triggers when the user wants to turn the current conversation, workflow, or troubleshooting path into a SKILL.md. Phrases like 'turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this', and any /make-skill <focus> invocation should fire this skill.

行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架