ing

Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.

Python video composition with moviepy 2.x — overlaying deterministic text on AI-generated video (LTX-2, SadTalker), compositing clips, single-file build.py…

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense…

Generate game art assets using each::sense AI. Create 2D sprites, character sprite sheets, seamless textures, UI elements, icons, tilesets, loading screens,…

Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory),…

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation…

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring…

| Nuxt 4 server-side development with Nitro: API routes, server middleware, database integration, and backend patterns. Use when: creating server API routes,…

阿里云 MaxCompute 项目管理技能。用于创建、查询和列出 MaxCompute 项目。触发词："maxcompute project"、"odps project"、"create maxcompute project"、"manage maxcompute project"、"list maxcompute project"。

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text…

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test…

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…

使用现代 Akka.Hosting.TestKit 模式为 Akka.NET Actor 编写单元测试和集成测试。涵盖依赖注入、TestProbe、持久化测试、集群测试、流测试以及基于 xUnit/NUnit 的测试编排。包括使用 TestKit 配置自定义 ActorSystem、通过 IServiceCollection 注入 mock 服务、利用 TestProbe 验证 Actor 交互模式、使用 EventSourcedBehavior 测试持久化 Actor、基于 MemorySnapshotStore 的快照验证、分布式数据 CRDT 测试、Streams TestKit 的 Source/Sink/Flow 断言、多节点 TestKit 的集群分片场景，以及 CI/CD 友好的并行执行配置与代码覆盖率集成。

How to choose and configure data sources for MapLibre GL JS — rendering your own data without tiles, hosted tile services, serverless PMTiles, self-hosted tile…

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…

Generates semantic commit messages following the Conventional Commits specification with proper types, scopes, breaking changes, and footers. Use when users…

Use this skill when users need to develop brand strategy, choose a company name, define brand positioning, create brand voice, or build brand identity from day…