代码生成
生成代码、脚手架和模板
rust-engineer
Jeffallan
Writes, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements ownership patterns, manages lifetimes, designs trait hierarchies, builds async applications with tokio, and structures error handling with Result/Option. Use when building Rust applications, solving ownership or borrowing issues, designing trait-based APIs, implementing async/await concurrency, creating FFI bindings, or optimizing for performance and memory safety. Invoke for Rust, Cargo, ownership, borrowing, lifetimes, async Rust, tokio, zero-cost abstractions, memory safety, systems programming.
javascript-pro
Jeffallan
Writes, debugs, and refactors JavaScript code using modern ES2023+ features, async/await patterns, ESM module systems, and Node.js APIs. Use when building vanilla JavaScript applications, implementing Promise-based async flows, optimising browser or Node.js performance, working with Web Workers or Fetch API, or reviewing .js/.mjs/.cjs files for correctness and best practices.
agentscope-java
agentscope-ai
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
create-custom-agent
dotnet
Creates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs. Use when scaffolding new custom agents, configuring agent workflows, or setting up agent-to-agent handoffs.
create-skill
dotnet
Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, writing a skill description that the runtime will actually route to, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance. Do not use for fixing a skill that already fails its evaluation (use improve-skill-quality) or for writing eval.yaml (use create-skill-test).
agent-sessions-layout
microsoft
Agent Sessions workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agent Sessions workbench layout.
mcp-builder
ComposioHQ
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
artifacts-builder
ComposioHQ
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
connect-apps
ComposioHQ
Connect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.
uml
markdown-viewer
Create UML diagrams using PlantUML syntax. Best for software modeling — Class, Sequence, Activity, State Machine, Component, Use Case, and Deployment diagrams with concise text-based notation and auto-layout.
brainstorming
obra
"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
diagram-maker
openclaw
Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.
clickhouse-pr-description
ClickHouse
Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations. Use when creating or updating PR descriptions.
syncable-entity-types-and-constants
twentyhq
Define types, entities, and central constant registrations for syncable entities in Twenty's workspace migration system. Use when creating new syncable entities, defining TypeORM entities, flat entity types, or registering in central constants (ALL_ENTITY_PROPERTIES_CONFIGURATION_BY_METADATA_NAME, ALL_ONE_TO_MANY_METADATA_RELATIONS, ALL_MANY_TO_ONE_METADATA_FOREIGN_KEY, ALL_MANY_TO_ONE_METADATA_RELATIONS).
syncable-entity-cache-and-transform
twentyhq
Create cache services and transformation utilities for syncable entities in Twenty. Use when implementing entity-to-flat conversions, input DTO transpilation to universal flat entities, or cache recomputation for syncable entities.
huggingface-accelerate
Orchestra-Research
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
peft-fine-tuning
Orchestra-Research
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
implementing-llms-litgpt
Orchestra-Research
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
simpo-training
Orchestra-Research
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
hqq-quantization
Orchestra-Research
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
axolotl
Orchestra-Research
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
miles-rl-training
Orchestra-Research
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
mamba-architecture
Orchestra-Research
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
pytorch-fsdp2
Orchestra-Research
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.