Performance

android-jetpack-compose-expert

by sickn33

Expert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and Material Design 3.

async-python-patterns

by sickn33

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

agent-orchestration-improve-agent

by sickn33

"Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration."

arm-cortex-expert

by sickn33

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.

application-performance-performance-optimization

by sickn33

"Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack."

ai-agents-architect

by sickn33

"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling."

awq-quantization

by Orchestra-Research

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

training-llms-megatron

by Orchestra-Research

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.

ML Training Recipes

by Orchestra-Research

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

optimizing-attention-flash

by Orchestra-Research

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

huggingface-tokenizers

by Orchestra-Research

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

llama-cpp

by Orchestra-Research

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

unsloth

by Orchestra-Research

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

sentencepiece

by Orchestra-Research

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

rwkv-architecture

by Orchestra-Research

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

researchers-biographical

by bitwize-music-studio

Researches personal backgrounds, interviews, motivations, and humanizing details. Use when research needs biographical context about people involved in the album's subject.

Spring Data JPA Implementation

by a-pavithraa

profile

by ccusage

Profiles ccusage performance. Use when a CLI command is slow, when checking that an optimization actually helped, when comparing a branch against main, or when reading a captured CPU profile.

avoid-ai-writing

by brycewang-stanford

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detection-only mode that flags patterns without rewriting.

browser

by julianromli

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements.

backend-dev

by julianromli

Comprehensive backend development workflow that orchestrates expert analysis, architecture design, implementation, and deployment using the integrated toolset. Handles everything from API design and database architecture to security implementation and DevOps automation.

x-filter

by kangarooking

Score and filter topics for X content creation using weighted criteria. Use when user wants to evaluate collected materials, filter topics by score, or mentions "filter topics", "score materials", "x-filter", "选题筛选". Applies 10-point scoring system with customizable weights.

django-perf-review

by getsentry

Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.

system-info

by UKGovernmentBEIS

Get detailed system information including OS, kernel, CPU, and memory details