性能
性能分析与优化
ads-tiktok
AgriciDaniel
TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", or "TikTok campaign".
agent-orchestration-improve-agent
rmyndharis
"Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration."
chaos-engineering-resilience
proffesor-for-testing
"Chaos engineering principles, controlled failure injection, resilience testing, and system recovery validation. Use when testing distributed systems, building confidence in fault tolerance, or validating disaster recovery."
address-sanitizer
trailofbits
AddressSanitizer detects memory errors during fuzzing. Use when fuzzing C/C++ code to find buffer overflows and use-after-free bugs.
databricks
databricks
"Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks."
databricks-apps
databricks
Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Invoke BEFORE starting implementation.
async-python-patterns
rmyndharis
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.
backtesting-frameworks
rmyndharis
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
android-jetpack-compose-expert
sickn33
Expert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and Material Design 3.
async-python-patterns
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
sickn33
"Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration."
arm-cortex-expert
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
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
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
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
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
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
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
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
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
Orchestra-Research
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
sentencepiece
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
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.
avoid-ai-writing
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.