性能
性能分析与优化
numerai-experiment-design
numerai
Design and manage Numerai experiments in this repo for any model idea.
3dsmax-rendering
TerminalSkills
Configure and optimize rendering in 3ds Max — V-Ray and Corona render settings, render elements, light mix, batch rendering, network rendering, denoising, and post-production workflows. Use when tasks involve setting up production renders, optimizing render times, batch rendering multiple views, or configuring render farms for archviz and product visualization.
powerbi-modeling
github
'Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance. Triggers on queries about DAX calculations, table relationships, dimension/fact table design, naming conventions, model documentation, cardinality, cross-filter direction, calculation groups, and data model best practices. Always connects to the active model first using power-bi-modeling MCP tools to understand the data structure before providing guidance.'
chrome-devtools
ChromeDevTools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
learn-about-omc
Yeachan-Heo
Learn about your OMC usage patterns and get personalized recommendations
writer-memory
Yeachan-Heo
Agentic memory system for writers - track characters, relationships, scenes, and themes
note
Yeachan-Heo
Save notes to notepad.md for compaction resilience
vercel-react-best-practices
evolving-machines-lab
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
interview-mock-partner
aipoch
Simulates behavioral interview questions for medical professionals.
networking-email-drafter
aipoch
Draft professional follow-up emails to contacts made at conferences
postdoc-fellowship-matcher
aipoch
Match postdoc applicants to eligible fellowships based on nationality
memory
SamSaffron
"Read and update persistent memory. Use when: user says 'remember', asks about past context, preferences, or projects. Also use proactively to save anything reusable before a conversation ends."
ask-questions-if-underspecified
thienanblog
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
agent-memory-systems
davila7
"Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm"
peft-fine-tuning
davila7
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.
unsloth
davila7
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
serving-llms-vllm
davila7
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
context-window-management
davila7
"Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context."
ai-agents-architect
davila7
"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."
conversation-memory
davila7
"Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history."
agent-memory-mcp
davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
deepspeed
davila7
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
training-llms-megatron
davila7
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.
1ea91a
plurigrid
"Gay MCP skill at invocation 27"