MLOps
模型部署、评估与运维
nemo-curator
NousResearch
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
llama-cpp
NousResearch
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.
huggingface-hub
NousResearch
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
lambda-labs-gpu-cloud
NousResearch
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
lambda-labs-gpu-cloud
NousResearch
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
hermes-atropos-environments
NousResearch
Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent repo.
modal-serverless-gpu
NousResearch
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
peft-fine-tuning
NousResearch
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.
clip
NousResearch
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
django-perf-review
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.
domain-driven-design
wondelai
'Model software around the business domain using bounded contexts, aggregates, and ubiquitous language. Use when the user mentions "domain modeling", "bounded context", "aggregate root", "ubiquitous language", or "anti-corruption layer". Covers entities vs value objects, domain events, and context mapping strategies. For architecture layers, see clean-architecture. For complexity, see software-design-philosophy.'
design-everyday-things
wondelai
'Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", or "fault tolerance". Covers the gulfs of execution and evaluation. For usability scoring, see ux-heuristics. For iOS-specific patterns, see ios-hig-design.'
predictable-revenue
wondelai
'Build a scalable outbound B2B sales process with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "prospecting emails", "sales pipeline", "SDR process", or "B2B SaaS sales". Covers lead generation, qualification frameworks, and separating prospecting from closing. For offer design, see hundred-million-offers. For persuasion science, see influence-psychology.'
flow-nexus-neural
ruvnet
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
AgentDB Learning Plugins
ruvnet
"Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience."
agent-data-ml-model
ruvnet
Agent skill for data-ml-model - invoke with $agent-data-ml-model
agent-neural-network
ruvnet
Agent skill for neural-network - invoke with $agent-neural-network
godot-adapt-3d-to-2d
thedivergentai
"Expert patterns for simplifying 3D games to 2D including dimension reduction strategies, camera flattening, physics conversion, 3D-to-sprite art pipeline, and control simplification. Use when porting 3D to 2D, creating 2D versions for mobile, or prototyping. Trigger keywords: CharacterBody3D to CharacterBody2D, Camera3D to Camera2D, Vector3 to Vector2, flatten Z-axis, orthogonal projection, 3D to sprite conversion, performance optimization."
investor-materials
affaan-m
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
regex-vs-llm-structured-text
affaan-m
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
django-patterns
affaan-m
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
foundation-models-on-device
affaan-m
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
investor-materials
affaan-m
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
cost-aware-llm-pipeline
affaan-m
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.