ML Ops
Machine learning operations
fuel
by openclaw-rocks
"Optimized LLM inference and agent config for OpenClaw. Multi-provider routing with automatic cheapest-provider selection, context pruning, smart compaction, cheap heartbeats, session initialization, prompt caching, and memory management — all calibrated for autonomous agents that run for hours without wasting tokens. Triggers on: 'save on inference,' 'cheaper models,' 'optimize costs,' 'LLM config,' 'model routing,' 'inference setup,' 'fuel,' 'reduce token usage,' 'context management,' or any request to make an OpenClaw agent more cost-effective."
hughes-property-based-testing
by copyleftdev
Test software in the style of John Hughes, inventor of QuickCheck and property-based testing. Emphasizes specifying properties that should hold for all inputs, generating random test cases, and shrinking failures to minimal examples. Use when testing algorithms, data structures, parsers, serializers, or any code with clear invariants.
context-fundamentals
by Nymbo
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
planning-marketing-budget
by amogha-dalvi
Use when the user needs to derive a marketing budget from revenue targets, plan headcount for a 1-3 person team, decide what to build vs. buy vs. automate, or allocate spend across channels with ROI expectations. Use when budget is based on gut feel rather than revenue math, or resource allocation feels arbitrary.
defining-icp-segmentation
by amogha-dalvi
Use when targeting feels unfocused, CAC is too high, churn patterns suggest bad-fit customers, or the ICP lives only in the founder's head. Use when entering a new market, conversion rates are low, or sales wastes cycles on wrong-fit accounts. Use after customer research is complete and before any channel or campaign decisions.
growing-nrr
by amogha-dalvi
Use when net revenue retention is below 110%, when churn patterns are reactive instead of predictive, when expansion revenue lacks systematic triggers, when onboarding fails to reach activation milestones, or when customer health scoring does not exist. Use when customer base is large enough for patterns (50-500 accounts) but retention is managed manually.
accelerating-pipeline
by amogha-dalvi
Use when pipeline velocity is flat or declining, win rates are below 20 percent, sales cycles are lengthening, deals are single-threaded, or lead routing is slow. Use when MQL volume is prioritized over pipeline quality, when marketing and sales define funnel stages differently, or when signal-based engagement has not replaced linear nurture drips.
dspy-prompting
by eyadsibai
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
llm-inference
by eyadsibai
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
ml-engineering
by eyadsibai
Use when "deploying ML models", "MLOps", "model serving", "feature stores", "model monitoring", or asking about "PyTorch deployment", "TensorFlow production", "RAG systems", "LLM integration", "ML infrastructure"
funsloth-runpod
by chrisvoncsefalvay
Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints
process-modeling
by spjoshis
Master process modeling with BPMN, flowcharts, swimlane diagrams, and process optimization techniques for business process improvement.
statistical-analysis
by spjoshis
Master statistical analysis with hypothesis testing, A/B testing, regression, and statistical methods for data-driven decisions.
cloudrouter
by manaflow-ai
Manage cloud development sandboxes with cloudrouter. Create, sync, and access remote VMs with GPU support, Docker, and browser automation. Use when asked to create a sandbox, spin up a dev environment, run code in the cloud, use GPUs, automate a browser, or interact with remote VMs.
workout-generator
by LKB-99
"Generate personalized workout plans with progression and tracking. Use this skill when users want to create a workout routine, training program, or exercise plan. Triggers: workout, training, exercise, fitness plan, gym routine, treino, academia, plano de treino, rotina de exercícios."
go-concurrency
by spjoshis
Master Go concurrency with goroutines, channels, select, sync primitives, and patterns for building concurrent applications.
marketing-system-index
by amogha-dalvi
Use when starting any marketing work for a SaaS business at 1M-5M ARR, when needing to find the right marketing skill, or when planning which marketing skills to execute and in what order.
designing-gtm-strategy
by amogha-dalvi
Use when the user needs to translate foundational marketing insights into an operational growth plan, select a GTM motion, prioritize channels, or create a 90-day execution plan. Use when marketing efforts feel like disconnected tactics without a coherent system connecting them to revenue targets.
modal
by eyadsibai
Use when "Modal", "serverless GPU", "cloud GPU", "deploy ML model", or asking about "serverless containers", "GPU compute", "batch processing", "scheduled jobs", "autoscaling ML"
funsloth-upload
by chrisvoncsefalvay
Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation
tavus-replica
by Tavus-Engineering
Create and manage Tavus replicas (AI digital twins). Use when training custom replicas from video, listing stock replicas, or managing replica assets. Covers training video requirements, consent statements, and the Phoenix-3 model.
tavus-overview
by Tavus-Engineering
Overview of Tavus, the AI research lab pioneering human computing. Use when you need context about what Tavus is, their mission, core concepts like CVI and Human Computing, the model stack (Phoenix, Raven, Sparrow), or links to docs/platform/resources.
shap
by eyadsibai
Use when "SHAP", "Shapley values", "feature importance", "model explainability", or asking about "explain predictions", "interpretable ML", "feature attribution", "waterfall plot", "beeswarm plot", "model debugging"
experiment-tracking
by eyadsibai
Use when "experiment tracking", "MLflow", "Weights & Biases", "wandb", "model registry", "hyperparameter logging", "ML experiments", "training metrics"