awesome-claude-skills
Machine Learning
313 skills in this domain
Table of Contents
- Model Training - 198 skills
- Hyperparameter Tuning - 63 skills
- Model Evaluation - 21 skills
- Feature Engineering - 20 skills
- Model Deployment - 11 skills
Model Training
198 skills
| Skill | Description | Author |
|---|---|---|
| apktool | Android APK unpacking and resource extraction tool for reverse engineering. Use when you need to … | BrownFineSecurity |
| assemblyai-upgrade-migration | Analyze, plan, and execute AssemblyAI SDK upgrades with breaking change detection. Use when upgra… | jeremylongshore |
| assemblyai-upgrade-migration | Analyze, plan, and execute AssemblyAI SDK upgrades with breaking change detection. Use when upgra… | jeremylongshore |
| bug-clustering | Internal process for the bug-clusterer agent. Defines the step-by-step procedure for parsing, cla… | jeremylongshore |
| bug-clustering | Internal process for the bug-clusterer agent. Defines the step-by-step procedure for parsing, cla… | jeremylongshore |
| ceo-advisor | Executive leadership guidance for strategic decision-making, organizational development, and stak… | davila7 |
| cirq | Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing nois… | K-Dense-AI |
| clade-multi-env-setup | Configure Claude across dev, staging, and production with different Use when working with multi-e… | jeremylongshore |
| clade-multi-env-setup | Configure Claude across dev, staging, and production with different Use when working with multi-e… | jeremylongshore |
| clade-upgrade-migration | Upgrade Anthropic SDK versions and migrate between Claude model generations. Use when working wit… | jeremylongshore |
| clade-upgrade-migration | Upgrade Anthropic SDK versions and migrate between Claude model generations. Use when working wit… | jeremylongshore |
| clip | OpenAI’s model connecting vision and language. Enables zero-shot image classification, image-text… | zechenzhangAGI |
| clip | OpenAI’s model connecting vision and language. Enables zero-shot image classification, image-text… | davila7 |
| cobrapy | Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models… | K-Dense-AI |
| cobrapy | Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models… | davila7 |
| coderabbit-core-workflow-b | Tune CodeRabbit review configuration: learnings, code guidelines, and noise reduction. Use when f… | jeremylongshore |
| coderabbit-core-workflow-b | Tune CodeRabbit review configuration: learnings, code guidelines, and noise reduction. Use when f… | jeremylongshore |
| confusion-matrix-generator | Confusion Matrix Generator - Auto-activating skill for ML Training. Triggers on: confusion matrix… | jeremylongshore |
| confusion-matrix-generator | Generate confusion matrix generator operations. Auto-activating skill for ML Training. Triggers o… | jeremylongshore |
| constitutional-ai | Anthropic’s method for training harmless AI through self-improvement. Two-phase approach - superv… | zechenzhangAGI |
| constitutional-ai | Anthropic’s method for training harmless AI through self-improvement. Two-phase approach - superv… | davila7 |
| coreweave-core-workflow-b | Run distributed GPU training jobs on CoreWeave with multi-node PyTorch. Use when training models … | jeremylongshore |
| coreweave-core-workflow-b | Run distributed GPU training jobs on CoreWeave with multi-node PyTorch. Use when training models … | jeremylongshore |
| cross-validation-setup | Cross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation set… | jeremylongshore |
| cross-validation-setup | Cross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation set… | jeremylongshore |
| cursor-model-selection | Configure and select AI models in Cursor for Chat, Composer, and Agent mode. Triggers on “cursor … | jeremylongshore |
| cursor-model-selection | Configure and select AI models in Cursor for Chat, Composer, and Agent mode. Triggers on “cursor … | jeremylongshore |
| cursor-sso-integration | Configure SAML 2.0 and OIDC SSO for Cursor with Okta, Microsoft Entra ID, and Google Workspace. T… | jeremylongshore |
| cursor-sso-integration | Configure SAML 2.0 and OIDC SSO for Cursor with Okta, Microsoft Entra ID, and Google Workspace. T… | jeremylongshore |
| deepchem | Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), Mole… | davila7 |
| design-everyday-things | Apply foundational design principles: affordances, signifiers, constraints, feedback, and concept… | jeremylongshore |
| design-everyday-things | Apply foundational design principles: affordances, signifiers, constraints, feedback, and concept… | jeremylongshore |
| distributed-llm-pretraining-torchtitan | Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, … | zechenzhangAGI |
| distributed-llm-pretraining-torchtitan | Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, … | davila7 |
| distributed-training-ray-train | davila7 | |
| distributed-training-setup | Configure distributed training setup operations. Auto-activating skill for ML Training. Triggers … | jeremylongshore |
| distributed-training-setup | Distributed Training Setup - Auto-activating skill for ML Training. Triggers on: distributed trai… | jeremylongshore |
| domain-driven-design | Plan and route Domain-Driven Design work from strategic modeling to tactical implementation and e… | davila7 |
| early-stopping-callback | Manage early stopping callback operations. Auto-activating skill for ML Training. Triggers on: ea… | jeremylongshore |
| early-stopping-callback | Manage early stopping callback operations. Auto-activating skill for ML Training. Triggers on: ea… | jeremylongshore |
| ElevenLabs Automation | Automate ElevenLabs text-to-speech workflows – generate speech from text, browse and inspect voi… | ComposioHQ |
| email-drafting | Draft email replies for Gonto’s Gmail accounts (m@gon.to, gonto@hypergrowthpartners.com). Handles… | jeremylongshore |
| email-drafting | Draft email replies for Gonto’s Gmail accounts (m@gon.to, gonto@hypergrowthpartners.com). Handles… | jeremylongshore |
| error-patterns | Error handling patterns: classification, recovery, logging, graceful degradation, resilience. | athola |
| escalation-governance | Assess whether to escalate models. Use when evaluating reasoning depth. | athola |
| event-sourcing-architect | Expert in event sourcing, CQRS, and event-driven architecture patterns. Masters event store desig… | davila7 |
| example-skill | Brief description of what this skill does and when the model should activate it. Use when [descri… | jeremylongshore |
| example-skill | Brief description of what this skill does and when the model should activate it. Use when [descri… | jeremylongshore |
| excel-dcf-modeler | Build discounted cash flow (DCF) valuation models in Excel. Use when creating DCF models, calcula… | jeremylongshore |
| excel-dcf-modeler | Build discounted cash flow (DCF) valuation models in Excel. Use when creating DCF models, calcula… | jeremylongshore |
| excel-lbo-modeler | Build leveraged buyout (LBO) models in Excel with debt schedules and IRR analysis. Use when struc… | jeremylongshore |
| excel-lbo-modeler | Build leveraged buyout (LBO) models in Excel with debt schedules and IRR analysis. Use when struc… | jeremylongshore |
| experiment-tracking-swanlab | Provides guidance for experiment tracking with SwanLab. Use when you need open-source run trackin… | zechenzhangAGI |
| fantasy-lineup-optimizer | Analyze matchups, injuries, weather, Vegas lines. Recommend sit/start decisions with confidence l… | OneWave-AI |
| feature-engineering-helper | Configure with feature engineering helper operations. Auto-activating skill for ML Training. Trig… | jeremylongshore |
| feature-engineering-helper | Feature Engineering Helper - Auto-activating skill for ML Training. Triggers on: feature engineer… | jeremylongshore |
| feature-importance-analyzer | Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importa… | jeremylongshore |
| feature-importance-analyzer | Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importa… | jeremylongshore |
| feedback-mastery | Navigate difficult conversations and deliver constructive feedback using structured frameworks. C… | davila7 |
| flyio-core-workflow-a | Execute Fly.io primary workflow: deploy, scale, and manage apps with flyctl and fly.toml. Use whe… | jeremylongshore |
| flyio-core-workflow-a | Execute Fly.io primary workflow: deploy, scale, and manage apps with flyctl and fly.toml. Use whe… | jeremylongshore |
| generate-image | Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image gene… | K-Dense-AI |
| generate-image | Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation … | davila7 |
| gradient-clipping-helper | Gradient Clipping Helper - Auto-activating skill for ML Training. Triggers on: gradient clipping … | jeremylongshore |
| gradient-clipping-helper | Configure with gradient clipping helper operations. Auto-activating skill for ML Training. Trigge… | jeremylongshore |
| groq-upgrade-migration | Upgrade groq-sdk versions and handle Groq model deprecations. Use when upgrading SDK versions, de… | jeremylongshore |
| groq-upgrade-migration | Upgrade groq-sdk versions and handle Groq model deprecations. Use when upgrading SDK versions, de… | jeremylongshore |
| grpo-rl-training | Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training | zechenzhangAGI |
| grpo-rl-training | Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training | davila7 |
| happy-audio-gen | Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenL… | iamzhihuix |
| huggingface-best | Use when the user asks about finding the best, top, or recommended model for a task, wants to kno… | huggingface |
| hyperparameter-tuner | Manage hyperparameter tuner operations. Auto-activating skill for ML Training. Triggers on: hyper… | jeremylongshore |
| hyperparameter-tuner | Manage hyperparameter tuner operations. Auto-activating skill for ML Training. Triggers on: hyper… | jeremylongshore |
| implementing-llms-litgpt | Implements and trains LLMs using Lightning AI’s LitGPT with 20+ pretrained architectures (Llama, … | zechenzhangAGI |
| implementing-llms-litgpt | Implements and trains LLMs using Lightning AI’s LitGPT with 20+ pretrained architectures (Llama, … | davila7 |
| langchain-core-workflow-b | Build LangChain agents with tool calling for autonomous task execution. Use when creating AI agen… | jeremylongshore |
| langchain-core-workflow-b | Build LangChain agents with tool calling for autonomous task execution. Use when creating AI agen… | jeremylongshore |
| langchain-local-dev-loop | Build a fast, deterministic local test loop for LangChain 1.0 / LangGraph 1.0 — FakeListChatModel… | jeremylongshore |
| langchain-local-dev-loop | Build a fast, deterministic local test loop for LangChain 1.0 / LangGraph 1.0 — FakeListChatModel… | jeremylongshore |
| learning-rate-scheduler | Learning Rate Scheduler - Auto-activating skill for ML Training. Triggers on: learning rate sched… | jeremylongshore |
| learning-rate-scheduler | Manage learning rate scheduler operations. Auto-activating skill for ML Training. Triggers on: le… | jeremylongshore |
| linear-enterprise-rbac | Implement enterprise role-based access control with Linear. Use when setting up team permissions,… | jeremylongshore |
| linear-enterprise-rbac | Implement enterprise role-based access control with Linear. Use when setting up team permissions,… | jeremylongshore |
| llamaguard | Meta’s 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - vi… | zechenzhangAGI |
| llamaguard | Meta’s 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - vi… | davila7 |
| marketing-psychology | When the user wants to apply psychological principles, mental models, or behavioral science to ma… | davila7 |
| miles-rl-training | Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime…. | zechenzhangAGI |
| miles-rl-training | Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime…. | davila7 |
| mindtickle-core-workflow-a | Execute MindTickle primary workflow: Training Content Management. Trigger: “mindtickle training c… | jeremylongshore |
| mindtickle-core-workflow-a | Execute MindTickle primary workflow: Training Content Management. Trigger: “mindtickle training c… | jeremylongshore |
| mixed-precision-trainer | Mixed Precision Trainer - Auto-activating skill for ML Training. Triggers on: mixed precision tra… | jeremylongshore |
| mixed-precision-trainer | Manage mixed precision trainer operations. Auto-activating skill for ML Training. Triggers on: mi… | jeremylongshore |
| ml-engineer | Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements mo… | davila7 |
| ml-training-recipes | Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging… | zechenzhangAGI |
| mlflow-tracking-setup | Mlflow Tracking Setup - Auto-activating skill for ML Training. Triggers on: mlflow tracking setup… | jeremylongshore |
| mlflow-tracking-setup | Configure mlflow tracking setup operations. Auto-activating skill for ML Training. Triggers on: m… | jeremylongshore |
| model-checkpoint-manager | Model Checkpoint Manager - Auto-activating skill for ML Training. Triggers on: model checkpoint m… | jeremylongshore |
| model-checkpoint-manager | Manage model checkpoint manager operations. Auto-activating skill for ML Training. Triggers on: m… | jeremylongshore |
| model-explainability-tool | Model Explainability Tool - Auto-activating skill for ML Training. Triggers on: model explainabil… | jeremylongshore |
| model-explainability-tool | Model Explainability Tool - Auto-activating skill for ML Training. Triggers on: model explainabil… | jeremylongshore |
| model-pruning | Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use w… | zechenzhangAGI |
| model-pruning | Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use w… | davila7 |
| moe-training | Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-sca… | zechenzhangAGI |
| moe-training | Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-sca… | davila7 |
| molfeat | Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (C… | K-Dense-AI |
| molfeat | Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (C… | davila7 |
| move-code-quality | Analyzes Move language packages against the official Move Book Code Quality Checklist. Use this s… | davila7 |
| nnsight-remote-interpretability | Provides guidance for interpreting and manipulating neural network internals using nnsight with o… | zechenzhangAGI |
| nnsight-remote-interpretability | Provides guidance for interpreting and manipulating neural network internals using nnsight with o… | davila7 |
| onboarding-checklist | Generates customized client onboarding checklists with phased tasks, ownership assignments, depen… | OneWave-AI |
| openrouter-fallback-config | Configure automatic model fallbacks for high availability on OpenRouter. Use when building resili… | jeremylongshore |
| openrouter-fallback-config | Configure automatic model fallbacks for high availability on OpenRouter. Use when building resili… | jeremylongshore |
| openrouter-function-calling | Implement function/tool calling with OpenRouter models. Use when building agents, structured outp… | jeremylongshore |
| openrouter-function-calling | Implement function/tool calling with OpenRouter models. Use when building agents, structured outp… | jeremylongshore |
| openrouter-model-availability | Monitor OpenRouter model availability and implement health checks. Use when building systems that… | jeremylongshore |
| openrouter-model-availability | Monitor OpenRouter model availability and implement health checks. Use when building systems that… | jeremylongshore |
| openrouter-model-routing | Implement intelligent model routing to optimize cost, quality, and latency on OpenRouter. Use whe… | jeremylongshore |
| openrouter-model-routing | Implement intelligent model routing to optimize cost, quality, and latency on OpenRouter. Use whe… | jeremylongshore |
| openrouter-pricing-basics | Understand OpenRouter pricing, calculate costs, and optimize spend. Use when budgeting, comparing… | jeremylongshore |
| openrouter-pricing-basics | Understand OpenRouter pricing, calculate costs, and optimize spend. Use when budgeting, comparing… | jeremylongshore |
| optuna-study-creator | Create optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optun… | jeremylongshore |
| optuna-study-creator | Optuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, … | jeremylongshore |
| pennylane | Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum … | K-Dense-AI |
| phylogenetics | Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelih… | K-Dense-AI |
| plantuml-diagram-generator | Plantuml Diagram Generator - Auto-activating skill for Visual Content. Triggers on: plantuml diag… | jeremylongshore |
| plantuml-diagram-generator | Generate plantuml diagram generator operations. Auto-activating skill for Visual Content. Trigger… | jeremylongshore |
| playwright-java | Scaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Obje… | davila7 |
| presenting-conference-talks | Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled pap… | zechenzhangAGI |
| proof-design | Design QA audit — red flags, severity classification, visual quality scorecard. Use when asked to… | jeremylongshore |
| proof-design | Design QA audit — red flags, severity classification, visual quality scorecard. Use when asked to… | jeremylongshore |
| pydantic-ai | Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, depend… | davila7 |
| pymoo | Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint hand… | K-Dense-AI |
| pymoo | Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint hand… | davila7 |
| python-packaging | Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and … | wshobson |
| pytorch-fsdp2 | Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision… | zechenzhangAGI |
| pytorch-lightning | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpe… | zechenzhangAGI |
| pytorch-lightning | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpe… | davila7 |
| pytorch-model-trainer | Pytorch Model Trainer - Auto-activating skill for ML Training. Triggers on: pytorch model trainer… | jeremylongshore |
| pytorch-model-trainer | Build pytorch model trainer operations. Auto-activating skill for ML Training. Triggers on: pytor… | jeremylongshore |
| qiskit | Comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits…. | davila7 |
| QuickBooks Automation | QuickBooks Automation: manage invoices, customers, accounts, and payments in QuickBooks Online fo… | ComposioHQ |
| quota-setting-calculator | Top-down vs bottom-up quota models. Historical attainment, market growth assumptions, ramp period… | OneWave-AI |
| ray-train | Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from la… | zechenzhangAGI |
| risk-classification | 4-tier risk classification for agent tasks. GREEN/YELLOW heuristic, RED/CRITICAL escalate to war-… | athola |
| roc-curve-plotter | Roc Curve Plotter - Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc cu… | jeremylongshore |
| roc-curve-plotter | Manage roc curve plotter operations. Auto-activating skill for ML Training. Triggers on: roc curv… | jeremylongshore |
| scientific-schematics | Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refine… | K-Dense-AI |
| scientific-schematics | Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refi… | davila7 |
| seaborn | Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation ma… | davila7 |
| security-requirement-extraction | Derive security requirements from threat models and business context. Use when translating threat… | wshobson |
| segment-anything-model | Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any… | zechenzhangAGI |
| segment-anything-model | Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any… | davila7 |
| sglang | Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/… | zechenzhangAGI |
| sglang | Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/… | davila7 |
| skill-share | A skill that creates new Claude skills and automatically shares them on Slack using Rube for seam… | ComposioHQ |
| skill-share | A skill that creates new Claude skills and automatically shares them on Slack using Rube for seam… | davila7 |
| slides-creator | Narrative-first slide deck creation. Guides users through structured narrative design (ABCDEFG mo… | daymade |
| snowflake-enterprise-rbac | Configure Snowflake enterprise RBAC with system roles, custom role hierarchies, SSO/SCIM integrat… | jeremylongshore |
| snowflake-enterprise-rbac | Configure Snowflake enterprise RBAC with system roles, custom role hierarchies, SSO/SCIM integrat… | jeremylongshore |
| sparse-autoencoder-training | Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompos… | zechenzhangAGI |
| sparse-autoencoder-training | Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompos… | davila7 |
| speak-core-workflow-b | Execute Speak secondary workflow: Pronunciation Training with phoneme-level analysis. Use when im… | jeremylongshore |
| speak-core-workflow-b | Execute Speak secondary workflow: Pronunciation Training with phoneme-level analysis. Use when im… | jeremylongshore |
| sprint-workflow | Execute this skill should be used when the user asks about “how sprints work”, “sprint phases”, “… | jeremylongshore |
| sprint-workflow | Execute this skill should be used when the user asks about “how sprints work”, “sprint phases”, “… | jeremylongshore |
| startup-financial-modeling | Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flo… | wshobson |
| stride-analysis-patterns | Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, … | wshobson |
| tensorboard-visualizer | Tensorboard Visualizer - Auto-activating skill for ML Training. Triggers on: tensorboard visualiz… | jeremylongshore |
| tensorboard-visualizer | Generate tensorboard visualizer operations. Auto-activating skill for ML Training. Triggers on: t… | jeremylongshore |
| tensorflow-model-trainer | Build tensorflow model trainer operations. Auto-activating skill for ML Training. Triggers on: te… | jeremylongshore |
| tensorflow-model-trainer | Build tensorflow model trainer operations. Auto-activating skill for ML Training. Triggers on: te… | jeremylongshore |
| territory-planning-optimizer | Account assignment by revenue potential, geography, relationship. Workload balancing, TAM/SAM cal… | OneWave-AI |
| threat-model-creator | Create threat model creator operations. Auto-activating skill for Security Advanced. Triggers on:… | jeremylongshore |
| threat-model-creator | Create threat model creator operations. Auto-activating skill for Security Advanced. Triggers on:… | jeremylongshore |
| torchforge-rl-training | Provides guidance for PyTorch-native agentic RL using torchforge, Meta’s library separating infra… | zechenzhangAGI |
| torchforge-rl-training | Provides guidance for PyTorch-native agentic RL using torchforge, Meta’s library separating infra… | davila7 |
| train-test-splitter | Train Test Splitter - Auto-activating skill for ML Training. Triggers on: train test splitter, tr… | jeremylongshore |
| train-test-splitter | Test train test splitter operations. Auto-activating skill for ML Training. Triggers on: train te… | jeremylongshore |
| unsloth | Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoR… | zechenzhangAGI |
| unsloth | Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoR… | davila7 |
| vastai-core-workflow-a | Execute Vast.ai primary workflow: GPU instance provisioning and job execution. Use when renting G… | jeremylongshore |
| vastai-core-workflow-a | Execute Vast.ai primary workflow: GPU instance provisioning and job execution. Use when renting G… | jeremylongshore |
| vastai-core-workflow-b | Execute Vast.ai secondary workflow: multi-instance orchestration, spot recovery, and cost optimiz… | jeremylongshore |
| vastai-core-workflow-b | Execute Vast.ai secondary workflow: multi-instance orchestration, spot recovery, and cost optimiz… | jeremylongshore |
| vercel-enterprise-rbac | Configure Vercel enterprise RBAC, access groups, SSO integration, and audit logging. Use when imp… | jeremylongshore |
| vercel-enterprise-rbac | Configure Vercel enterprise RBAC, access groups, SSO integration, and audit logging. Use when imp… | jeremylongshore |
| wandb-experiment-logger | Wandb Experiment Logger - Auto-activating skill for ML Training. Triggers on: wandb experiment lo… | jeremylongshore |
| wandb-experiment-logger | Wandb Experiment Logger - Auto-activating skill for ML Training. Triggers on: wandb experiment lo… | jeremylongshore |
| warden | Security engineer — IAM, secrets, threat modeling, hardening, auth, and supply chain security. | jeremylongshore |
| warden | Security engineer — IAM, secrets, threat modeling, hardening, auth, and supply chain security. | jeremylongshore |
| whisper | OpenAI’s general-purpose speech recognition model. Supports 99 languages, transcription, translat… | zechenzhangAGI |
| whisper | OpenAI’s general-purpose speech recognition model. Supports 99 languages, transcription, translat… | davila7 |
| windsurf-enterprise-rbac | Configure Windsurf enterprise SSO, RBAC, and organization-level controls. Use when implementing S… | jeremylongshore |
| windsurf-enterprise-rbac | Configure Windsurf enterprise SSO, RBAC, and organization-level controls. Use when implementing S… | jeremylongshore |
| windsurf-enterprise-sso | Configure enterprise SSO integration for Windsurf. Activate when users mention “sso configuration… | jeremylongshore |
| windsurf-enterprise-sso | Configure enterprise SSO integration for Windsurf. Activate when users mention “sso configuration… | jeremylongshore |
| windsurf-rate-limits | Understand and manage Windsurf credit system, usage limits, and model selection. Use when running… | jeremylongshore |
| windsurf-rate-limits | Understand and manage Windsurf credit system, usage limits, and model selection. Use when running… | jeremylongshore |
Hyperparameter Tuning
63 skills
| Skill | Description | Author |
|---|---|---|
| ai-product | Every product will be AI-powered. The question is whether you’ll build it right or ship a demo th… | davila7 |
| athlete-social-media-manager | Create brand-safe content for athletes. Personal branding strategy, engagement optimization, cris… | OneWave-AI |
| bigml-automation | Automate Bigml tasks via Rube MCP (Composio). Always search tools first for current schemas. | ComposioHQ |
| capa-officer | Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Mana… | davila7 |
| castai-core-workflow-a | Configure CAST AI autoscaler policies and node templates for cost optimization. Use when enabling… | jeremylongshore |
| castai-core-workflow-a | Configure CAST AI autoscaler policies and node templates for cost optimization. Use when enabling… | jeremylongshore |
| cirq | Quantum computing framework for building, simulating, optimizing, and executing quantum circuits…. | davila7 |
| claude-md-improver | Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, im… | anthropics |
| clerk-cost-tuning | Optimize Clerk costs and understand pricing. Use when planning budget, reducing costs, or underst… | jeremylongshore |
| clerk-cost-tuning | Optimize Clerk costs and understand pricing. Use when planning budget, reducing costs, or underst… | jeremylongshore |
| coderabbit-cost-tuning | Optimize CodeRabbit costs through seat management, repo selection, and review scope tuning. Use w… | jeremylongshore |
| coderabbit-cost-tuning | Optimize CodeRabbit costs through seat management, repo selection, and review scope tuning. Use w… | jeremylongshore |
| content-creator | Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer… | davila7 |
| context-optimization | Optimize context window via MECW principles, memory tiering, and subagent coordination. | athola |
| elevenlabs-cost-tuning | Optimize ElevenLabs costs through model selection, character-efficient patterns, caching, and usa… | jeremylongshore |
| elevenlabs-cost-tuning | Optimize ElevenLabs costs through model selection, character-efficient patterns, caching, and usa… | jeremylongshore |
| embedding-strategies | Select and optimize embedding models for semantic search and RAG applications. Use when choosing … | wshobson |
| geo-fundamentals | Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity). | davila7 |
| glycoengineering | Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T),… | K-Dense-AI |
| godot-gdscript-patterns | Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization. Use… | wshobson |
| klingai-pricing-basics | Understand Kling AI pricing, credits, and cost optimization strategies. Use when budgeting or est… | jeremylongshore |
| klingai-pricing-basics | Understand Kling AI pricing, credits, and cost optimization strategies. Use when budgeting or est… | jeremylongshore |
| knowledge-base-builder | FAQ identification from support tickets, step-by-step tutorial creation, screenshot/video script … | OneWave-AI |
| lindy-cost-tuning | Optimize Lindy AI costs through credit management, model selection, and agent consolidation. Use … | jeremylongshore |
| lindy-cost-tuning | Optimize Lindy AI costs through credit management, model selection, and agent consolidation. Use … | jeremylongshore |
| llama-factory | Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8… | zechenzhangAGI |
| llama-factory | Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8… | davila7 |
| llava | Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversati… | zechenzhangAGI |
| llava | Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversati… | davila7 |
| metacognitive-self-mod | Analyze and improve the improvement process. Use for detecting quality regressions and refining m… | athola |
| mistral_ai-automation | Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and mode… | ComposioHQ |
| ml-paper-writing | Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting … | zechenzhangAGI |
| ml-paper-writing | Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting … | davila7 |
| modelry-automation | Automate Modelry tasks via Rube MCP (Composio). Always search tools first for current schemas. | ComposioHQ |
| navan-cost-tuning | Use when optimizing travel spend with Navan’s policy engine, analyzing booking patterns for savin… | jeremylongshore |
| navan-cost-tuning | Use when optimizing travel spend with Navan’s policy engine, analyzing booking patterns for savin… | jeremylongshore |
| onboarding-cro | When the user wants to optimize post-signup onboarding, user activation, first-run experience, or… | davila7 |
| one-page-marketing | Build a complete marketing plan covering the full customer journey from stranger to raving fan. U… | jeremylongshore |
| one-page-marketing | Build a complete marketing plan covering the full customer journey from stranger to raving fan. U… | jeremylongshore |
| openrouter-context-optimization | Optimize context window usage for OpenRouter models to reduce cost and improve quality. Use when … | jeremylongshore |
| openrouter-context-optimization | Optimize context window usage for OpenRouter models to reduce cost and improve quality. Use when … | jeremylongshore |
| pricing-strategy | Designs pricing strategies for products and services. Takes product/service, costs, target market… | OneWave-AI |
| progressive-loading | Progressive module loading with hub-and-spoke pattern for token optimization. Lazy loading. | athola |
| prompt-engineering | Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use whe… | davila7 |
| qiskit | IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Run… | K-Dense-AI |
| quality-manager-qms-iso13485 | ISO 13485 Quality Management System specialist for medical device companies. Provides QMS impleme… | davila7 |
| rag-implementation | Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrie… | davila7 |
| referral-program | When the user wants to create, optimize, or analyze a referral program, affiliate program, or wor… | davila7 |
| schema-optimization-orchestrator | Multi-phase schema optimization workflow orchestrator. Creates session directories, spawns phase … | jeremylongshore |
| schema-optimization-orchestrator | Multi-phase schema optimization workflow orchestrator. Creates session directories, spawns phase … | jeremylongshore |
| sentry-cost-tuning | Optimize Sentry costs, reduce event volume, and manage quota spend. Use when analyzing Sentry bil… | jeremylongshore |
| sentry-cost-tuning | Optimize Sentry costs, reduce event volume, and manage quota spend. Use when analyzing Sentry bil… | jeremylongshore |
| SEO Optimizer | Search Engine Optimization specialist for content strategy, technical SEO, keyword research, and … | davila7 |
| simla-com-automation | Automate Simla Com tasks via Rube MCP (Composio). Always search tools first for current schemas. | ComposioHQ |
| statistical-analysis | Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlati… | davila7 |
| windsurf-cascade-context | Manage Cascade context window and memory for complex projects. Activate when users mention “casca… | jeremylongshore |
| windsurf-cascade-context | Manage Cascade context window and memory for complex projects. Activate when users mention “casca… | jeremylongshore |
| windsurf-code-completion | Configure and optimize Supercomplete code suggestions. Activate when users mention “code completi… | jeremylongshore |
| windsurf-code-completion | Configure and optimize Supercomplete code suggestions. Activate when users mention “code completi… | jeremylongshore |
| windsurf-license-management | Manage Windsurf licenses and seat allocation. Activate when users mention “license management”, “… | jeremylongshore |
| windsurf-license-management | Manage Windsurf licenses and seat allocation. Activate when users mention “license management”, “… | jeremylongshore |
| yt-packaging | Create optimized YouTube titles and thumbnail concepts for maximum CTR. Use this skill whenever t… | jeremylongshore |
| yt-packaging | Create optimized YouTube titles and thumbnail concepts for maximum CTR. Use this skill whenever t… | jeremylongshore |
Model Evaluation
21 skills
| Skill | Description | Author |
|---|---|---|
| coreweave-hello-world | Deploy a GPU workload on CoreWeave with kubectl. Use when running your first GPU job, testing inf… | jeremylongshore |
| coreweave-hello-world | Deploy a GPU workload on CoreWeave with kubectl. Use when running your first GPU job, testing inf… | jeremylongshore |
| e2e-testing-patterns | Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship cod… | davila7 |
| evaluating-cosmos-policy | Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting u… | zechenzhangAGI |
| freelancer-review | Reviews contracts from a freelancer’s perspective across 14 evaluation lenses including misclassi… | jeremylongshore |
| freelancer-review | Reviews contracts from a freelancer’s perspective across 14 evaluation lenses including misclassi… | jeremylongshore |
| groq-core-workflow-b | Execute Groq secondary workflows: audio transcription (Whisper), vision, text-to-speech, and batc… | jeremylongshore |
| groq-core-workflow-b | Execute Groq secondary workflows: audio transcription (Whisper), vision, text-to-speech, and batc… | jeremylongshore |
| langchain-prompt-engineering | Manage LangChain 1.0 prompts like code — LangSmith prompt hub versioning, XML-tag conventions for… | jeremylongshore |
| langchain-prompt-engineering | Manage LangChain 1.0 prompts like code — LangSmith prompt hub versioning, XML-tag conventions for… | jeremylongshore |
| mdr-745-specialist | EU MDR 2017/745 regulation specialist and consultant for medical device requirement management. P… | davila7 |
| obsidian-local-dev-loop | Set up a fast Obsidian plugin development loop with hot reload. Covers cloning the sample plugin,… | jeremylongshore |
| obsidian-local-dev-loop | Set up a fast Obsidian plugin development loop with hot reload. Covers cloning the sample plugin,… | jeremylongshore |
| optimizing-defi-yields | Find and compare DeFi yield opportunities across protocols with APY calculations, risk assessment… | jeremylongshore |
| optimizing-defi-yields | Find and compare DeFi yield opportunities across protocols with APY calculations, risk assessment… | jeremylongshore |
| qa-test-planner | Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for… | davila7 |
| statsmodels | Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnosti… | davila7 |
| surge-plg | PLG motion design — free tier definition, activation sequence, expansion trigger points, viral me… | jeremylongshore |
| surge-plg | PLG motion design — free tier definition, activation sequence, expansion trigger points, viral me… | jeremylongshore |
| threat-modeling-expert | Expert in threat modeling methodologies, security architecture review, and risk assessment. Maste… | davila7 |
| torch-geometric | Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, het… | davila7 |
Feature Engineering
20 skills
| Skill | Description | Author |
|---|---|---|
| assemblyai-cost-tuning | Optimize AssemblyAI costs through model selection, feature budgeting, and usage monitoring. Use w… | jeremylongshore |
| assemblyai-cost-tuning | Optimize AssemblyAI costs through model selection, feature budgeting, and usage monitoring. Use w… | jeremylongshore |
| castai-prod-checklist | Production readiness checklist for CAST AI cluster onboarding. Use when going live with CAST AI a… | jeremylongshore |
| castai-prod-checklist | Production readiness checklist for CAST AI cluster onboarding. Use when going live with CAST AI a… | jeremylongshore |
| clay-upgrade-migration | Navigate Clay plan changes, pricing migrations, and feature upgrades. Use when upgrading Clay pla… | jeremylongshore |
| clay-upgrade-migration | Navigate Clay plan changes, pricing migrations, and feature upgrades. Use when upgrading Clay pla… | jeremylongshore |
| coreweave-core-workflow-a | Deploy KServe InferenceService on CoreWeave with autoscaling and GPU scheduling. Use when serving… | jeremylongshore |
| coreweave-core-workflow-a | Deploy KServe InferenceService on CoreWeave with autoscaling and GPU scheduling. Use when serving… | jeremylongshore |
| groq-core-workflow-a | Execute Groq primary workflow: chat completions with tool use and JSON mode. Use when implementin… | jeremylongshore |
| groq-core-workflow-a | Execute Groq primary workflow: chat completions with tool use and JSON mode. Use when implementin… | jeremylongshore |
| klingai-model-catalog | Explore Kling AI models, versions, and capabilities for video and image generation. Use when sele… | jeremylongshore |
| klingai-model-catalog | Explore Kling AI models, versions, and capabilities for video and image generation. Use when sele… | jeremylongshore |
| klingai-upgrade-migration | Migrate between Kling AI model versions safely. Use when upgrading from v1.x to v2.x or adopting … | jeremylongshore |
| klingai-upgrade-migration | Migrate between Kling AI model versions safely. Use when upgrading from v1.x to v2.x or adopting … | jeremylongshore |
| product-analysis | Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel … | daymade |
| rails-expert | Rails 7+ specialist that optimizes Active Record queries with includes/eager_load, implements Tur… | Jeffallan |
| warden-threat | Produce a threat model — assets, ranked threats, mitigations, accepted risks. Use when asked to “… | jeremylongshore |
| warden-threat | Produce a threat model — assets, ranked threats, mitigations, accepted risks. Use when asked to “… | jeremylongshore |
| windsurf-keyboard-shortcuts | Configure custom keyboard shortcuts for Cascade and AI features. Activate when users mention “key… | jeremylongshore |
| windsurf-keyboard-shortcuts | Configure custom keyboard shortcuts for Cascade and AI features. Activate when users mention “key… | jeremylongshore |
Model Deployment
11 skills
| Skill | Description | Author |
|---|---|---|
| awq-quantization | Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accura… | zechenzhangAGI |
| awq-quantization | Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accura… | davila7 |
| coreweave-webhooks-events | Monitor CoreWeave cluster events and GPU workload status. Use when tracking pod lifecycle events,… | jeremylongshore |
| coreweave-webhooks-events | Monitor CoreWeave cluster events and GPU workload status. Use when tracking pod lifecycle events,… | jeremylongshore |
| langchain-model-inference | Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on the content-block, to… | jeremylongshore |
| langchain-model-inference | Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on the content-block, to… | jeremylongshore |
| nowait-reasoning-optimizer | Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inf… | davila7 |
| pymc | Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/W… | K-Dense-AI |
| pymc-bayesian-modeling | Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/W… | davila7 |
| Replicate Automation | Automate Replicate AI model operations – run predictions, upload files, inspect model schemas, l… | ComposioHQ |
| setup | Provision the oracle inference daemon (Python 3.11+, onnxruntime via uv). | athola |