Machine Learning

Use this skill when the user wants model-building or model-scoring tasks rather than simple statistics. Trigger it for requests such as “make it train or apply a model,” “make it generate predictions,” “make it compare model quality,” or “make it produce a submission file.” Plain-language examples: “Give me a forecasting or prediction task,” “make it output the model result file,” “make it evaluate how good the model is.”

Dingxingdi0

Machine Learning

Model Routing

Use when selecting AI models for different tasks, designing cost-aware routing (cheap→expensive cascade), implementing model fallbacks, and optimizing the capability/cost/latency tradeoff across model tiers.

kienbui19950

Machine Learning

TRL Training on Hugging Face Jobs

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

ISAQQSAI0

Machine Learning

Lean Fderiv Linearity

Proving fderiv distributes over addition, subtraction, negation, and scalar multiplication in Lean 4 / Mathlib. Use when proving curl/div/grad linearity or splitting fderiv of compound expressions.

a-bekheet0

Machine Learning

Lambda Labs Gpu Cloud

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.

adm-humanerd0

Machine Learning

Testing Strategy Blueprint

Shape layered test plans that balance coverage, speed, and confidence.

damilola-elegbede-org0

Machine Learning

Memory

Two-layer memory system with grep-based recall.

daemon3650

Machine Learning

Hkdse Divided Grading

Divided-part grading template for HKDSE elective subjects. Adapts the standard 7-phase grading workflow for exams split into multiple independently-graded parts. Each part is extracted, graded, and level-divided independently. Subject-specific skills embed this template and fill in template variables.

AKCqhzdy0

Machine Learning

Blender Pro Character Pipeline

Build or polish character models in Blender to professional quality with strict gates for silhouette, topology, materials, rigging, natural animation, and export validation. Use when users ask for high-quality character creation before final export.

aki-27to0

Machine Learning

Smart Model Switching

Auto-route tasks to cheapest model. Multi-provider: GLM (Flash→Standard→Plus) + Qwen (Coder→Flash). Routes coding to kiro-cli.

akzedevops0

Machine Learning

Researching Programs

系統性研究目標學校的 AI/MLOps/AI Infra 碩士學程——課程結構、師資、研究方向、產學合作、校友出路。用於選校決策前的資訊收集。

Alanlee03230

Machine Learning

Learn

Intelligent lesson capture with novelty detection and usefulness filtering

EndUser1230

Machine Learning

Gsd Set Profile

Switch model profile for GSD agents (quality/balanced/budget/inherit)

amanjeet2330

Machine Learning

Gsd Set Profile

Switch model profile for GSD agents (quality/balanced/budget/inherit)

amanjeet2330

Machine Learning

Data Science

Universal data science skill covering ML model development, feature engineering, experimentation design, model evaluation, and productionizing models. Apply when building predictive models, recommendation systems, NLP pipelines, or ML-powered features.

Amitavpanda0

Machine Learning

Trading Agent

Use when modifying or analyzing the hybrid forex/crypto trading bot that combines MT5 execution, LightGBM signals, Backtrader validation, and a multiagent voting layer.

Artesania-Honuras0

Machine Learning

ML Engineer Agent

Design and implement ML models, training pipelines, inference services, and data labeling workflows. Trigger keywords: "machine learning", "ML model", "anomaly detection", "video analytics", "object detection", "classification", "training pipeline", "inference", "model serving", "ONNX", "TensorFlow", "PyTorch", "computer vision", "time series anomaly", "predictive maintenance", "model deployment", "A/B test model", "data labeling", "feature engineering", "model monitoring", "drift detection", "MLOps". NOT for data pipelines (use data-engineer) or infrastructure (use devops-agent).

asalhamed0

Machine Learning

Hydrodynamics Skill

Implements hydrodynamics for the bubbling fluidized bed gasifier, including minimum fluidization velocity, bubble dynamics, and K_bd inter-phase mass transfer. Use when implementing or modifying calc_hydrodynamics, K_bd, bubble velocity, or U_mf-related logic in the BFB 1D model.

dachou52240

Machine Learning

Postgresql Persistence Design

Use this skill when modeling data, writing repositories, or configuring persistence.

DABO-ERP0

Machine Learning

Evolution Engine — System Intelligence & Continuous Improvement

Self-improving intelligence layer for Tory Owens' Life OS. Dispatches 7 parallel domain scouts to scan the external world, evaluates findings against Tory's context, auto-implements low-risk upgrades (Tier 1), queues high-risk changes for review (Tier 2), and feeds intelligence into the COP, morning sweep, and sentinel engine. Triggers on: "Evolution sweep", "Run the evolution engine", "System evolution", "What's new out there", "Upgrade scan", "Intelligence sweep". Runs autonomously on schedule: Sunday 2000 + Wednesday 2000.

dabrewskie0

Machine Learning

scikit-survival: Survival Analysis in Python

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library. Also use for 生存分析, time-to-event, Kaplan-Meier, Cox 回归, competing risks, censored data, and paper-ready survival modeling.

BKZhao0

Machine Learning

Bmad Bmm Correct Course

bmad-bmm-correct-course skill

blackisthelight0

Machine Learning

Bmad Tea Testarch Framework

bmad-tea-testarch-framework skill

blackisthelight0

Machine Learning

Image Generation Prompting Skill

This skill should be used when the user asks to "generate an image", "create a picture", "make an illustration", "edit this image", "upscale", or any request involving AI image generation, nanobanana, nano banana, visual grounding, prompt engineering, or image editing. Provides model selection guidance (Flash/NB2/Pro), prompt engineering techniques, visual grounding best practices, resolution and cost optimization, and multi-image editing workflows for the Nano Banana MCP server (Gemini image models).

bloknayrb0

Machine Learning

F1 Market Analysis

Translate a Formula 1 thesis into market-specific logic for qualifying H2H, race H2H, top-6, top-10, and selective outright markets. Use after the F1 weekend read is built and the timing mode is already fixed.

BlueDark670

Machine Learning