Machine Learning Skills

Extracts and tracks the consumed token usage from an LLM API response to monitor API cost and utilization.

Work with tectonic plate boundary datasets (PB2002 format) to identify plate regions, extract specific plate boundaries, and perform spatial filtering. Load plate boundary and plate polygon data, identify specific plates like the Pacific plate, and extract relevant boundaries. Use this skill when parsing plate tectonics datasets, identifying plate regions from boundary lines, or filtering spatial data by plate membership.

Set up Python environment for PyTorch-based NLP projects with transformers and alignment training. Use this skill when initializing project environments, managing dependencies from environment.yml files, installing required packages, and ensuring CUDA/device compatibility. Essential for reproducible machine learning research requiring specific package versions.

Run PyTorch unit tests, save results to NumPy files, and log environment information for reproducibility. Use this skill when executing test suites for neural network functions, validating loss computations, saving tensor outputs for verification, and creating reproducibility logs with Python/package versions.

Guidelines for implementing the SimPO (Simple Preference Optimization) loss function for NLP model training. Use this skill when modifying trainers or implementing preference-based loss functions in transformer projects.

Computing RMSE (Root Mean Squared Error) and other metrics for water temperature model validation. Use this skill whenever you need to match simulated temperatures with field observations, compute RMSE by depth categories, calculate annual/seasonal subsets, or prepare model evaluation metrics. Essential for lake model calibration and validation workflows.

Set up Python environments for NLP/ML projects using PyTorch, transformers, and TRL. Use this skill when installing dependencies for preference optimization, RLHF, or transformer-based training pipelines.

Procedures for performing precise distance calculations between points and geometries using GeoPandas. Use this skill when calculating distances in kilometers, reprojecting GeoDataFrames, or finding the nearest features in a geospatial dataset.

Techniques for processing tectonic plate data, specifically using the PB2002 dataset. Use this skill when filtering points within plates, identifying plate boundaries, or working with global tectonic geometries in GeoPandas.

How to optimize DBSCAN hyperparameters for Mars cloud clustering. Use this skill whenever performing grid search, DBSCAN clustering, or evaluating F1 and delta for Mars datasets.

> Handles loading and processing of earthquake and plate boundary data. Use this for reading, filtering, and joining geospatial datasets related to tectonics (plates, boundaries, earthquake points).

Procedures for setting up the environment for research projects involving Python, PyTorch, and NLP models. Use whenever environment requirements (environment.yml) are present.

How to calculate and save GLM performance metrics (RMSE) to metrics.json. Use this whenever the user asks for RMSE checks or final model evaluation.

How to implement custom loss functions in PyTorch. Use this skill whenever the user asks to implement a loss function, write a custom criterion, or mentions PyTorch tensor operations for backpropagation.

invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.

Automates the Karpathy LLM Wiki workflow: turns web, GitHub, and YouTube URLs into well-structured, citable, wikilinked pages with automatic linting and sourcing — invoke with /pin-llm-wiki

Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding. Use after a review run, when the user wants to reduce false positives, before fix-llm-artifacts on dead code, or when validating a full-project scan.

Use this skill whenever a question should be answered from documents stored in a LlamaCloud Index v2 knowledge base — retrieving passages, locating indexed files, or searching indexed content through the LlamaParse Platform REST API with curl. Teaches agentic retrieval — navigating an index like a file system instead of one-shot RAG.

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific dom...

Use when improving documentation structure, accuracy, and RAG readiness.

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debug...

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, buildin...

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or ...

Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management. Always search tools first for current schemas.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, ...

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Update the llms.txt file in the root folder to reflect changes in documentation or specifications following the llms.txt specification at https://llmstxt.org/

Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.

Automate Mistral AI operations -- manage files and libraries, upload documents for fine-tuning, batch processing, and OCR, track fine-tuning jobs, and build RAG pipelines via the Composio MCP integration.

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks

Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tok...

环境准备。安装依赖、下载模型、验证环境。触发词：安装、环境准备、初始化