Skill UI

A comprehensive collection of patterns and best practices for automating GitHub workflows using advanced AI models. This skill enables automated PR reviews, sophisticated issue triage (labeling and commenting), and seamless integration of AI into CI/CD pipelines, significantly enhancing DevOps efficiency and code quality assurance.

This comprehensive workflow automates the entire post-meeting cycle. It enhances raw transcripts by structuring notes, extracting action items, and summarizing key decisions using advanced AI models. Users can then seamlessly share these structured notes to integrations like Slack, Notion, and CRMs (HubSpot), while also using the Chat feature to draft follow-up emails and automatically update contact records in the built-in CRM.

Configure robust CI/CD pipelines for Groq API integrations using GitHub Actions. This guide covers setting up unit tests (mocked), live integration tests, and automated model deprecation checks. It ensures that your LLM-powered application remains stable and compatible as models evolve.

The official Hugging Face Hub CLI (`hf`) is a comprehensive command-line tool for managing all types of resources on the Hugging Face Hub. Use it to download, upload, synchronize, and manage models, datasets, Spaces, and cloud buckets. It facilitates secure authentication, local cache management, and complex data operations, making it essential for ML workflows.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

A comprehensive guide for configuring API access across development, staging, and production environments. This setup ensures strict isolation of API keys and environment-specific parameters (like models, speed, and caching). It covers best practices for secret management using major CI/CD and secret services (GitHub Actions, AWS Secrets Manager, GCP Secret Manager).

This guide details best practices for configuring LangChain applications across development, staging, and production environments. It ensures strict environment isolation by managing separate API keys, model settings, and LangSmith project names. The setup utilizes Zod for robust validation and integrates secure secret management via GitHub Actions, AWS Secrets Manager, or GCP, guaranteeing reliable and secure deployments.

Integrate Langfuse into CI/CD pipelines (e.g., GitHub Actions) to automate the testing and validation of Large Language Models (LLMs). This guide covers prompt regression testing, tracing validation, and setting up experiment-driven quality gates, ensuring reliable and high-performing AI applications throughout the development lifecycle.

This central skill specializes in performing comprehensive threat modeling using STRIDE and calculating risk via DREAD scoring. It guides users through defining scope, identifying threats, and planning mitigations for new architectures. Crucially, it acts as a security router, directing specialized requests—such as pen-testing, incident response, cloud posture checks, and AI security reviews—to the appropriate dedicated skill.

This guide details how to integrate Vast.ai's GPU provisioning capabilities into automated CI/CD pipelines, such as GitHub Actions. It enables developers to run GPU-accelerated tests, model benchmarks, and validations automatically. Key features include robust instance lifecycle management (provisioning, running, and cleanup) and advanced cost-control mechanisms (e.g., setting budget limits) to ensure reliable and efficient testing in a cloud environment.

Molfeat is a Python toolkit that converts SMILES/RDKit molecules into embeddings via 100+ calculators, transformers, and pretrained models for QSAR, screening, similarity search, and deep learning pipelines.

A comprehensive skill for fine-tuning and training large language and vision models using advanced techniques like TRL (SFT, DPO, GRPO) or Unsloth. This process runs entirely on managed Hugging Face cloud GPUs, eliminating the need for local GPU setup. It supports modern training workflows, model conversion (GGUF for local deployment), and ensures seamless artifact storage to the Hugging Face Hub.