Skill UI

torchforge is Meta's advanced PyTorch-native library designed for agentic Reinforcement Learning (RL). It fundamentally separates core RL algorithms from complex distributed infrastructure concerns. This allows researchers to rapidly prototype and experiment with novel RL methods (like GRPO) using clean, PyTorch-native abstractions, while automatically handling large-scale tasks like distributed training across thousands of GPUs using Monarch and TorchTitan.

Production-ready guidance on adopting Http.ai SDK design patterns for TypeScript and Python, covering singleton clients, safe wrappers, retries, and validation to standardize Vast.ai integrations and improve API reliability.

Design and implement API versioning with routers, compatibility layers, deprecation headers, breaking-change detection, tests, and migration docs to keep APIs backward-compatible while evolving.

Automated versioning strategy helper that activates on API development requests, guiding best practices, code/config generation, and validation for REST, GraphQL, OpenAPI, authentication, and API design patterns.

Designs and builds production-ready real-time voice agents with OpenAI Realtime, Vapi, Deepgram, ElevenLabs, LiveKit, and WebRTC, optimizing for latency, audio quality, and responsive UX.

Automates guidance for designing and deploying webhook senders, covering integration patterns, SDK generation, and production-ready configurations.

Guides non-developers through Zapier and Make automation patterns, platform selection, reliability practices, branching, and data transformation so they can design resilient workflows and know when to switch to code-based solutions.

A comprehensive guide for designing and implementing production-grade microservices using gRPC in Go. Covers best practices for API contract standardization with Protobuf and Buf, securing service-to-service communication via mTLS, and integrating deep observability using OpenTelemetry interceptors. Ideal for building high-performance, reliable internal APIs.

Generates high-fidelity mobile and web UI/UX mockups with atomic design principles, responsive layouts, and accessible design tokens via muapi.ai for product requirements that need professional wireframes or design systems.

Guides use of the Adaptyv Bio Foundry API and Python SDK to design protein experiments, submit sequences, automate workflows, and fetch BLI/SPR or thermostability assay results via authenticated requests for lab-ready studies.

Combines ESM3 and ESM C protein language models to generate sequences, predict structures, condition functions, and extract embeddings via local or Forge API inference for protein design and engineering workflows.

A specialized assistant designed to act as a senior software architect. It critiques code generated by AI tools or rapidly prototyped code, moving beyond simple syntax checks. The auditor identifies deep structural flaws, technical debt, architectural weaknesses, and production risks (e.g., security vulnerabilities, poor error handling, tight coupling) that make code fragile or unsuitable for deployment.