Agent skills for OpenAI Agents SDK

Automatically discover Modal platform skills when working with Modal.

Inspect or change Babysitter model-routing policy by phase.

Expert at writing Rails 8 models with proper validations, associations, scopes, callbacks, and concerns.

Use when choosing or changing the actual model for an AI feature in a BRICKS app — which GGUF, which quantization, which size — and when…

Generate a personalized "how to use this new model" report by mining ALL your local Claude Code sessions, then comparing your actual usage…

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

Guide for maintaining the MassGen model and backend registry.

Guidelines and workflows for community moderation, trust & safety, and

Implement or debug JavaScript language behavior, including promise completion, async iteration, mutation, and runtime compatibility.

Write modern PHP 8.x code — typed properties, enums, readonly classes, match expressions, named arguments, union/intersection types…

This skill should be used when the user wants an overview of the Modern Product Operating Model — a collection of 6 composable product…

Modern Python patterns for Modal.com serverless platform.

Generates a clean, professional single-page A4 resume optimized for print and PDF export.

Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target.

Give structured, constructive feedback on any design using UX frameworks.

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis.

monday.com via Apideck's Proxy API + managed Vault auth — Apideck handles auth and proxies HTTP calls to monday.com's native API.

MongoDB Atlas cloud database management including clusters, schemas, aggregation pipelines, and Prisma ORM integration.

Help with MongoDB query optimization and indexing.

Monitor running experiments, check progress, collect results.

Check status of running subagents including token usage and context limits