Agent skills for OpenAI Agents SDK

Deploy Julian to an exe.xyz VM (new instance or update existing)

Unified Azure OpenAI model deployment skill with intelligent intent-based routing.

Deploy main to Vercel production the safe way (clean worktree, env baked in) and smoke it with Reelier at Level 0 — zero tokens.

Audit current model deployment topology — serving config, latency profile, version inventory.

Deploy to QA environment (QA1 or QA2). Use when deploying code to the QA testing environments via GitHub Actions. Includes pre-deployment…

Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks.

Build and deploy the UniAgent Apps HTTPS stack, including required Atlas migration gates for Operations and Studio backend releases.

Deploy serverless applications on Cloudflare Workers.

Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry.

Deploy applications with confidence using CI/CD pipelines, containerization, and infrastructure as code.

Use this skill when the user needs to deploy their app, choose a hosting provider, connect a custom domain, set up environment variables…

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness…

Deployment topology, parallelism, memory planning, quantization,

Generates deployment strategy configurations.

DeploymentAdminClient API skill. Use when working with DeploymentAdminClient for subscriptions. Covers 4 endpoints.

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene…

Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners.

Research a codebase and create architectural documentation describing how features or systems work.

Design system reasoning. Maps product domain to style, palette, typography, and platform-specific patterns. Generates…

Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference.

Generate multiple radically different interface designs for a module using parallel sub-agents.