Build AI applications with OpenAI Agents SDK - text agents, voice agents (realtime), multi-agent workflows with handoffs, tools with Zod…
Build with OpenAI's stateless APIs - Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation.
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. ⚠️ Sunset H1 2026…
Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns.
Cross-vendor OpenCL runtime management and kernel development.
Create high-performing LinkedIn posts and content strategy.
Use immediately for any pasted OpenClaw GitHub issue or PR URL/number, and for OpenClaw issue/PR orchestration, review, triage, root-cause…
Orchestrate worker fleets over OpenClaw issues and PRs: prove root causes, prefer clean refactors over quick patches, land verified…
Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.
Guides the creation and injection of custom, accessible UI themes for OpenClaw Control UI and web apps with automated self-healing.
Generates multi-platform UI prototypes, event landing pages, pitch decks, and multimedia assets aligned with custom brand design systems.
Generates platform-optimized OpenGraph images and social media cards using AI-powered backgrounds and precise typography engines.
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process
Use when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents…
Answer "what is being done, and what needs my attention?" across every coding session and every repository, by running the `ol` command…
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference…
Use the OpenQASM 3 specification, reference grammar, and openqasm3
High-performance RLHF framework with Ray+vLLM acceleration.
Monitor OpenRouter model availability and implement health checks.
Generate a concise PR description from code changes, following the repo's PR template
Implement tasks from an OpenSpec change.