Agent skills for OpenAI Agents SDK

Methodology for evaluating the live product via a real browser (Playwright MCP) when planning work or evaluating a PRD.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract…

Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff.

Report the embedded release marker when testing public Skill installation or marketplace updates.

Veteran livestream e-commerce coach specializing in host training and live room operations across Douyin, Kuaishou, Taobao Live, and…

Use for Livewire performance work. Covers what one Livewire request actually costs, the snapshot that travels both ways on every request…

Use at ship time to merge the spec into the living documentation, delete the staging spec and plan, and ask how to finish.

Develop and contribute to the PinchTab project.

Use proactively whenever LLM API costs come up -- or should.

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously…

Run multi-LLM council for adversarial debate and cross-validation.

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI…

Demonstrate unbounded resource consumption against an LLM application — token floods, unbounded output, and cost/denial-of-wallet…

Generate a publication-quality methodology diagram from a text file using PaperBanana.

Configure and manage Learning Management System operations including courses, enrollments, compliance training, and learning analytics

Generates seed data from ORM schemas or entity definitions to any target format.

Expert skill for load balancer configuration, algorithms, and high availability design

Validate load balancer behavior, failover, and traffic distribution.

Load GitHub PR review comments into AI session — analyze, triage, plan.

Load the shader-nodes skill system. Run this first to establish the shader development workflow.