Agent skills for OpenAI Agents SDK

Configure Tempo blockchain as an MPP payment method — USDC stablecoin payments with sub-second finality, 100,000+ TPS, and no gas…

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features…

Run a browser automation task on a website using natural language.

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture"…

Multi-language Workers development with Rust, Python, and WebAssembly.

Automates multi-platform code standardization and generates comprehensive technical documentation within WPS Notes.

Assess and improve cloud portability — identify lock-in, prioritize abstraction, and design migration paths.

Reviews product requirements documents across five specialized roles to identify completeness, consistency, and testability issues.

Multiple comparison correction methods

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration…

This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief…

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash…

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy…

Generates MyBatis-Plus code (Entity, Mapper, Service, ServiceImpl, Controller, DTO, VO, BO) from database tables.

Core myfy patterns and conventions for building applications.

Direct MySQL database access with mysql2 driver -- connection pools, prepared statements, transactions, streaming, typed queries, error…

Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API.

Transform lessons and insights into compelling short stories with tension, conflict, reversal, and clear takeaways.

NVIDIA Collective Communications Library integration for multi-GPU operations.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

NVIDIA's runtime safety framework for LLM applications.