openai/openai-agents-python
7 skills761 installs199k starsGitHub
Install
npx skills add https://github.com/openai/openai-agents-pythonSkills in this repo
1Openai KnowledgeUse when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`. Use the OpenAI Developer Documentation MCP server to search and fetch exact docs (markdown), then base your answer on that text instead of guessing.400installs2Docs SyncAnalyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs under docs/** and never touch translated docs under docs/ja, docs/ko, or docs/zh. Provide a report and ask for approval before editing docs. Identify doc coverage gaps and inaccuracies by comparing main branch features and configuration options against the current docs structure, then propose targeted improvements.180installs3Implementation StrategyDecide how to implement runtime and API changes in openai-agents-python before editing code. Use when a task changes exported APIs, runtime behavior, serialized state, tests, or docs and you need to choose the compatibility boundary, whether shims or migrations are warranted, and when unreleased interfaces can be rewritten directly. Use this skill before editing code when the task changes runtime behavior or anything that might look like a compatibility concern. The goal is to keep implementations simple while protecting real released contracts.104installs4Runtime Behavior ProbeThe runtime-behavior-probe skill plans and executes runtime-behavior investigations using temporary probe scripts, validation matrices, state controls, and findings-first reports. It targets cases where code or documentation alone cannot confirm actual behavior, especially edge cases, undocumented behavior, or common failure modes in local or live OpenAI Agents Python integrations. Core rules require explicit manual invocation, planning a case matrix before execution, defaulting to local or read-only probes, and applying destination, intent, and data gates before live probes that read environment variables or mutate remote state. The workflow restates investigation targets, builds matrices covering baseline, boundary, invalid input, retry, and concurrency cases, chooses execution modes like single-shot or repeat-N, and records runtime context including commit, interpreter, and approved variable names without printing secrets. Probe scripts live in temporary directories, maximize observability, and are deleted after reporting unless follow-up is needed. Reporting puts unexpected findings first, then validation approach, case results, and artifact status. OpenAI-specific guidance co.71installs5Credit Note Fixercredit-note-fixer skill documents Fix the tiny credit-note formatting bug and rerun the exact targeted test command.. name: credit-note-fixer description: Fix the tiny credit-note formatting bug and rerun the exact targeted test command.2installs6Csv Workbenchcsv-workbench skill documents Analyze CSV files in /mnt/data and return concise numeric summaries.. name: csv-workbench description: Analyze CSV files in /mnt/data and return concise numeric summaries.2installs7Prior Auth Packet Builderprior-auth-packet-builder skill documents Build a concise prior authorization packet from local case files and payer policy docs.. name: prior-auth-packet-builder description: Build a concise prior authorization packet from local case files and payer policy docs.2installs