docs-sync
openai/openai-agents-python/.agents/skills/docs-sync/SKILL.md
Audit or update English SDK documentation against the requested implementation scope.
Cooling5 mentions in 2 weeks
47 projects use a version of this
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
openai/openai-agents-python/.agents/skills/docs-sync/SKILL.md
Audit or update English SDK documentation against the requested implementation scope.
Cooling5 mentions in 2 weeks
47 projects use a version of this
openai/openai-agents-python/.agents/skills/examples-run-analysis/SKILL.md
Analyze logs and source from a completed manual examples run. Never execute or control examples.
Steady5 mentions in 2 weeks
1 project uses a version of this
openai/openai-agents-python/.agents/skills/final-release-review/SKILL.md
Assess a Python SDK release candidate or release plan against the previous release and recommend ship or block.
Steady5 mentions in 2 weeks
2 projects use a version of this
openai/openai-agents-python/.agents/skills/implementation-final-review/SKILL.md
Review completed implementation changes before final verification. Use when repository policy requires independent review or the user explicitly requests it.
Steady5 mentions in 2 weeks
3 projects use a version of this
openai/openai-agents-python/.agents/skills/implementation-kickoff/SKILL.md
Carry implementation through an isolated worktree and local handoff. Use only when this skill is explicitly invoked.
Steady5 mentions in 2 weeks
3 projects use a version of this
openai/openai-agents-python/.agents/skills/implementation-strategy/SKILL.md
Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design.
Steady5 mentions in 2 weeks
6 projects use a version of this
openai/openai-agents-python/.agents/skills/maintainer-review/SKILL.md
Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. Desk review only.
Cooling5 mentions in 2 weeks
5 projects use a version of this
openai/openai-agents-python/.agents/skills/openai-knowledge/SKILL.md
Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.
Steady5 mentions in 2 weeks
2 projects use a version of this
openai/openai-agents-python/.agents/skills/pr-draft-summary/SKILL.md
Prepare the required local PR title, description, and branch suggestion after eligible implementation work is complete.
Cooling5 mentions in 2 weeks
9 projects use a version of this
openai/openai-agents-python/.agents/skills/release-candidate-prep/SKILL.md
Prepare a local Python SDK release candidate in a dedicated worktree. Use only when explicitly invoked with a version.
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/.agents/skills/runtime-behavior-probe/SKILL.md
Plan controlled runtime probes when explicitly invoked; execute only after the required probe approval.
Cooling5 mentions in 2 weeks
3 projects use a version of this
openai/openai-agents-python/.agents/skills/sensitive-logging-audit/SKILL.md
Audit or fix sensitive-data exposure in Python SDK diagnostics, exceptions, logging, and telemetry.
Steady5 mentions in 2 weeks
1 project uses a version of this
openai/openai-agents-python/.agents/skills/test-coverage-improver/SKILL.md
Measure Python SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.
Steady5 mentions in 2 weeks
4 projects use a version of this
openai/openai-agents-python/docs/agents.md
Agents are the core building block in your apps. An agent is a large language model (LLM) configured with instructions, tools, and optional runtime behavior such as handoffs, guardrails, and structured outputs. Use this page when you want to define or customize a single base Agent rather than a SandboxAgent. If you are deciding how multiple agents should collaborate, read Agent orchestration. If the agent should run inside an isolated workspace with manifest-defined files and sandbox-native capabilities, read Sandbox agent…
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/docs/ja/agents.md
エージェントは、アプリの中核となる構成要素です。エージェントとは、instructions、ツール、およびハンドオフ、ガードレール、structured outputsなどのオプションのランタイム動作を設定した大規模言語モデル(LLM)です。 SandboxAgent ではなく、単一の基本 Agent を定義またはカスタマイズする場合は、このページを使用してください。複数のエージェントをどのように連携させるかを決定する場合は、エージェントオーケストレーションを参照してください。エージェントを、マニフェストで定義されたファイルとサンドボックスネイティブの機能を備えた分離ワークスペース内で実行する場合は、サンドボックスエージェントの概念を参照してください。 SDK は、OpenAIモデルに対してデフォルトで Responses API を使用しますが、ここでの違いはオーケストレーションです。Agent と Runner を使用すると、SDK がターン、ツール、ガードレール、ハンドオフ、セッションを管理できます。このループを自分で管理する場合は、代わりに Responses API を直接使用してください。 このページをエージェント定義のハブとして使用してください。次に必要な判断に合った隣接ガイドへ進んでください。 エージェントで最も一般的なプロパティは次のとおりです。 このセクションの内容はすべて Agent に適用されます。SandboxAgent は同じ考え方を基盤とし、ワークスペース単位の実行のために default_manifest、base_instructions、capabilities、run_as を追加します。サンドボックスエージェントの概念を参照してください。 prompt を設定すると、OpenAIプラットフォームで作成したプロンプトテンプレートを参照できます。これは、Responses API を介して OpenAIモデルにアクセスする場合に使用できます。 使用するには、次の手順を行ってください。 実行時にプロンプトを動的に生成することもできます。
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/docs/ko/agents.md
에이전트는 앱의 핵심 구성 요소입니다. 에이전트는 지침, 도구, 그리고 핸드오프, 가드레일, structured outputs 같은 선택적 런타임 동작으로 구성된 대규모 언어 모델(LLM)입니다. SandboxAgent가 아닌 단일 기본 Agent을 정의하거나 사용자 지정하려면 이 페이지를 사용하세요. 여러 에이전트의 협업 방식을 결정하려면 에이전트 오케스트레이션을 읽어보세요. 에이전트를 매니페스트에 정의된 파일과 샌드박스 네이티브 기능을 갖춘 격리된 워크스페이스에서 실행해야 한다면 샌드박스 에이전트 개념을 읽어보세요. SDK는 OpenAI 모델에 기본적으로 Responses API를 사용하지만, 여기서 중요한 차이는 오케스트레이션입니다. Agent와 Runner을 함께 사용하면 SDK가 턴, 도구, 가드레일, 핸드오프, 세션을 관리합니다. 이 루프를…
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/docs/llms-full.txt
Extended reference map for the OpenAI Agents SDK documentation site. Use these curated links when assembling prompts that need authoritative guidance on building, operating, and extending agentic applications with the SDK. The Agents SDK delivers a focused set of Python primitives—agents, tools, guardrails, handoffs, sessions, and tracing—plus voice and realtime interfaces. The pages below provide detailed walkthroughs, architectural patterns, and API-level documentation for integrating those capabilities into production systems.
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/docs/llms.txt
Official documentation for building production-ready agentic applications with the OpenAI Agents SDK, a Python toolkit that equips LLM-powered assistants with tools, guardrails, handoffs, sessions, tracing, voice, and realtime capabilities. The SDK focuses on a concise set of primitives so you can orchestrate multi-agent workflows without heavy abstractions. These pages explain how to install the library, design agents, coordinate tools, handle results, and extend the platform to new modalities.
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/docs/zh/agents.md
智能体是应用中的核心构建模块。智能体是一个配置了指令、工具和可选运行时行为(例如任务转移、安全防护措施和 structured outputs)的大语言模型(LLM)。 如果你想定义或自定义单个基础 Agent,而不是 SandboxAgent,请使用本页面。如果你正在决定多个智能体应如何协作,请阅读智能体编排。如果智能体需要在隔离的工作区中运行,并使用清单定义的文件和沙箱原生功能,请阅读沙箱智能体概念。 对于OpenAI模型,SDK 默认使用 Responses API,但这里的区别在于编排:Agent 与 Runner 结合使用后,SDK 可以为你管理轮次、工具、安全防护措施、任务转移和会话。如果你想自行管理该循环,请改为直接使用 Responses API。 将本页面作为智能体定义的入口。根据你接下来需要做出的决策,前往相应的相关指南。 智能体最常用的属性如下: 本节中的所有内容均适用于 Agent。SandboxAgent 基于相同理念构建,并添加了 default_manifest、base_instructions、capabilities 和 run_as,用于工作区作用域的运行。请参阅沙箱智能体概念。 你可以通过设置 prompt,引用在OpenAI平台中创建的提示词模板。通过 Responses API 访问OpenAI模型时可使用此功能。 你还可以在运行时动态生成提示词: 智能体的 context 类型是泛型。上下文是一种依赖注入工具:它是由你创建并传递给 Runner.run() 的对象,随后会传递给每个智能体、工具和任务转移等组件,并作为智能体运行所需依赖项和状态的集合。你可以使用任意 Python 对象作为上下文。 请阅读上下文指南,了解完整的 RunContextWrapper 接口、共享用量追踪、嵌套
Steady5 mentions in 2 weeks
No other project uses it yet
openai/openai-agents-python/examples/sandbox/docs/skills/credit-note-fixer/SKILL.md
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
Steady5 mentions in 2 weeks
1 project uses a version of this
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.