agents-sdk Skill
Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally through the Agents SDK Deployment Manager. Published by openai in plugins.
What is agents-sdk Skill?
Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally through the Agents SDK Deployment Manager. Published by openai in plugins. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Deployment
- Documentation
- Deployment use cases
- Documentation use cases
Technical details
- Install or run with Copy skill directory
When to use agents-sdk Skill
- Use it for deployment.
- Use it for documentation.
Built with
Editorial notes
Source
- Creator: openai
- Repository: openai/plugins
- Skill file: plugins/openai-developers/skills/agents-sdk/SKILL.md
What it does
Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally through the Agents SDK Deployment Manager.
Skill instructions
Agents SDK Use this skill to turn an idea, repo, or prior Codex thread into a small runnable Agents SDK app. Verify it locally, then deploy it through the local Deployment Manager when the user wants a running service. Prefer Python unless the user asks for TypeScript. References - Agents guide: https://developers.openai.com/api/docs/guides/agents - Sandbox Agents guide: https://developers.openai.com/api/docs/guides/agents/sandboxes - Python SDK: https://github.com/openai/openai-agents-python - TypeScript SDK: https://github.com/openai/openai-agents-js - Deployment Manager: https://github.com/openai/openai-cookbook/tree/main/examples/agentssdk/deploymentmanager - Agent evals guide: https://developers.openai.com/api/docs/guides/agent-evals Rules - Read the Agents guide before creating or changing an Agents SDK implementation. - Read the Sandbox Agents guide before choosing SandboxAgent, workspace manifests, shell/file access, skills, or sandbox backend behavior. - If a docs MCP/tool is
Explore related resources
Frequently asked questions
What is agents-sdk?
agents-sdk is a open-source AI agent skill with Copy skill directory. Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a.
Who is agents-sdk best for?
agents-sdk is best for reusing agent instructions, scripts, and references, deployment workflows, documentation workflows.
How do I install agents-sdk?
Install or run agents-sdk using Copy skill directory. Check agents-sdk for the latest setup command.
Is agents-sdk actively maintained?
agents-sdk may need a closer maintenance check before production use.
Auto-fetched from GitHub.
