Skip to content
Back to skills

Openai Api

ASecurity

Builds or debugs OpenAI Chat Completions, Responses API, and OpenAI Agents SDK patterns — function calling, structured output, streaming, handoffs. Use when extending src/lib/ai/clients/openai.ts or adding OpenAI-first agents.

  • 2 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 26, 2026
ai-agentspythongitapi

Works with

  • cursor
  • cli
  • api

Security analysis

A100/100

Scanned October 26, 2026

npx -y skills add JoshuaShepherd/my-skills --skill openai-api --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openai Api?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Openai Api
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/joshuashepherd-openai-api-my-skills/badge)](https://www.skillsdirectory.com/skills/joshuashepherd-openai-api-my-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: openai-api
description: Builds or debugs OpenAI Chat Completions, Responses API, and OpenAI Agents SDK patterns — function calling, structured output, streaming, handoffs. Use when extending src/lib/ai/clients/openai.ts or adding OpenAI-first agents.
---

# OpenAI API (Cursor)

## Canonical source

**`.claude/skills/openai-api/SKILL.md`** lists **platform.openai.com** and **openai.github.io/openai-agents-python** references and implementation patterns.

## In Cursor

1. Read the canonical skill for the surface you need (`agents` vs `chat`).
2. Fetch current OpenAI docs (model list, API reference) before relying on model IDs or parameters.
3. OpenAI REST + Agents SDK entry: `src/lib/ai/clients/openai.ts` (`openaiClient`, `createAgent`, `createRunner`, re-exports `run`, `tool`, `fileSearchTool`).

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.