Claude Code Plugins

Community-maintained marketplace

Feedback

|

Install Skill

1Download skill
2Enable skills in Claude

Open claude.ai/settings/capabilities and find the "Skills" section

3Upload to Claude

Click "Upload skill" and select the downloaded ZIP file

Note: Please verify skill by going through its instructions before using it.

SKILL.md

name openai-api
description OpenAI REST API integration guide. Use when: making direct HTTP calls to OpenAI API, understanding API structure without SDK, debugging API requests, learning request/response formats, handling errors and rate limits. Covers: authentication, Chat Completions, Embeddings, Images (DALL-E), Audio (Whisper/TTS), error handling, streaming.

OpenAI REST API

Direct HTTP integration with OpenAI API. For SDK usage, see openai-sdk skill.

Base URL & Authentication

Base URL: https://api.openai.com/v1
curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{...}'

Optional headers:

  • OpenAI-Organization: org-xxx — for multi-org accounts
  • OpenAI-Project: proj-xxx — for project-specific billing

Core Endpoints

Endpoint Method Use Case
/chat/completions POST Text generation, chat
/embeddings POST Vector embeddings
/images/generations POST DALL-E image creation
/audio/transcriptions POST Whisper speech-to-text
/audio/speech POST TTS text-to-speech
/models GET List available models

Quick Reference

Chat Completions (most common)

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Response structure:

{
  "id": "chatcmpl-xxx",
  "choices": [{
    "message": {"role": "assistant", "content": "Hi! How can I help?"},
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 10, "completion_tokens": 8, "total_tokens": 18}
}

Embeddings

curl https://api.openai.com/v1/embeddings \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "text-embedding-3-small", "input": "Hello world"}'

Streaming

Add "stream": true to request. Response is SSE:

data: {"choices":[{"delta":{"content":"Hello"}}]}
data: {"choices":[{"delta":{"content":" world"}}]}
data: [DONE]

References

Official Documentation

For latest/complete docs, fetch:

  • https://cdn.openai.com/API/docs/txt/llms-api-reference.txt
  • https://cdn.openai.com/API/docs/txt/llms-guides.txt