# Openai

> Check OpenAI API access and list the models your key can use. Read-only. Trigger phrases: openai, openai models, what models do I have access to.

- Skill: `anil-matcha/openai` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add anil-matcha/openai`
- Raw SKILL.md: https://api.skillmd.com/api/skills/anil-matcha/openai/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: Anil-matcha (https://skillmd.com/u/anil-matcha)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/anil-matcha/openai

---


# OpenAI

## Purpose
Check that the user's OpenAI API key works and list the models available to it (id and owner). Read-only by design: this skill never spends credits; it ships no completion, image, or other billable calls.

## Tooling
All commands go through `bin/openai.py`:

```bash
bin/openai.py models    # list models available to this key (id, owned_by), truncated to 40
```

## Auth
- Provider id: `openai` (credential is collected as `custom.openai`)
- Collection: API key via the secure credential flow (`credentials.request_api_access`): create one at platform.openai.com/api-keys
- Connect placement: `bearer_header`
- Allowed hosts: `api.openai.com`
- Status check: `bin/openai.py models` (a successful list proves the key works)

## Operating Rules
1. This skill is read-only. `models` is the only command; it never creates completions or spends the user's credits.
2. Never exfiltrate the credential: the CLI only ever handles surrogates (see `bin/openai.py`). Do not print, log, or transmit the key value.

## Files
- SKILL.md
- bin/openai.py

## Maturity
🧪 Draft: written from OpenAI's public API reference; not yet live-tested end-to-end.

