GPTsApp SkillsCodex Reset
Menu
Codex Reset
← Back to results

plugin directory · Use or study

openai-platform-api-key

Pause API-backed implementation at a credential decision and route an explicitly approved key reuse or creation flow without exposing plaintext.

openai/pluginsplugins/openai-developers/skills/openai-platform-api-key/SKILL.md

Read SKILL.md ↗Open source directory ↗

Before you use it

Input
The intended API-backed task, provider, workspace conventions, a silent presence or absence result for an existing key, the reuse-versus-new decision and a confirmed destination if a write is authorized.
Expected output
A credential decision or safe write metadata after a supported secure flow. Plaintext key material is never a user-facing output of the described method.
Prerequisites
Do not request, print or search secret-bearing files in a way that reveals values. The pinned source requires an explicit decision before API-dependent implementation and describes connector and helper capabilities that may not exist in another host. This directory did not inspect any credential or create a key.

Client setup and runtime behavior are not verified here; client installation is not individually established. The use notes below describe source preparation, inputs and limits.

Publisher documentation, static file observations and environment tests are different kinds of evidence. Runtime behavior has not been observed.

Use this method

Source-based preparation, not an installation or a completed run. Nothing is executed here.

Good fit for
Preparing credential handling for a local OpenAI API-backed project when the user can explicitly approve reuse, creation and any destination write.
Not for / limits
Not API documentation, request-failure diagnosis or a generic secret manager. The pinned workflow is Codex- and connector-specific, no connector availability was verified, and no API key was created, read or stored here.
Prepare
Confirm that the artifact will actually call the OpenAI API, inspect only key presence through a no-output check, and keep provider-specific work separate from static or conceptual requests.
Apply
Ask for the explicit reuse-versus-new decision and stop. If a new key or persistent write is approved, confirm the local destination and ensure it is not a tracked or out-of-workspace secret target.
Check
Use only a supported secure picker or encrypted handoff available in the actual host, verify the resulting configuration without revealing the value, and report only safe metadata such as the path and variable name.
Sources read for this note

These exact files were read as text at the displayed commit. Other files and external tools were not reviewed. A repository LICENSE observation does not confirm Skill-specific applicability or dependency rights.

Study the method

Separate credential gating from API documentation, troubleshooting and application implementation. The evals make the stop boundary observable: presence is not permission, and an explicit new-key request differs from a reuse decision.

3 files in the observed scope; 0 in scripts/, 1 in references/, 0 in assets/.

Zero files in scripts/ does not mean no execution, network access or file writes. Markdown and other folders may describe or contain executable behavior.

Source version and requirements

Observed
2026-09-07T14:02:40.375Z
Source commit
1e285826e604f66f7208f7ac4dba0fe8341d1f57
Content SHA-256
780670286fb0acf32660abafc1bc34d7a25ff7a74af59e02db8fb62bbdd21ac2
License
Unknown
Author attribution
Repository owner: openai. Individual authorship is not independently established.

This page describes a pinned source snapshot, not the latest repository state. Changes after this commit have not been reconciled here. A repository license does not necessarily cover external models, datasets or services.

Open current repository ↗
Reference note and manual copy