Name: openai-platform-api-key
Rating: 68 (1 reviews)
Author: openai

openai-platform-api-key

Use when Codex is asked to build, run, test, debug, or configure an OpenAI-backed or provider-unspecified AI app, UI, script, CLI, generator, or tool, especially requests phrased only as "using AI" or generators driven by forms/user input; also use for OPENAI_API_KEY or sk-proj setup. Treat this as the credential gate: inspect safely, ask reuse-vs-new before API work, and never expose plaintext.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

62%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers a well-sequenced, validated workflow with concrete tool calls and fallbacks, but it is weighed down by heavy repetition of the credential-gate concept and references a helper script that is missing from the bundle. Tightening the redundancy and shipping or removing the dangling script reference would lift the weaker dimensions.

Suggestions

Consolidate the repeated credential-gate / hard-stop guidance (currently restated in Coordination, Mandatory First Step, Credential Decision Messages, and Workflow) into a single authoritative section to reduce redundancy.

Add the missing scripts/openai-platform-api-key.mjs to the bundle or drop the inline Helper commands that reference it, so the executable examples resolve against the actual file listing.

Split the long inline Credential Decision Messages and Workflow detail into a one-level-deep reference file so the SKILL.md body stays an overview with well-signaled navigation.

Dimension	Reasoning	Score
Conciseness	The credential-gate / 'stop until the user answers' hard-stop is restated across Coordination, Mandatory First Step, Credential Decision Messages, and Workflow step 2, so it could be tightened substantially; it does not, however, pad with concepts Claude already knows, keeping it above a 1.	2 / 3
Actionability	Guidance is highly concrete (exact tool names, full argument specs, verbatim user prompts, explicit fallbacks), but the core helper script referenced in the commands is absent from the bundle and '<plugin root>' is an unresolved placeholder, so the examples are not fully copy-paste executable as shipped.	2 / 3
Workflow Clarity	An 8-step numbered workflow with explicit validation checkpoints (destination approval, tracked-file check, refuse symlink/out-of-workspace, decline->stop) and feedback loops (tool unavailable -> ask to connect -> retry) for a secret-writing operation.	3 / 3
Progressive Disclosure	Headers organize the body and there is one real one-level reference (references/evals.md, which exists), but the body is a long inline monolith and it references scripts/openai-platform-api-key.mjs, a path not present in the bundle.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states both the capability and explicit 'Use when...' triggers, with concrete actions and natural trigger terms. It carves a distinct OpenAI credential-gate niche and uses third-person/imperative voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('build, run, test, debug, or configure', 'inspect safely', 'ask reuse-vs-new', 'never expose plaintext') rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('Treat this as the credential gate: inspect safely, ask reuse-vs-new...') and when (a leading 'Use when Codex is asked to...' clause), so it is not capped at 2 for a missing trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users actually say — 'using AI', 'AI app', 'OPENAI_API_KEY', 'sk-proj', 'generator' — giving good coverage rather than just technical jargon.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche as the OpenAI credential gate with distinct triggers (OPENAI_API_KEY/sk-proj); the 'provider-unspecified' broadening is intentional and the OpenAI scope keeps it unlikely to conflict.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/openai-developers/skills/openai-platform-api-key/SKILL.md
Commit: 11c74d6

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.