Name: openai-platform-api-key
Rating: 70.39999999999999 (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

86%

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

81%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced skill body with concrete tool calls, bash commands, and explicit validation gates for a sensitive secret-handling workflow. The main weakness is repetition of the credential-decision gate logic across several sections, which inflates length without adding new information.

Suggestions

Consolidate the reuse-vs-new "ask then stop" gate logic into a single section (Mandatory First Step or Workflow step 2) and have other sections reference it, rather than restating the rule in When To Use, Credential Decision Messages, and the Workflow.

Consider externalizing the detailed Credential Decision Messages branches and the picker/connector tool-call choreography into a reference file, keeping SKILL.md as a tighter overview that points to it.

Soften the soft validation in step 8 ("when practical") into an explicit checkpoint, or state the fallback verification when running the project command is not practical.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the reuse-vs-new "ask then stop" gate logic is restated across When To Use, Mandatory First Step, Credential Decision Messages, and Workflow step 2, so it could be tightened.	3 / 5
Actionability	Fully executable guidance with exact tool names, tool_search procedures, connector ids, and copy-paste bash commands (e.g. `node "<plugin root>/scripts/openai-platform-api-key.mjs" prepare --name "Codex"`) covering the common cases.	5 / 5
Workflow Clarity	An 8-step sequence with explicit validation checkpoints ("stop until the user answers", refuse symlink/out-of-workspace targets, verify by running the project command) and feedback loops (retry tool_search after the user connects the app).	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep reference (`references/evals.md`), though the dense body keeps most operational detail inline rather than splitting it into separate files.	4 / 5
	Total	17 / 20 Passed

Description

91%Weight 40%Scale 1-5

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, specific description that clearly states both the skill's purpose as a credential gate and its trigger conditions, with rich natural keyword coverage. Minor overlap risk with general AI app-building skills keeps distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability actions ("inspect safely, ask reuse-vs-new before API work, and never expose plaintext") plus the trigger domain, but the capability list is somewhat condensed with minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (credential gate: inspect, ask reuse-vs-new, never expose plaintext) and when ("Use when Codex is asked to build, run, test, debug, or configure...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including the env var OPENAI_API_KEY, the sk-proj key format, and the explicit "using AI" phrasing alongside generators driven by forms/user input.	5 / 5
Distinctiveness Conflict Risk	The credential-gate framing carves a distinct niche, but "provider-unspecified AI app" and "using AI" generator triggers carry minor overlap risk with general app-builder skills.	4 / 5
	Total	18 / 20 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: 1dc1958

Reviewed: 2 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.