Publisher: Openai Developers plugin in openai/plugins · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Trace exposed tools into their helpers before drafting review claims. A harmless tool name can conceal a write, queued job or external message, so describe actual side effects.
What input and output should you expect?
Input: A complete MCP server codebase, manifests, widget metadata and accurate product information. Include helper modules needed to understand tool behavior.
Output: A chatgpt-app-submission.json draft, review findings and warnings about missing output schemas, plus positive and negative test cases.
What does it need to run?
A compatible coding client with repository access. The source workflow relies on real implementation evidence and requires unresolved annotation mismatches to be addressed before generating misleading material.
Published in the OpenAI Codex plugins repository. Compatibility evidence is the plugin package and its source instructions; this is not a claim of identical behavior in other agent clients.
How should you approach installation?
- Open the pinned source and review the complete skill folder, including referenced helpers and license, before enabling it.
- Use the corresponding plugin in a compatible Codex environment; preserve the skill folder structure rather than copying only SKILL.md. Confirm current plugin availability in your client.
- Start with a disposable project and the trial prompt below. Grant only the stated access, inspect the proposed diff, and require separate approval for remote writes or publishing.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads source and writes a local submission artifact. Fixing source annotations is a separate reviewed edit. Uploading the file or submitting an app is an external action requiring your instruction.
What does the skill cost?
Local artifact preparation has no separate skill execution price. Coding-agent usage, test infrastructure and any services exercised during later validation may incur costs.
What are its limits and alternatives?
This is preparation, not platform acceptance or certification. Generated cases are proposed tests unless separately executed; an accurate description cannot compensate for unsafe server behavior.
Use Build ChatGPT App to create the server first; use a separate security review for deeper authentication and authorization analysis.
What could you ask in a small trial?
Try this with a small sample:
Inspect this sample MCP server, enumerate actual side effects and compare all three tool hints with implementation. Draft test cases and report blockers. Do not edit source or submit anything.
How would you verify the result?
- Every exposed tool has an evidence-based hint explanation.
- Negative tests cover invalid input and unauthorized actions.
- Output-schema gaps are clearly identified.
- The submission text makes no unverified test or approval claim.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 License evidence
Version details and review scope
Source: openai/plugins/plugins/openai-developers/skills/chatgpt-app-submission
Reviewed commit: 0722921d5542fc593105c27bd52630babd8b8c2a
SKILL.md SHA-256: c9b43ca8fe60189e541afa30ea32a86f1bd7ab58a353faac777192a282b796cf
Pinned source and license review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.