Publisher: Expo plugin in openai/plugins · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Start by identifying the current SDK and whether native projects are generated or manually maintained. Preserve custom native work before considering regeneration or cache cleanup.
What input and output should you expect?
Input: package.json, lockfile, app configuration, current SDK, target version and an inventory of native customizations and device features.
Output: A staged upgrade diff, dependency issues, migration notes and a platform-specific regression checklist.
What does it need to run?
An Expo project, package tooling and access to release notes. Building native targets may require platform SDKs or a hosted build service; plan that access before upgrading.
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?
The workflow changes dependency and configuration files and may suggest deleting generated artifacts. Native regeneration can overwrite custom changes; require a verified backup and explicit review before destructive cleanup.
What does the skill cost?
The skill files are MIT licensed. Coding-agent usage, native build infrastructure, hosted build quotas and app-store accounts are not included.
What are its limits and alternatives?
Successful package installation does not establish a working app. Preview releases and platform requirements differ; examples in a pinned skill must be checked against the chosen stable target.
Use native-data-fetching for an isolated networking bug. A small module upgrade may be preferable when a full SDK migration is unnecessary.
What could you ask in a small trial?
Try this with a small sample:
Inspect this project and propose a stable SDK upgrade plan. Identify manually maintained native files and deprecated APIs first. Produce only a migration plan; do not install, clear caches or regenerate native directories.
How would you verify the result?
- The target version is intentional and supported by required modules.
- Custom native changes have a restoration path.
- Navigation, login, camera, audio and notifications have relevant tests.
- Both platform builds and a rollback to the old lockfile are planned.
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:
MIT License evidence
Version details and review scope
Source: openai/plugins/plugins/expo/skills/upgrading-expo
Reviewed commit: 0722921d5542fc593105c27bd52630babd8b8c2a
SKILL.md SHA-256: 373efb08acd4002922b1d6eb6dbfff6a871e38841f72f0753f4928650ed70ee1
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.