expo-deployment

Deploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes

1.50x

Quality

81%

Does it follow best practices?

Impact

90%

1.50x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%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 content is concise and highly actionable with concrete commands and configs, but it lacks validation checkpoints in the build→submit workflow and contains broken reference paths that undermine navigation.

Suggestions

Fix the reference path inconsistency: the body uses ./reference/ (singular) in the iOS, Android, Web, and Automated Deployments sections, but the actual bundle directory is ./references/ (plural) — 5 links currently resolve to nothing.

Add explicit validation/verification checkpoints to the build→submit workflow, e.g. check `eas build:view` succeeds before submitting and confirm `eas submit:list` status after submission.

Verify command accuracy: `npx testflight`, `eas build:version:get`, and `eas build:version:set` are not real EAS CLI commands and will fail to execute.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven — install/init/build/submit/deploy commands plus concrete eas.json and workflow YAML — with only minimal, useful prose and no padding explaining what Expo or EAS is, matching the 'every token earns its place' anchor.	3 / 3
Actionability	It provides concrete, copy-paste-ready commands (eas build/submit/deploy, eas credentials, eas build:list/view, eas submit:list) and a full eas.json config block, satisfying the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	An implied install→init→build→submit sequence exists and the workflow YAML shows job dependencies, but there are no explicit validation/verification checkpoints for the store-submission flow, which the guidelines cap at 2 for destructive/batch operations.	2 / 3
Progressive Disclosure	The body has a well-signaled one-level-deep References section, but the Platform-Specific Guides and Automated Deployments sections point to ./reference/ (singular) while the actual bundle directory is ./references/ (plural), breaking navigation for 5 links per the 'score against actual bundle structure' guideline.	2 / 3
	Total	10 / 12 Passed

Description

82%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.

The description is specific and uses natural trigger terms within a clear Expo-deployment niche, but it omits an explicit "Use when..." clause so it does not fully answer when Claude should invoke it.

Suggestions

Append an explicit trigger clause, e.g. "Use when deploying Expo or React Native apps to the iOS App Store, Google Play, web hosting, or EAS API routes."

Clarify "API routes", which is vague alongside concrete store/hosting targets — specify whether it means deploying serverless functions via EAS Hosting.

Dimension	Reasoning	Score
Specificity	"Deploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes" names the domain and enumerates multiple concrete deployment targets rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does (deploying Expo apps to four targets) but lacks any "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Natural user-facing terms — "Expo apps", "iOS App Store", "Android Play Store", "web hosting", "API routes" — are exactly what a user would say when they need this skill, giving good coverage per the anchor.	3 / 3
Distinctiveness Conflict Risk	The Expo-specific deployment niche with named store/hosting targets is clearly distinguishable and unlikely to trigger for unrelated skills, matching the 'clear niche' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/expo/skills/expo-deployment/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.