auth0-expo
Use when adding authentication to Expo (React Native) mobile apps — login, logout, user sessions, protected routes, biometrics, or token management. Integrates react-native-auth0 SDK with Expo Config Plugin for native iOS/Android builds. Trigger for any Expo project needing Auth0, including app.json plugin config, custom scheme setup, or credential management. Do NOT use for bare React Native CLI projects (use auth0-react-native), React web apps (use auth0-react), Next.js (use auth0-nextjs), or backend APIs.
89
88%
Does it follow best practices?
Impact
87%
1.15xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, clear trigger conditions with a 'Use when' clause, abundant natural keywords, and explicit exclusion boundaries that prevent conflicts with related skills. The third-person voice is maintained throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: login, logout, user sessions, protected routes, biometrics, token management, app.json plugin config, custom scheme setup, credential management. Very specific about the SDK (react-native-auth0) and platform (Expo with native iOS/Android builds). | 3 / 3 |
Completeness | Clearly answers both 'what' (authentication features, Auth0 SDK integration with Expo Config Plugin) and 'when' (explicit 'Use when' clause at the start, plus 'Trigger for any Expo project needing Auth0'). Also includes explicit 'Do NOT use' guidance for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'authentication', 'Expo', 'React Native', 'login', 'logout', 'biometrics', 'token management', 'Auth0', 'app.json', 'custom scheme'. Also includes negative triggers distinguishing from bare React Native CLI, React web, Next.js, and backend APIs. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — narrowly scoped to Expo + Auth0 specifically, and explicitly excludes bare React Native CLI, React web, Next.js, and backend API projects. This makes it very unlikely to conflict with other auth-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionability and workflow clarity. The step-by-step process includes thoughtful agent instructions for checking prerequisites, handling edge cases, and verifying builds with explicit failure recovery. The main areas for improvement are moderate verbosity (the 'When NOT to Use' table and common mistakes section are extensive) and the inability to verify referenced bundle files exist.
Suggestions
Consider moving the 'Common Mistakes' table to a reference file (e.g., references/troubleshooting.md) and keeping only the top 3 most critical mistakes inline to reduce token usage.
The 'When NOT to Use' table could be condensed to 3-4 key alternatives rather than 8 rows, since Claude can infer most of these from the skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity — the 'When NOT to Use' table is extensive (8 rows for a skill that could just say 'Expo only'), and the common mistakes table, while useful, is lengthy. The agent instruction blocks add bulk but are genuinely useful for guiding behavior. Some tightening is possible but overall it respects Claude's intelligence. | 2 / 3 |
Actionability | Provides fully executable code examples including complete TypeScript components, exact bash commands for installation and building, specific JSON configuration for app.json, and precise callback URL formats. The code is copy-paste ready with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: Step 2 checks for expo-dev-client before proceeding, Step 7 includes build verification with specific error diagnosis, a retry loop, and a failcheck after 5-6 attempts that asks the user how to proceed. The feedback loop for build failures is well-structured. | 3 / 3 |
Progressive Disclosure | References to setup.md, integration.md, and api.md are well-signaled and one level deep, which is good. However, no bundle files were provided, so we cannot verify these references actually exist. The main SKILL.md itself is quite long (~180 lines of substantive content) with the common mistakes table and detailed agent instructions that could potentially be moved to reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- Repository
- auth0/agent-skills
- Commit
bdf0dc2
- Reviewed
Table of Contents
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.