OAuth 2.0 and OpenID Connect authentication with secure flows. Use for third-party integrations, SSO systems, token-based API access, or encountering authorization code flow, PKCE, token refresh, scope management errors.
95
95%
Does it follow best practices?
Impact
93%
1.20xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 a strong description with excellent trigger terms and completeness. It clearly identifies its authentication/authorization niche and provides explicit 'Use for' guidance. The main weakness is that it describes the domain rather than listing specific concrete actions Claude can perform with this skill.
Suggestions
Add specific action verbs describing what the skill does, e.g., 'Implements OAuth flows, generates tokens, debugs authentication errors, configures PKCE challenges'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (OAuth 2.0, OpenID Connect) and mentions some technical concepts (authorization code flow, PKCE, token refresh, scope management), but doesn't list concrete actions like 'implement', 'configure', 'debug', or 'generate tokens'. | 2 / 3 |
Completeness | Clearly answers both what (OAuth 2.0 and OpenID Connect authentication with secure flows) and when (explicit 'Use for' clause listing third-party integrations, SSO systems, token-based API access, and specific error scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'OAuth', 'SSO', 'third-party integrations', 'token refresh', 'PKCE', 'authorization code flow', 'scope management errors' - good coverage of both common and technical terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific protocol names (OAuth 2.0, OpenID Connect, PKCE) and clear niche in authentication/authorization - unlikely to conflict with general API or security skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates best practices across all dimensions. It provides concrete, executable code for the most common OAuth flow, includes essential security requirements as a checklist, and appropriately delegates language-specific implementations to a reference file. The content respects Claude's intelligence by avoiding explanations of OAuth concepts while providing the specific implementation details needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, jumping directly into actionable tables and code without explaining what OAuth is or how authentication works conceptually. Every section adds value Claude wouldn't inherently know about implementation specifics. | 3 / 3 |
Actionability | Provides fully executable Express.js code for the authorization code flow, complete PKCE implementation, and specific security requirements. The code is copy-paste ready with clear variable names and proper error handling. | 3 / 3 |
Workflow Clarity | The authorization code flow is clearly sequenced with explicit steps (Step 1: Redirect, Step 2: Handle callback), includes state validation as a security checkpoint, and the flow table provides clear decision guidance for which flow to use. | 3 / 3 |
Progressive Disclosure | Core implementation is in the main file with a clear reference to additional implementations (Python, Java, OIDC discovery) in a separate file. The reference is one level deep and clearly signals what content is available there. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
90d6bd7
Table of Contents
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.