Implement OAuth 2.0 authentication with GitHub and Microsoft Entra (Azure AD) in Cloudflare Workers and other edge environments. Covers provider-specific quirks, required headers, scope requirements, and token handling without MSAL. Use when: implementing GitHub OAuth, Microsoft/Azure AD authentication, handling OAuth callbacks, or troubleshooting 403 errors in OAuth flows.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill oauth-integrations93
Does it follow best practices?
Validation for skill structure
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, uses natural trigger terms users would actually search for, explicitly states when to use it, and carves out a distinctive niche at the intersection of OAuth providers and edge computing environments. The troubleshooting angle (403 errors) is a particularly smart inclusion for discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Implement OAuth 2.0 authentication', 'Covers provider-specific quirks, required headers, scope requirements, and token handling'. Specifies concrete technologies (GitHub, Microsoft Entra, Cloudflare Workers) and implementation details (without MSAL). | 3 / 3 |
Completeness | Clearly answers both what (implement OAuth 2.0 with specific providers, covers quirks/headers/scopes/tokens) AND when (explicit 'Use when:' clause with four specific trigger scenarios including troubleshooting 403 errors). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'GitHub OAuth', 'Microsoft/Azure AD authentication', 'OAuth callbacks', '403 errors in OAuth flows', 'Cloudflare Workers', 'edge environments'. Includes both formal names and common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining OAuth 2.0 + specific providers (GitHub, Microsoft Entra) + specific runtime (Cloudflare Workers/edge). The combination of these constraints makes it unlikely to conflict with generic auth or generic Cloudflare skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently covers edge-specific OAuth quirks for GitHub and Microsoft. The content is actionable with executable code and excellent error reference tables. The main weakness is the lack of explicit end-to-end workflow sequences showing the complete OAuth flow with validation steps.
Suggestions
Add a numbered workflow section showing the complete OAuth flow sequence (e.g., '1. Redirect to auth URL → 2. Handle callback → 3. Exchange code for token → 4. Validate token → 5. Fetch user info') with explicit validation checkpoints between steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section provides specific, non-obvious information (User-Agent requirement, MSAL incompatibility reasons, scope requirements). No explanations of basic OAuth concepts Claude already knows; tables efficiently convey key information. | 3 / 3 |
Actionability | All code examples are complete and executable TypeScript. Specific headers, endpoints, and scope strings are provided. The 'Common Corrections' table gives exact replacements, and error tables provide specific fixes. | 3 / 3 |
Workflow Clarity | While individual operations are clear, the skill lacks explicit step-by-step workflows for complete OAuth flows. Azure Portal Setup has numbered steps, but the main OAuth flows (authorization → token exchange → user info) aren't sequenced with validation checkpoints. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, tables for quick reference, and external documentation links at the end. For a skill of this scope (~150 lines), the inline organization is appropriate without needing separate files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
93%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 |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
Total | 15 / 16 Passed | |
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.