authentication-patterns

Authentication patterns: session vs JWT vs OAuth comparison, provider selection (NextAuth, Clerk, Supabase Auth), security checklist, and common mistakes. Use when implementing auth, reviewing auth flows, or choosing auth providers.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code and a strong decision framework, but it leans encyclopedic and keeps everything inline rather than splitting deep reference material into separate files. Tightening redundant truisms and gating the shipping checklist with explicit validation would lift the weaker dimensions.

Suggestions

Split the provider setup patterns and the full SECURITY_CHECKLIST into referenced bundle files (e.g., providers.md, checklist.md) so SKILL.md stays a concise overview with one-level-deep links.

Remove or compress truisms Claude already knows (e.g., "never commit secrets", "use established libraries") to improve token efficiency.

Convert the shipping checklist into a gated sequence with an explicit validation checkpoint (e.g., run all checklist items → fix failures → re-verify before marking shipped).

Dimension	Reasoning	Score
Conciseness	The body is information-dense with terse rules, tables, and code, but its encyclopedic breadth and a few universal truisms ("never commit secrets", "never MD5, SHA-1") restate knowledge Claude already has and could be tightened.	2.5 / 3
Actionability	Fully executable, copy-paste-ready examples (NextAuth route handler, bcrypt and argon2 hash/verify) plus concrete decision guidance and [P0-MUST]/[P1-SHOULD] rules give specific actionable instruction.	3 / 3
Workflow Clarity	A clear decision guide and token lifecycle diagram provide sequence, and the shipping checklist is structured, but there are no explicit validation checkpoints or feedback loops for the multi-step shipping flow.	2.5 / 3
Progressive Disclosure	The ~167-line body is well sectioned but monolithic — all detail (provider setup, full checklist, comparison tables) is inline with no one-level-deep references to bundle files, so content that could be split stays in SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong across all dimensions: concrete capabilities, natural trigger terms, explicit use-when guidance, and a distinct authentication niche. It reads in third person and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — "session vs JWT vs OAuth comparison", "provider selection (NextAuth, Clerk, Supabase Auth)", "security checklist", and "common mistakes" — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It explicitly states what the skill does (comparison, provider selection, checklist, mistakes) and includes a clear "Use when implementing auth, reviewing auth flows, or choosing auth providers" trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Natural user phrasings like "implementing auth", "reviewing auth flows", and "choosing auth providers" appear alongside common terms (session, JWT, OAuth, named providers), giving good coverage of words users would actually say.	3 / 3
Distinctiveness Conflict Risk	The authentication niche with named providers and distinct triggers is unlikely to fire for general web or database skills, matching the anchor for a clear niche with distinct triggers.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/authentication-patterns/SKILL.md
Commit: af7d491

Reviewed: about 9 hours 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.