auth-and-authorization-patterns

Use this skill when implementing authentication (login, token issuance) or authorization (access control, permissions). Apply whenever the task involves login flows, JWT, OAuth2, session management, or RBAC.

Quality

92%

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

85%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 body is a compact, well-organized reference of auth/authz best practices that respects token budget and assumes Claude's competence. Its main weakness is actionability: the guidance is concrete but advisory, with no executable code or copy-paste examples.

Suggestions

Add at least one short executable snippet (e.g., a bcrypt hashing call or a JWT claim-validation check) to lift actionability toward copy-paste ready.

For advisory directives like 'Implement MFA for sensitive operations', add a concrete starting point (library, flow, or verification step) so Claude knows exactly what to do.

Add a brief validation/verification step for token handling (e.g., 'Confirm the token validates all of iss, aud, exp, nonce before trusting claims') to make the OAuth2 workflow checkable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient, assuming Claude's knowledge — no explanation of what JWT, bcrypt, or OAuth2 are — with every line earning its place (e.g., 'Hash passwords with bcrypt/argon2; never MD5/SHA1'). It is not score 2 because there is no padding or unnecessary explanation.	3 / 3
Actionability	Provides concrete, specific guidance (named libraries, claims to validate, cookie flags, JWT lifetimes) but is advisory rather than executable — items like 'Implement MFA' are high-level with no code or copy-paste examples. It is not score 1 because guidance is concrete rather than abstract, and not score 3 because nothing is executable or copy-paste ready.	2 / 3
Workflow Clarity	A well-organized single-purpose skill under 50 lines, grouped into clear sections (Authentication, Authorization, OAuth2/OIDC, Session management). Per the simple-skills note this scores 3 when clear and well-organized; it is not score 2 because organization is explicit and unambiguous.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references and no bundle files present; content is well-organized into labeled sections, which satisfies the progressive-disclosure note for small skills. It is not score 2 because nothing is monolithic or poorly structured.	3 / 3
	Total	11 / 12 Passed

Description

100%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 concise and well-structured, clearly stating both the capabilities and the explicit 'Use when' trigger conditions with natural terminology. It distinguishes itself well from generic security skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'implementing authentication (login, token issuance) or authorization (access control, permissions)' — alongside named mechanisms (JWT, OAuth2, RBAC). It is not score 2 because the actions are explicitly enumerated rather than only naming a domain.	3 / 3
Completeness	Explicitly answers both what (auth/authorization, login, token issuance, access control) and when ('Use this skill when...', 'Apply whenever the task involves...'). The explicit 'Use when...' trigger clause avoids the cap at 2.	3 / 3
Trigger Term Quality	Includes natural user-facing terms — 'login flows, JWT, OAuth2, session management, or RBAC' — that a person would actually say when needing this skill. Coverage is broad enough to clear score 2, which only requires 'some relevant keywords.'	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (auth and authorization patterns) with distinct triggers (login, OAuth2, JWT, RBAC) unlikely to fire for unrelated skills. It is not score 2 because the triggers are specific rather than broadly overlapping.	3 / 3
	Total	12 / 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: aiming-lab/MetaClaw
Path: memory_data/skills/auth-and-authorization-patterns/SKILL.md
Commit: 922caf3

Reviewed: 9 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.