An exemplar content body: lean, executable, and well-structured, with a real source-discovery workflow, validation/typecheck checkpoints, and a clean one-level reference split that keeps the overview navigable. The minor editorializing does not materially weaken it.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable — tables of imports/mounts, concrete shell commands, and copy-paste TS blocks — assuming Claude's competence rather than re-explaining library basics. A few editorial lines ('Ship code against the current source, not memory') are mild padding but not enough to drop below the lean-and-efficient anchor.	3 / 3
Actionability	Fully executable guidance throughout: `ask src better-auth`, `bun add better-auth`, `rg "^export " $SRC/...`, `npx auth generate`, plus concrete server/client/framework/plugin/DB-adapter import paths and code blocks that are copy-paste ready.	3 / 3
Workflow Clarity	A clear sequence is given (resolve installed version → verify plugin/adapter shapes → write code → typecheck → surface conflicts), with an explicit validation checkpoint ('Run typecheck after changes to surface silent breakage early') and a feedback loop section ('When Typecheck or Runtime Fails') that routes through `references/common-errors.md` then source grep.	3 / 3
Progressive Disclosure	SKILL.md is a well-signaled overview with four one-level-deep references (adapters.md, plugins.md, databases.md, common-errors.md), all verified to exist under ./references/, each clearly scoped in the References section, with no nested two-plus-level indirection.	3 / 3
	Total	12 / 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.

A strong, third-person description that crisply states what the skill does and when to invoke it, with concrete API names and an explicit trigger list. It avoids vague fluff and over-claims while covering a clear niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Answer questions about better-auth', 'help build authentication features', wire up sign-in/sign-up/sessions, integrate named framework adapters, add named plugins, configure named DB adapters) with specific identifiers like `betterAuth`, `authClient.*`.	3 / 3
Completeness	Clearly answers both 'what' (answer questions and build auth features with enumerated capabilities) and 'when' ('Use when developers: (1)...' plus a 'Triggers on:' list), with explicit trigger guidance.	3 / 3
Trigger Term Quality	An explicit 'Triggers on:' list provides natural terms a user would say — 'better-auth', 'sign in flow', 'auth session', 'social login', 'magic link', 'passkey', 'organization plugin' — giving good coverage of natural phrasings.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to the named better-auth library, its specific plugins (organization, two-factor, magic-link, passkey, oauth-proxy) and named frameworks/DB adapters, making it unlikely to trigger for the wrong skill.	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.

Reviewed

29 days ago

Table of Contents

Discovery Implementation Validation