CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clerk-auth

Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentication, sign in, sign up.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/clerk-auth/SKILL.md

The canonical home for this skill is clerk-auth in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

32%Weight 40%Scale 1-5

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 skeletal outline: it correctly identifies the important Clerk patterns but gives no executable guidance, no workflow sequence, and — most damaging — an all-placeholder sharp-edges table whose "See docs" solutions reference documentation that does not exist anywhere in the bundle. The skill names the right topics but cannot currently guide an implementation.

Suggestions

Replace every 'Issue | See docs' placeholder row in the Sharp Edges table with the actual issue and its concrete fix (or move the table to a references/sharp-edges.md file that actually exists), since these are marked critical/high severity yet currently carry zero information.

Add minimal executable snippets to each pattern: the ClerkProvider wrapper with the required env var names (e.g. NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY/CLERK_SECRET_KEY), the middleware.ts code using createRouteMatcher and auth.protect(), and an auth() usage example in a server component.

Turn the three pattern sections into an ordered workflow (install dependencies -> wrap app in ClerkProvider -> add middleware -> protect routes -> access auth in server components) and delete the generic 'When to Use' filler line in favor of the concrete triggers already present in the description.

DimensionReasoningScore

Conciseness

The body is short and mostly lean with bullets rather than padded prose, but 8 placeholder table rows ("Issue | critical | See docs"), a boilerplate 'When to Use' sentence, and uncontextualized version numbers ("Next.js 14/15") waste tokens, fitting anchor 3's mostly-efficient-but-needs-tightening.

3 / 5

Actionability

The body names APIs and components (ClerkProvider, <SignIn />, auth(), createRouteMatcher, auth.protect()) but provides zero executable code, environment variable names, or commands, and every sharp-edge 'solution' is the unactionable 'See docs' — matching anchor 2's high-level hints missing the specific steps to execute rather than anchor 3's partially concrete guidance.

2 / 5

Workflow Clarity

Content is organized as topical patterns with no setup sequence (install, provider, middleware, protect), and the one place validation/error guidance belongs — the sharp-edges table — is entirely placeholders. This matches anchor 2's rough outline with many gaps and absent validation; it does not reach anchor 3 because even listed steps with implicit checkpoints are missing.

2 / 5

Progressive Disclosure

No references/, scripts/, or assets/ files exist in the bundle, yet the body's "See docs" is repeated 8 times pointing to nothing, leaving the critical sharp-edges content unreachable. The section headers provide some structure, but the dangling references and content that clearly should live in a real reference file or be inlined fit anchor 2 rather than anchor 3's present-but-unclear references.

2 / 5

Total

9

/

20

Passed

Description

70%Weight 40%Scale 1-5

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 solidly above-average description with an explicit and natural 'Use when:' trigger clause covering the main Clerk capability areas. Its weaknesses are the noun-topic 'what' framing ('Expert patterns for...') rather than concrete actions, and mostly generic auth triggers that overlap with non-Clerk auth skills.

DimensionReasoningScore

Specificity

Names the Clerk domain and several concrete sub-areas ("middleware, organizations, webhooks, and user sync"), but they are presented as topics under 'Expert patterns for' with no action verbs, matching anchor 3's non-comprehensive capability listing rather than anchor 4's several specific actions.

3 / 5

Completeness

Both 'what' ("Clerk auth implementation, middleware, organizations, webhooks, and user sync") and an explicit 'Use when:' clause with concrete triggers are present, exceeding anchor 4's weakly-specified 'when'; however the noun-based capability list plus 'Expert patterns' filler falls short of anchor 5's fully concrete action enumeration, placing it between anchors.

4 / 5

Trigger Term Quality

"adding authentication, clerk auth, user authentication, sign in, sign up" are natural phrases users would say, with the Clerk-specific trigger included; common variations like "log in", "login", and "session" are missing, matching anchor 4's good-but-incomplete keyword coverage.

4 / 5

Distinctiveness Conflict Risk

The skill is clearly niched to Clerk with a distinctive "clerk auth" trigger, but most triggers ("adding authentication", "user authentication", "sign in", "sign up") are generic and would also match other auth-provider skills, fitting anchor 4's minor overlap risk with closely related skills rather than anchor 5's minimal conflict risk.

4 / 5

Total

15

/

20

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/clerk-auth/SKILL.md

Reviewed

Table of Contents

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.