CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nextjs

Next.js App Router expert guidance. Use when building, debugging, or architecting Next.js applications — routing, Server Components, Server Actions, Cache Components, layouts, middleware/proxy, data fetching, rendering strategies, and deployment on Vercel.

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured progressive-disclosure index: lean, navigable, with verified one-level references. The main weakness is that the body delegates everything — no inline code or rules for the most common cases — plus one orphaned bundle file.

Suggestions

Inline a few copy-paste snippets for the highest-frequency patterns (e.g. 'use client' directive placement, awaiting params/searchParams in Next.js 15+) so common tasks don't require loading a reference file.

Link references/app-router-files.md from the body (e.g. from the File Conventions section) or fold its content into file-conventions.md so no bundle file is undiscoverable.

Add a brief 'which file do I need' decision hint or ordering (e.g. check file-conventions and rsc-boundaries first when reviewing existing code) to guide selection across the 18 topics.

DimensionReasoningScore

Conciseness

The body is a lean ~145-line index: each section is a one-line pointer plus 3-5 topic bullets ("See [rsc-boundaries.md](references/rsc-boundaries.md) for: Async client component detection..."). No concept explanations Claude already knows, no padding; the one-line intros ("Next.js 15+ async API changes.") earn their place as version context. It is not below 5 — nothing here can be cut without losing discovery value.

5 / 5

Actionability

Pointers are concrete (exact file paths with topic bullets), but the body itself contains no executable guidance — no code, commands, or rules; the directive "Apply these rules when writing or reviewing Next.js code" defers all actual rules to the references. This fits the 3 anchor (some concrete guidance but incomplete / missing key details) rather than 4, since even the most common cases (e.g. 'use client' placement, async params) have no inline example; it is above 2 because the navigation it does give is specific and immediately followable.

3 / 5

Workflow Clarity

For a reference-lookup skill the single action is unambiguous (match the concern, read the named file), and the 18 concern-labeled sections make selection easy. Not a 5: with 18 parallel topics there is no guidance on priority or which file to consult when multiple apply, and no verification step for applying rules during code review; not a 3 because the structure itself is coherent and complete with no gaps in the lookup flow.

4 / 5

Progressive Disclosure

Textbook one-level-deep structure: every section links a real file in references/ (all 19 linked paths verified to exist, no nested .md chains), each clearly signaled with topic bullets. It falls short of 5 because the bundle contains references/app-router-files.md, which is never linked from the body — an orphaned file that hurts discoverability against the 'easy navigation' anchor.

4 / 5

Total

16

/

20

Passed

Description

87%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 strong description: explicit what+when, concrete topic coverage, and natural trigger terms scoped to a distinct framework niche. The only softness is the abstract head noun "expert guidance" carried by a topic list rather than concrete operation verbs.

DimensionReasoningScore

Specificity

"building, debugging, or architecting Next.js applications" names three concrete actions, and the enumeration "routing, Server Components, Server Actions, Cache Components, layouts, middleware/proxy, data fetching, rendering strategies, and deployment on Vercel" gives broad, specific coverage. Not a 5 because the head noun "expert guidance" is abstract — capability is conveyed as a topic list rather than multiple concrete operations like the 5-anchor examples ("Extract text... fill forms, merge documents").

4 / 5

Completeness

Explicitly answers both: what ("Next.js App Router expert guidance" with a concrete topic inventory) and when ("Use when building, debugging, or architecting Next.js applications"), with concrete trigger phrases. This matches the 5-anchor pattern (what + explicit 'Use when...' with triggers); it is not a 4 because the 'when' clause is specific and multi-scenario, not merely present.

5 / 5

Trigger Term Quality

Strong natural phrases users would say — "Next.js", "App Router", "Server Components", "Server Actions", "layouts", "data fetching", "Vercel". A few natural terms are missing (e.g. "use client", "pages router", file extensions like .tsx), so it falls short of the comprehensive-with-synonyms 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Next.js App Router" is a clear, well-named niche with distinct framework-specific triggers (Server Actions, Cache Components, middleware/proxy, Vercel), so overlap with generic React or web-dev skills is minimal.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/nextjs/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.