Skillzwave Logo
Skillzwave

nextjs-16

17.3
B

Build Next.js 16 applications with the correct patterns. Use this skill when creating pages, layouts, middleware (now proxy.ts), dynamic routes, or upgrading from Next.js 15. Covers breaking changes like async params/searchParams, Turbopack defaults, proxy.ts (replacing middleware.ts), and cacheComponents.

Also in: pdf javascript

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install mjunaidca/mjs-agent-skills/nextjs-16
skilz install mjunaidca/mjs-agent-skills/nextjs-16 --agent opencode
skilz install mjunaidca/mjs-agent-skills/nextjs-16 --agent codex
skilz install mjunaidca/mjs-agent-skills/nextjs-16 --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding agents

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/mjunaidca/mjs-agent-skills
2. Copy the agent skill directory:
cp -r mjs-agent-skills/docs/taskflow-vault/skills/engineering/nextjs-16 ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

exec-briefing

by gtmagents

Use to craft concise executive updates, agendas, and follow-up logs for QBR/EBR sessions.

93
A
ci cd
Marketplace

makefile-review

by athola

Audit Makefiles for duplication, portability, and idiomatic GNU Make usage.Triggers: Makefile review, build system, GNU Make, portability, deduplicati...

80
B
TECHci cd
Marketplace
+networking

build-assistant

by vanman2024

Build Claude Code framework components (agents, slash commands, skills, plugins) following standardized templates. Use when creating new agents, comma...

74
C
TECHci cd
Marketplace

astro-patterns

by vanman2024

Astro best practices, routing patterns, component architecture, and static site generation techniques. Use when building Astro websites, setting up ro...

63
D
TECHci cd
Marketplace

Agentic Skill Details

Type
Technical
Meta-Domain
development
Primary Domain
ci cd
Market Score
17.3

Agent Skill Grade

B
Score: 87/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
27/30
Ease of Use
22/25
Writing Style
9/10
Utility
18/20

Areas to Improve

  • No trigger phrases
  • SKILL.md is 719 lines without a table of contents; PDA guidelines require TOC for files >100 lines
  • Common patterns and implementations shown as examples but not as explicit step-by-step workflows

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 1/24/2026

Developer Feedback

I looked at your nextjs-16 skill and noticed you're tackling the async component patterns that most devs still find confusing in App Router—the streaming and Suspense integration feels like it actually accounts for real-world complexity rather than glossing over it, which is probably why you landed at an 87.

Links:

The TL;DR

You're at 87/100, solid B territory. This skill is grounded in Anthropic's best practices for agentic skill design. Your strongest area is Progressive Disclosure Architecture (27/30)—you've got the layering right with references tucked away cleanly. Weakest spot is Spec Compliance (11/15), mostly because your description is missing trigger phrases that help agents discover and activate the skill.

What's Working Well

  • Progressive Disclosure nailed it: You're not dumping everything into one massive wall of text. The SKILL.md uses ~719 lines efficiently with practical examples and clear separation into references (httpOnly-cookie-proxy.md, better-auth-integration.md). Token economy is excellent.

  • Triggering is thoughtful: Your activation keywords ("pages", "layouts", "middleware", "proxy.ts", "upgrading") are specific enough that an agent knows exactly when to reach for this skill, not generic buzzwords.

  • Real-world patterns over theory: You're showing actual httpOnly cookie forwarding, async params gotchas, and the migration checklist—the stuff devs actually need when upgrading, not just "here's what changed."

  • Consistent terminology: "proxy" (not middleware), "async params", "cacheComponents"—you stick to the actual Next.js 16 API names, which makes it grep-friendly and reduces confusion.

The Big One: Add Trigger Phrases to Your Description

This is holding back your Spec Compliance score by 2-3 points. Right now your description reads like:

"Build Next.js 16 applications with the correct patterns. Use this skill when creating pages, layouts..."

Agents need explicit trigger phrases in the description field so they know how to invoke you. Change it to:

"Performs Next.js 16 operations. Use when asked to 'nextjs 16', 'upgrade to nextjs 16', 'nextjs 16 patterns', or 'nextjs app router'."

This small addition unlocks better discoverability in agent routing and improves your Spec Compliance from 11 to 13 points.

Other Things Worth Fixing

  1. Add a table of contents (→ +1 point): A 719-line SKILL.md needs a TOC at the top. PDA guidelines say files over 100 lines should have one. Add it right after the title with links to your major sections (When to Use, Breaking Changes, Common Pitfalls, Migration Checklist).

  2. Convert examples to numbered workflows (→ +2 points): Your httpOnly cookie proxy and Better Auth integration are shown as examples, but agents work better with step-by-step workflows. "1. Create catch-all route at app/api/proxy/[...path]/route.ts → 2. Import cookies from next/headers → 3. Read httpOnly token → 4. Forward with Authorization header."

  3. Cut repetition in Common Pitfalls (→ +1 point): Your "Forgetting to await params" section repeats the same code you already showed in Breaking Changes #1. Link to it instead with a brief explanation of the symptom and fix.

  4. Add actual error output (→ +1 point): Show the TypeScript errors and runtime output users will actually see. When they forget await params, display shows [object Promise]. When types are wrong, show the actual error message from the compiler.

Quick Wins

  • Add trigger phrases to description (2-3 pts)
  • TOC for the long SKILL.md (1 pt)
  • Workflows over examples (2 pts)
  • Cut repetition in pitfalls section (1 pt)
  • Include error messages alongside code examples (1 pt)

These fixes should push you from 87 to 94-96 range. You've got the hard part down—making it discoverable and structured is just cleanup.


Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.

Report Security Issue

Found a security vulnerability in this agent skill?