Skillzwave Logo
Skillzwave

nextjs-devtools

17.3
D

Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps.Use when working on Next.js applications, debugging routing, or inspecting app structure.NOT for general React or non-Next.js projects.

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-devtools
skilz install mjunaidca/mjs-agent-skills/nextjs-devtools --agent opencode
skilz install mjunaidca/mjs-agent-skills/nextjs-devtools --agent codex
skilz install mjunaidca/mjs-agent-skills/nextjs-devtools --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/.claude/skills/nextjs-devtools ~/.claude/skills/

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

Related Agentic Skills

tailwind-shadcn-setup

by vanman2024

Setup Tailwind CSS and shadcn/ui component library for Next.js projects. Use when configuring Tailwind CSS, installing shadcn/ui, setting up design to...

89
B
TECHjavascript
Marketplace
+github+json

spanish-language-tutor

by sandraschi

Comprehensive Spanish language expert covering grammar, conversation, regional dialects, and language learning strategies

88
B
javascript
+github

frontend-dev-guidelines

by diet103

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organizati...

85
B
TECHjavascript

torch-geometric

by davila7

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for...

84
B
TECHjavascript
Marketplace
+machine learning

Agentic Skill Details

Type
Technical
Meta-Domain
development
Primary Domain
javascript
Market Score
17.3

Agent Skill Grade

D
Score: 67/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
20/30
Ease of Use
18/25
Writing Style
7/10
Utility
11/20
Modifiers: -1

Areas to Improve

  • Scripts referenced (start-server.sh, mcp-client.py) don't exist in skill directory
  • File exceeds 100 lines without table of contents for navigation
  • Workflows lack validation steps; no run→check→fix patterns for debugging

Recommendations

  • Focus on improving Utility (currently 11/20)
  • Address 3 high-severity issues first
  • Add trigger phrases to description for discoverability

Graded: 1/24/2026

Developer Feedback

I was curious how you'd handle integrating devtools into the Next.js ecosystem—the timing hints at solving some real pain points in the developer experience, but the implementation seems to be missing some structural decisions that would make it production-ready.

Links:

The TL;DR

You're at 67/100, which puts you in D territory. This is graded against Anthropic's skill best practices—specifically their Progressive Disclosure Architecture (PDA) standards. Your strongest area is Spec Compliance (12/15), but Utility is dragging you down hard at 11/20. The good news? You've got a solid foundation; you're just missing the structural pieces that would make this actually useful at scale.

What's Working Well

  • Spec compliance is solid — your frontmatter is valid YAML with all required fields, and the hyphen-case naming convention is correct
  • Clear trigger phrases — terms like "Next.js debugging," "inspect routes," and "component tree inspection" are discoverable and specific
  • Good troubleshooting table — having a dedicated section with common issues shows you're thinking about user pain points
  • Concrete command examples — you provide actual bash commands users can run, which is better than abstract explanations

The Big One: Missing Scripts and Layered Structure

Here's what's holding you back the most: you reference scripts (scripts/start-server.sh, scripts/mcp-client.py) that don't exist in your skill package, and everything lives in a single 103-line SKILL.md file with no supporting documentation.

Why it matters: Users can't actually run your examples. When they try bash scripts/start-server.sh, it fails. That breaks trust immediately.

The fix: Either include the actual scripts in your skill's directory structure, or remove the references and document the manual setup steps inline. If you're going with scripts, create a scripts/ subdirectory with those files. If going manual, walk through each setup step explicitly. Additionally, create a references/ directory—pull out the MCP server setup details into references/mcp-setup.md and detailed tool documentation into references/tools-reference.md. This gives you the PDA layering you're missing (+4 points).

Other Things Worth Fixing

  1. Add a table of contents — at 103 lines, your skill needs navigation. Add one right after the title with links to Quick Start, Available Tools, Workflow Patterns, Scripts, and Troubleshooting (+1 point)

  2. Show example outputs — you explain what each tool does, but users don't see what success looks like. Add JSON/text samples showing what list-routes or inspect-component actually returns (+1 point)

  3. Build validation loops into workflows — your "Workflow Patterns" section shows commands but no verification steps. Add: "Run command → Check output contains X → If missing, verify Y → Re-run after fixes" patterns. This bridges the gap between knowing what to run and knowing if it worked (+3 points)

  4. Consolidate repetitive bash — that full python3 scripts/mcp-client.py call -s "npx next-devtools-mcp@latest" command appears 7+ times. Define it once as an alias or variable, then reuse it (+1 point)

Quick Wins

  • Most impactful: Include actual scripts or document manual setup (verify this works end-to-end)
  • Second: Restructure into PDA layers—move MCP details to references/mcp-setup.md
  • Third: Add example outputs so users know what to expect
  • Easy: Add a TOC, fix terminology consistency (pick "on-demand" OR "per-call"), build validation into workflows

These fixes would bump you to roughly 80/100 and move you from D to B territory.


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?