vscode-extension

3 stars
16
B

Use when developing VSCode extensions - covers language support, LSP integration, and packaging

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 mcclowes/lea/vscode-extension
skilz install mcclowes/lea/vscode-extension --agent opencode
skilz install mcclowes/lea/vscode-extension --agent codex
skilz install mcclowes/lea/vscode-extension --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

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/mcclowes/lea
2. Copy the agent skill directory:
cp -r lea/.claude/skills/vscode-extension ~/.claude/skills/

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

Related Agentic Skills

Agentic Skill Details

Repository
lea
Stars
3
Type
Technical
Meta-Domain
development
Primary Domain
testing
Market Score
16

Agent Skill Grade

B
Score: 83/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
24/30
Ease of Use
20/25
Writing Style
8/10
Utility
16/20
Modifiers: +3

Areas to Improve

  • Missing TOC in SKILL.md
  • No workflow checklists
  • Missing feedback loops

Recommendations

  • Address 2 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I found your vscode-extension skill while reviewing the marketplace—the B grade (83/100) actually highlights something interesting: you've built something genuinely useful, but there's untapped potential in how you're explaining why it matters to developers who might use it.

Links:

The TL;DR

You're at 83/100, solid B territory. This is based on Anthropic's skill best practices across five pillars. Your strongest area is Spec Compliance (12/15)—the frontmatter and structure are clean. The weakest is Ease of Use (20/25) and Utility (16/20), which is where you can make the biggest impact. The gap here isn't about technical depth; it's about guiding developers when and how to actually use this.

What's Working Well

  • Clear trigger phrases - You've got 'VSCode extensions', 'LSP integration', and 'packaging' scattered through the description, which helps discoverability.
  • Good layered structure - SKILL.md hooks into reference files (activation.md, commands.md) exactly one level deep. That's the architecture working.
  • Solid code examples - The activation and command setup examples show input/output clearly. Developers can see what to expect.
  • Consistent terminology - 'activation', 'command', 'client' used the same way throughout. No surprises.

The Big One: Missing Workflow & Testing Guidance

Here's what's holding you back most: you're showing configuration code, but not how developers actually validate that it works. The Utility score (16/20) drops because there's zero guidance on debugging, testing, or what success looks like.

Right now, someone using this skill gets activation setup and command definitions—but then what? They hit F5 and... is it working? Where do they look for errors? What if...

Report Security Issue

Found a security vulnerability in this agent skill?