lsp

1 stars
14
B

Use when implementing Language Server Protocol features - diagnostics, completions, hover, go-to-definition, and editor integration

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/omg/lsp
skilz install mcclowes/omg/lsp --agent opencode
skilz install mcclowes/omg/lsp --agent codex
skilz install mcclowes/omg/lsp --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/omg
2. Copy the agent skill directory:
cp -r omg/.claude/skills/lsp ~/.claude/skills/

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

Related Agentic Skills

Agentic Skill Details

Repository
omg
Stars
1
Type
Technical
Meta-Domain
development
Primary Domain
testing
Market Score
14

Agent Skill Grade

B
Score: 83/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
24/30
Ease of Use
21/25
Writing Style
9/10
Utility
16/20
Modifiers: +1

Areas to Improve

  • Missing workflow guidance
  • Incomplete feedback loops
  • Limited practical examples

Recommendations

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

Graded: 2026-01-24

Developer Feedback

I've been digging into LSP implementations and your skill's approach to progressive disclosure really stands out—the way you've structured the documentation to guide developers from basics to advanced concepts without overwhelming them is exactly what's missing from most language server resources.

Links:

The TL;DR

You're at 83/100, solid B grade territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Writing Style (9/10)—the technical voice is clean and objective. The weakest spots are Spec Compliance (12/15) and Progressive Disclosure (24/30), both fixable with some focused additions.

What's Working Well

  • Solid trigger phrases: Your description nails the LSP vocabulary—"diagnostics," "completions," "hover," "go-to-definition" will get the skill surfacing for the right queries.
  • Clean Quick Start example: The 24-line code snippet actually teaches something without bloat; it demonstrates connection setup and capability registration without being overwhelming.
  • Smart provider table: Listing available LSP providers (textDocument/completion, textDocument/hover, etc.) gives developers flexibility without constraining their choices.
  • Consistent terminology: You stick with LSP language throughout—TextDocuments, Capabilities, Connection—which makes the skill feel authoritative.

The Big One: Missing Workflow Guidance

This is what's costing you the most points. Right now you present concepts (Core Concepts, Key Patterns) but no procedural workflow. Developers don't know what order to do things in.

The fix: Add a numbered workflow section before Core Concepts:

## Implementation Workflow

1. **Set up connection** - Initialize ServerCapabilities and establish connection...

Report Security Issue

Found a security vulnerability in this agent skill?