A precise Language Server Protocol integration for Openclaw Skills that enables deep code intelligence and navigation.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install lsp-assist
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install lsp-assist using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
lsp-assist is a specialized integration designed for Openclaw Skills that brings the full power of the Language Server Protocol (LSP) to AI coding agents. While basic agents often rely on grep or simple string searches, lsp-assist provides a deeper understanding of the codebase by interacting directly with official language servers like pyright and the typescript-language-server. This allows agents to resolve complex symbol definitions, track cross-file references, and perform type-aware analysis with the same accuracy as a modern IDE.
Built with performance and security in mind, this skill supports both a high-throughput daemon mode for ongoing development sessions and a one-shot mode for quick, isolated queries. It acts as the bridge between an agent's logical reasoning and the technical truth of a compiled or interpreted project, making it an essential component for any developer building sophisticated agents with Openclaw Skills.
To integrate lsp-assist into your environment for Openclaw Skills, ensure you have Python 3.10+ and the necessary language servers installed.
# Install the required language servers globally
npm i -g typescript-language-server typescript
pip install pyright
# To start the daemon for a specific project
python3 scripts/lsp_client.py daemon --lang typescript --root /path/to/project --port 9876
# For a single query without a persistent daemon (One-shot mode)
python3 scripts/lsp_client.py --lang python --root . goto --file main.py --line 5 --col 10
The skill returns structured JSON data to ensure compatibility with agentic workflows. Below is the mapping of actions to their output structures:
| Action | Return Format | Description |
|---|---|---|
goto / refs |
Array<Object> |
Contains file, line, and col keys for symbol locations. |
hover |
String |
A markdown-formatted string describing the symbol type and documentation. |
diag |
Array<Object> |
Lists severity, line, and message for project errors. |
symbols |
Array<Object> |
Detailed list including symbol name, kind, and container. |
ping |
Object |
Health check returning {"status": "ok"}. |
Loading
A specialized tool for formatting self-media articles into highly readable, visually appealing, and mobile-optimized content.

A sophisticated automation suite that executes, chains, and manages AI applications on transweb.cn through browser-based agent workflows.

A comprehensive skill for AI agents to register, publish services, and conduct autonomous transactions within a decentralized marketplace.

Snail is an AI agent dating protocol that prioritizes cautious matching and slow-paced connection building.

Kindergarten Video is a specialized AI agent skill designed to create professional enrollment and marketing videos that simplify the transition from preschool to kindergarten.

A professional tool for building AI-ready corpora using intelligent chunking, multi-dimensional AI annotation, and vector database storage.








































