lsp

Multi-language code navigation via persistent LSP daemons. Supports Python (pyright), TypeScript/JS, Rust, Go, C/C++, Bash, Java, CSS, HTML, JSON. Auto-detects language from file extension and lazy-starts the appropriate server. Use instead of grep for definitions, references, hover, symbols, and diagnostics.

3,891 stars

Best use case

lsp is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Multi-language code navigation via persistent LSP daemons. Supports Python (pyright), TypeScript/JS, Rust, Go, C/C++, Bash, Java, CSS, HTML, JSON. Auto-detects language from file extension and lazy-starts the appropriate server. Use instead of grep for definitions, references, hover, symbols, and diagnostics.

Teams using lsp should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/lsp/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/adamnaghs/lsp/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/lsp/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How lsp Compares

Feature / AgentlspStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Multi-language code navigation via persistent LSP daemons. Supports Python (pyright), TypeScript/JS, Rust, Go, C/C++, Bash, Java, CSS, HTML, JSON. Auto-detects language from file extension and lazy-starts the appropriate server. Use instead of grep for definitions, references, hover, symbols, and diagnostics.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# LSP Code Navigation

Multi-language LSP client that manages per-language background daemons. Auto-detects the language from file extension and routes queries to the correct server. Each server lazy-starts on first use and idles out after 5 minutes of inactivity.

**Use this instead of grep/read when you need to:**
- Find where something is defined
- Find all usages of a symbol
- Get type signatures or docstrings
- List all classes/functions in a file
- Check for type errors before running code
- Search for a symbol across an entire workspace

## Supported Languages

| Language | Server | Extensions | Install |
|----------|--------|------------|---------|
| Python | `pyright-langserver` | .py, .pyi, .pyx | `npm install -g pyright` |
| TypeScript/JS | `typescript-language-server` | .ts, .tsx, .js, .jsx, .mjs, .cjs | `npm install -g typescript-language-server typescript` |
| Rust | `rust-analyzer` | .rs | `rustup component add rust-analyzer` |
| Go | `gopls` | .go | `go install golang.org/x/tools/gopls@latest` |
| C/C++ | `clangd` | .c, .h, .cpp, .cc, .hpp | `apt install clangd` or `brew install llvm` |
| Bash | `bash-language-server` | .sh, .bash, .zsh | `npm install -g bash-language-server` |
| Java | `jdtls` | .java | [eclipse.jdt.ls](https://github.com/eclipse-jdtls/eclipse.jdt.ls) |
| CSS | `vscode-css-language-server` | .css, .scss, .less | `npm install -g vscode-langservers-extracted` |
| HTML | `vscode-html-language-server` | .html, .htm | `npm install -g vscode-langservers-extracted` |
| JSON | `vscode-json-language-server` | .json, .jsonc | `npm install -g vscode-langservers-extracted` |

Only install the servers you need. The skill auto-detects which are available and reports helpful install commands for missing ones.

## Setup

### Prerequisites

- Python 3.10+ (for the client script itself -- stdlib only, no pip deps)
- At least one language server installed (see table above)

### Installation

The skill includes a Python script at `{baseDir}/scripts/lsp-query.py`. This is the LSP client -- it manages background daemons and handles all queries.

To make it callable as `lsp-query` from anywhere, symlink it into your PATH:

```bash
ln -sf {baseDir}/scripts/lsp-query.py /usr/local/bin/lsp-query
# or:
ln -sf {baseDir}/scripts/lsp-query.py ~/.npm-global/bin/lsp-query
```

Alternatively, invoke it directly:

```bash
{baseDir}/scripts/lsp-query.py <command> [args...]
```

### Configuration

Set `LSP_WORKSPACE` to the repo root before querying. If unset, defaults to the git root or cwd.

## Commands

All line and column numbers are **1-indexed** (human-friendly, matching editor display).

### Go to Definition

```bash
lsp-query definition /path/to/file.py <line> <col>
```

### Find References

```bash
lsp-query references /path/to/file.py <line> <col>
```

### Hover (Type Info)

```bash
lsp-query hover /path/to/file.py <line> <col>
```

### Document Symbols

```bash
lsp-query symbols /path/to/file.py
```

### Workspace Symbol Search

```bash
lsp-query workspace-symbols "ClassName"
```

### Diagnostics

```bash
lsp-query diagnostics /path/to/file.py
```

### Completions

```bash
lsp-query completions /path/to/file.py <line> <col>
```

### Signature Help

```bash
lsp-query signature /path/to/file.py <line> <col>
```

### Rename Preview

```bash
lsp-query rename /path/to/file.py <line> <col> new_name
```

### Server Management

```bash
lsp-query languages                    # Show all supported languages + install status
lsp-query servers                      # List running language daemons
lsp-query shutdown                     # Stop all daemons
lsp-query shutdown python              # Stop just the Python daemon
```

## What's Included

```
{baseDir}/
├── SKILL.md              # This file
└── scripts/
    └── lsp-query.py      # Python script -- multi-language LSP client + daemon manager
```

`lsp-query.py` is a self-contained Python script (~850 lines, stdlib only, no pip dependencies). It:
1. Forks a single background daemon process on first use
2. The daemon lazy-starts language servers as needed (e.g., pyright for .py, typescript-language-server for .ts)
3. Communicates with the daemon over a Unix socket (`~/.cache/lsp-query/daemon.sock`)
4. Translates CLI commands into LSP JSON-RPC requests and prints human-readable results
5. Each language server auto-stops after 5 minutes idle; the daemon itself stops when all servers are idle

## Environment Variables

| Variable | Default | Description |
|----------|---------|-------------|
| `LSP_WORKSPACE` | git root or cwd | Workspace root for LSP servers |
| `LSP_SERVER` | auto per language | Override server command for ALL languages |
| `LSP_LANG` | auto from extension | Force a specific language (bypass detection) |
| `LSP_TIMEOUT` | `300` | Server idle timeout in seconds |
| `LSP_SOCK` | `~/.cache/lsp-query/daemon.sock` | Unix socket path |

## Examples

```bash
export LSP_WORKSPACE=/path/to/repo

# Python
lsp-query symbols src/model.py
lsp-query hover src/model.py 42 10
lsp-query references src/model.py 42 10

# TypeScript (auto-detected from .ts extension)
lsp-query symbols src/index.ts
lsp-query definition src/app.tsx 15 8

# Rust
lsp-query symbols src/main.rs
lsp-query diagnostics src/lib.rs

# Check what's available
lsp-query languages
lsp-query servers
```

## Troubleshooting

- **"Server not found for X"**: The language server binary isn't installed. The error message includes the install command.
- **"could not connect to LSP daemon"**: Daemon failed to start. Verify Python 3.10+ is available.
- **Import errors in diagnostics**: Expected when packages aren't installed in the current Python environment. These resolve on machines with the correct venv.
- **Stale results**: Run `lsp-query shutdown` to restart all servers fresh.
- **Slow first query per language**: Each server takes 1-2 seconds to cold-start. Subsequent queries to the same language are ~200ms.
- **Wrong language detected**: Use `LSP_LANG=rust lsp-query symbols myfile` to force.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation