lsp-management
LSP server recommendations, .lsp.json configuration, installation guides, and troubleshooting for Language Server Protocol in Claude Code
What this skill does
# LSP Management Skill
> ## ๐จ MANDATORY: Invoke docs-management First
>
> **STOP - Before providing ANY response about LSP configuration:**
>
> 1. **INVOKE** `docs-management` skill for Claude Code LSP documentation
> 2. **QUERY** for the user's specific LSP topic
> 3. **BASE** all responses on official documentation + this skill's knowledge base
>
> **Skipping this step results in outdated or incorrect information.**
## โ ๏ธ EXPERIMENTAL: Claude Code LSP Status
**LSP support in Claude Code is experimental and has known issues.** Key points:
| Requirement | Details |
|-------------|---------|
| **Environment Variable** | `ENABLE_LSP_TOOL=1` (singular) required to expose LSP tool |
| **Current Version** | v2.1.0+ has partial support (regression #17468) |
| **Stable Version** | v2.0.67 is last known stable LSP version |
| **Configuration** | `.lsp.json` at project root or `lspServers` in plugin.json |
**See [troubleshooting.md](references/troubleshooting.md) for version-specific issues and workarounds.**
## Overview
Central authority for Language Server Protocol (LSP) configuration in Claude Code. This skill provides:
- **LSP server recommendations** by language/technology
- **Configuration patterns** for `.lsp.json` files
- **Installation guides** for each recommended server
- **Troubleshooting** for common LSP issues
**Architecture:** Keyword registry + curated knowledge base. Delegates to docs-management for official Claude Code LSP documentation.
## When to Use This Skill
**Keywords:** LSP, language server, language-server-protocol, code intelligence, hover, go-to-definition, find-references, diagnostics, pyright, typescript-language-server, gopls, rust-analyzer, csharp-ls, .lsp.json, LSP configuration, LSP setup, LSP troubleshooting
**Use this skill when:**
- Setting up LSP servers for a project
- Choosing between LSP server options for a language
- Configuring `.lsp.json` files
- Troubleshooting LSP issues (hover not working, diagnostics missing, etc.)
- Understanding LSP server installation requirements
- Auto-detecting needed LSPs based on project file types
## Keyword Registry for docs-management Queries
Use these keywords when querying docs-management skill for official documentation:
### Core Concepts
| Topic | Keywords |
| --- | --- |
| LSP Overview | "LSP", "language server protocol", "code intelligence" |
| Configuration File | ".lsp.json", "LSP configuration", "language server config" |
| Features | "hover", "go-to-definition", "find-references", "diagnostics", "document symbols" |
### Server-Specific
| Topic | Keywords |
| --- | --- |
| Python | "pyright", "pylsp", "python language server" |
| TypeScript/JavaScript | "typescript-language-server", "vtsls", "tsserver" |
| Go | "gopls", "go language server" |
| Rust | "rust-analyzer", "rust language server" |
| C# | "csharp-ls", "OmniSharp", "C# language server" |
| C/C++ | "clangd", "ccls", "C++ language server" |
### Troubleshooting
| Topic | Keywords |
| --- | --- |
| Server Issues | "LSP not working", "language server crash", "LSP restart" |
| Feature Issues | "hover not working", "diagnostics missing", "go-to-definition failing" |
| Configuration Issues | "LSP config invalid", ".lsp.json error", "extension mapping" |
## Quick Decision Tree
**What do you need?**
1. **Set up LSP for a new project** โ See [server-database.md](references/server-database.md) for recommended servers
2. **Configure .lsp.json** โ See [configuration-patterns.md](references/configuration-patterns.md) for patterns
3. **Install a specific LSP server** โ See [installation-guide.md](references/installation-guide.md) for per-server commands
4. **Fix LSP issues** โ See [troubleshooting.md](references/troubleshooting.md) for common problems
5. **Understand Claude Code LSP support** โ Query docs-management: "LSP configuration Claude Code"
## LSP Server Recommendations (Quick Reference)
| Language | Recommended Server | Why |
| --- | --- | --- |
| Python | Pyright | Fast, accurate type checking, broad ecosystem support |
| TypeScript/JavaScript | typescript-language-server | Official TypeScript support, widely used |
| Go | gopls | Official Go team server, comprehensive |
| Rust | rust-analyzer | De facto standard, excellent performance |
| C# | csharp-ls | Lightweight, cross-platform, dotnet tool |
| C/C++ | clangd | LLVM-backed, fast, accurate |
| Java | Eclipse JDTLS | Full-featured, widely supported |
| Ruby | solargraph | Type inference, documentation support |
| PHP | intelephense | Premium features, fast |
| Lua | lua-language-server | Official, well-maintained |
| YAML | yaml-language-server | Schema validation, completion |
| JSON | vscode-json-languageserver | Schema validation, formatting |
For detailed recommendations with alternatives and trade-offs, see [server-database.md](references/server-database.md).
## .lsp.json Configuration Format
Claude Code reads LSP configuration from `.lsp.json` in the project root.
**Basic Structure:**
```json
{
"server-name": {
"command": "server-executable",
"args": ["--stdio"],
"extensionToLanguage": {
".ext": "language-id"
},
"restartOnCrash": true,
"maxRestarts": 3
}
}
```
**Required Fields:**
| Field | Type | Description |
| --- | --- | --- |
| `command` | string | Executable command for the server |
| `args` | string[] | Command-line arguments (typically `["--stdio"]`) |
| `extensionToLanguage` | object | Maps file extensions to language IDs |
**Optional Fields:**
| Field | Type | Default | Description |
| --- | --- | --- | --- |
| `restartOnCrash` | boolean | `true` | Auto-restart server on crash |
| `maxRestarts` | number | `3` | Maximum restart attempts |
For complete patterns and examples, see [configuration-patterns.md](references/configuration-patterns.md).
## Auto-Detection Strategy
When auto-detecting needed LSPs for a project:
1. **Scan for file extensions** using Glob patterns
2. **Match extensions to languages** using the mapping table below
3. **Recommend servers** from server-database.md
### Extension to Language Mapping
| Extensions | Language | Recommended Server |
| --- | --- | --- |
| `.py`, `.pyi` | Python | pyright |
| `.ts`, `.tsx`, `.js`, `.jsx` | TypeScript/JavaScript | typescript-language-server |
| `.go` | Go | gopls |
| `.rs` | Rust | rust-analyzer |
| `.cs`, `.csx` | C# | csharp-ls |
| `.c`, `.h`, `.cpp`, `.hpp`, `.cc` | C/C++ | clangd |
| `.java` | Java | jdtls |
| `.rb` | Ruby | solargraph |
| `.php` | PHP | intelephense |
| `.lua` | Lua | lua-language-server |
| `.yaml`, `.yml` | YAML | yaml-language-server |
| `.json` | JSON | vscode-json-languageserver |
## Integration with Existing Infrastructure
### Relationship to audit-lsp
The `audit-lsp` command validates existing `.lsp.json` configurations. This skill provides:
- Server recommendations that audit-lsp can validate against
- Configuration patterns that audit-lsp checks for compliance
- Troubleshooting guidance when audit-lsp finds issues
### Relationship to setup-lsp
The `setup-lsp` command creates/updates `.lsp.json` configurations. This skill provides:
- Server database for recommendations
- Installation guides for chosen servers
- Configuration templates for generation
## Test Scenarios
These scenarios should activate this skill:
1. **Direct activation**: "Use the lsp-management skill to recommend a Python LSP"
2. **Setup question**: "How do I set up LSP for my TypeScript project?"
3. **Configuration question**: "What should my .lsp.json look like for Go?"
4. **Troubleshooting**: "My hover tooltips aren't working in Python files"
5. **Comparison**: "Should I use pyright or pylsp for Python?"
## Related Skills
| Skill | Relationship |
| --- | --- |
| **docs-management** | Delegates to for official Claude Code LSP documentation |
| **plugin-development** | Plugins can provide LSP configurations via `lspServers` field |
## References
**Detailed guides (load on-demand):**
- [Server Database](refeRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.