MCP.Market

lsp-setup skill

by code-yeongyu·code-yeongyu/oh-my-openagent·71k stars

Configures a language server so editor/agent tooling (diagnostics, go-to-definition, references, rename) works. Use when a project needs an LSP installed or wired, or a 'no LSP server configured' error appears.

D40/100content scan

Is the lsp-setup skill safe?

Serious findings: read the flagged lines first. We read 25 files in the folder on 2026-11-14.

  • highSKILL.md:148

    Downloads a script and runs it in one step, so what runs is whatever that server sends that day. Common for installers, and still worth a look at the address.

    Run with [Bun](https://bun.sh): `curl -fsSL https://bun.sh/install | bash`.
  • highreferences/julia/README.md:14

    Downloads a script and runs it in one step, so what runs is whatever that server sends that day. Common for installers, and still worth a look at the address.

    - **Linux:** `curl -fsSL https://install.julialang.org | sh` (installs juliaup)

Install the lsp-setup skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. Read the findings above first.

git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
mkdir -p ~/.claude/skills
cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/lsp-setup ~/.claude/skills/lsp-setup
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

LSP Setup

Configure the right Language Server for a project so the lsp MCP tools (diagnostics, gotodefinition, findreferences, symbols, rename) actually work. This skill is an index: detect what a project needs, install the server, write the config, then verify with a real roundtrip.

The list of servers we ship as builtin is the source of truth in packages/lsp-tools-mcp/src/lsp/server-definitions.ts (BUILTINSERVERS + LSPINSTALL_HINTS). The per-language references below mirror it.

PHASE 0 — LANGUAGE GATE (run first)

Identify the language from the file extension, then read the matching reference before installing or configuring anything.

WORKFLOW — detect → install → configure → verify

1. Detect

Scan the project to see which languages are present and whether each server is installed and configured:

bun scripts/detect-lsp.ts <projectDir>      # human report (default: cwd)
bun scripts/detect-lsp.ts <projectDir> --json

For each detected language it prints the builtin server id, the executable it needs on PATH, whether that executable is installed, an install hint, and whether a project config file already references it.

2. Install

Open references//README.md and run the install command for your OS. Then confirm the executable resolves:

command -v <server-executable>   # e.g. typescript-language-server, gopls, rust-analyzer

3. Configure

Most builtin servers need no config — they are resolved automatically by file extension. Write config only to: pick between competing servers, set a priority, pass initialization options, override extensions, set env (user config only), or disable a server.

Config files per harness, identical JSON shape. Each harness reads the first project file that exists, plus one user file:

A standalone lsp-tools-mcp launch reads the paths in LSPTOOLSMCPPROJECTCONFIG / LSPTOOLSMCPUSERCONFIG instead.

{
  "lsp": {
    "<server-id>": {
      "command": ["<bin>", "<args>"],   // optional for builtin ids (supplied automatically)
      "extensions": [".ext"],            // optional override
      "priority": 100,                    // higher wins when several servers match an extension
      "initialization": { },              // server-specific initializationOptions
      "env": { "KEY": "value" },          // optional
      "disabled": false                   // set true to turn a server off
    }
  }
}

Rules enforced by config-loader.ts:

command automatically — you only override extensions / priority / initialization / disabled. Its env is dropped, and a non-builtin id in a project config is ignored.

  • In a project config an entry whose id is a builtin server inherits

own command, put it in the user config from the table above, where command + extensions + env are honored.

  • To set env, or to define a fully custom (non-builtin) server with its

entry is skipped when an enabled project entry has the same id, so keep an id that needs env out of the project config.

  • Project entries win over user entries; both win over builtin defaults. A user

Each language reference gives a ready-to-paste snippet.

4. Verify

Run a real diagnostics roundtrip against a source file. This spawns the server, opens the file, requests diagnostics, and reports OK/FAIL:

bun scripts/verify-lsp.ts <path/to/file.ext>
bun scripts/verify-lsp.ts <file> --timeout=90000

OK = the server started and answered. FAIL: language server not installed = go back to step 2. Other FAIL text carries the server/startup error. SKIP = the engine source could not be located; run from inside the omo repo/worktree, or call the lsp MCP diagnostics tool directly.

Scripts

Run with Bun: curl -fsSL https://bun.sh/install | bash.

More skills from code-yeongyu/oh-my-openagent

  • Aast-grepSearches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
  • AbrowserDrives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.
  • Acodex-qaQA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.
  • Acoding-agent-sessionsFinds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.
  • Acomment-checkerUse when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
  • Adag-libraryStores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved one, or schedule the same multi-agent graph repeatedly.
  • Ddata-scientistProcesses and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.
  • AdebuggingRuns a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
  • Adev-browserBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
  • Aeval-integrityAssess integrity of an eval, benchmark, metric, A/B test, holdout, LLM-judge, or user-study claim when the question is whether measurement, comparison, or evidence is independent and trustworthy.
  • AfrontendBuilds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way.
  • AfrontendBuilds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way.

All agent skills → · MCP servers