Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Enable code intelligence (go-to-definition, find-references, hover, type info) for any programming language by installing and configuring an LSP server for Copilot CLI. Detects the OS, installs the right server, and generates the JSON configuration (user-level or repo-level). Use when you need deeper code understanding and no LSP server is configured, or when the user asks to set up, install, or configure an LSP server.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
UTILITY SKILL — installs and configures Language Server Protocol servers for Copilot CLI. USE FOR: "setup LSP", "install language server", "configure LSP for Java", "add TypeScript LSP", "enable code intelligence", "I need go-to-definition", "find references not working", "need better code understanding" DO NOT USE FOR: general coding tasks, IDE/editor LSP configuration, non-Copilot-CLI setups
ask_user to ask which programming language(s) the user wants LSP support foruname -s (or check for Windows via $env:OS / %OS%) to determine macOS, Linux, or Windowsreferences/lsp-servers.md for known servers, install commands, and config snippetsask_user to ask whether the config should be user-level (~/.copilot/lsp-config.json) or repo-level (lsp.json at the repo root or .github/lsp.json)~/.copilot/lsp-config.json for user-level; lsp.json or .github/lsp.json for repo-level). If a repo-level config already exists, keep using that location; otherwise ask the user which repo-level location they prefer. Create the file if missing and preserve existing entries.$PATH and the config file is valid JSONCopilot CLI reads LSP configuration from user-level or repo-level locations, and repo-level config takes precedence over user-level config:
~/.copilot/lsp-config.jsonlsp.json (repo root) or .github/lsp.jsonThe JSON structure:
json{ "lspServers": { "<server-key>": { "command": "<binary>", "args": ["--stdio"], "fileExtensions": { ".<ext>": "<languageId>", ".<ext2>": "<languageId>" } } } }
command is the binary name (must be on $PATH) or an absolute path.args almost always includes "--stdio" to use standard I/O transport.fileExtensions maps each file extension (with leading dot) to a Language ID.lspServers.ask_user with choices when asking the user to pick a language or scope.references/lsp-servers.md, search the web for "<language> LSP server" and guide the user through manual configuration.which <binary> (or where.exe on Windows) to confirm the binary is accessible.After setup, tell the user:
/exit to quit Copilot CLI — this is required so the new LSP configuration is loaded on next launchcopilot in a project with files of the configured language/lsp to check the server status| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 16 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.