From Lubby
Connect this machine to a Lubby server with a connector token. Use when the user wants to log in to Lubby or set up Lubby presence sharing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lubby:login [api-url] [token][api-url] [token]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Store the user's Lubby connector token in `~/.lubby/config.json`.
Store the user's Lubby connector token in ~/.lubby/config.json.
$ARGUMENTS. It may contain an API URL (anything starting with http) and/or a token (starts with lub_).http://localhost:8000/dashboard). Never invent a token.http://localhost:8000/api for local development. Ensure the URL ends with /api.mkdir -p ~/.lubby
node -e '
const fs = require("fs"), p = process.env.HOME + "/.lubby/config.json";
let c = {}; try { c = JSON.parse(fs.readFileSync(p, "utf8")); } catch {}
c.api_url = process.argv[1]; c.token = process.argv[2];
c.share_level = c.share_level || "presence_only"; c.paused = false;
fs.writeFileSync(p, JSON.stringify(c, null, 2) + "\n", { mode: 0o600 });
console.log("Lubby config written to " + p);
' "<API_URL>" "<TOKEN>"
{"ok":true,...}:echo '{}' | node "${CLAUDE_PLUGIN_ROOT}/scripts/lubby-event.mjs" heartbeat && echo "ok"
(If CLAUDE_PLUGIN_ROOT is not set in your shell, locate the script under ~/.claude/plugins/.) Tell the user they will now appear as "waiting" on the dashboard whenever Claude is working, and that only presence is shared, never code, file names, or prompts.
npx claudepluginhub aliwesome/lubby-plugin --plugin lubbyProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.