suxrobgm/claude-plugins/setup

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install the meatgg-bot support session on this machine. Writes the tmux respawn script, permissions, operating policy and an .env to fill in. Use when the user wants to set up, install or deploy the meat.gg support bot.

Install

npx vskill@latest install suxrobgm/claude-plugins/setup

SKILL.md

Set up the meat.gg support bot

bash
bun run ${CLAUDE_PLUGIN_ROOT}/dist/server.js setup

Denied? Then this session runs in the bot's own working directory, whose policy denies Bash(bun *) and outranks this skill. Say so and give the user the command for a plain shell.

It installs into ~/bots/meatgg/ (pass a path for another directory). The plugin owns the files it writes there and respawn.sh reinstalls them before every spawn, so never patch an installed copy. The operator's .env and settings.json live in .state/ below it and are never touched once they exist.

Relay the printed "still to do" list, then offer to:

  • open ~/bots/meatgg/.state/.env for the API key. It must be an ApiKey from

/admin/api-keys, owned by an admin holding VIEW_TICKETS, scoped to the write permissions MANAGE_TICKETS, MANAGE_COMPLAINTS, MANAGE_DROPS, MANAGE_PUNISHMENTS, DELETE_CHAT_MESSAGES plus the reads the bot answers from: VIEW_TICKETS, VIEW_COMPLAINTS, VIEW_USERS, VIEW_PUNISHMENTS, VIEW_DROPS, VIEW_SUBSCRIPTIONS, VIEW_RULES, VIEW_SERVERS, VIEW_SITE_SETTINGS. A tool the key lacks permission for is not listed at all. The bot user's own AdminProfile still needs MANAGE_TICKETS and MANAGE_COMPLAINTS, since the replies, assign_ticket and set_complaint_status act as the bot rather than as the key's owner;

  • show the cron lines from ${CLAUDE_PLUGIN_ROOT}/deploy/README.md.

Do not fill in the key and do not start the session: it has to launch from its own working directory to pick up the policy just written.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/suxrobgm/claude-plugins/setup/badge)](https://verified-skill.com/skills/suxrobgm/claude-plugins/setup)

Something wrong with this skill or its page? Tell us.