AI Builder Club Skills plugin

AI Builder Club — Skills

A Claude Code plugin marketplace to make a repo agent-ready and run compounding agent loops

  • 1,310 ★ on the repository
  • Last commit
Plugin

Broad access

Why this level

  • The skills run, test and ship code autonomously
  • They spin up cloud boxes and delegate work to other CLI agents, running shell commands and scripts
All reasons and checks

ai-builder-club/skills

Install

Works in

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/ai-builder-club-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • The skills run, test and ship code autonomously
  • They spin up cloud boxes and delegate work to other CLI agents, running shell commands and scripts

This is third-party code. Review the repository files before installing.

What it does

The repository is a Claude Code plugin marketplace that bundles several skill sets. A codebase harness makes a repo agent-ready: local run, an e2e gate, an isolated cloud box per agent via crabbox and a verify-before-ship step. The loops set spins up a file-based knowledge base and loops where an agent picks up work, finishes it, verifies it and logs what it learned. There are standalone skills too: agent-context-audit checks an agent's context against Anthropic's guidance, open-agent-teams delegates tasks to other CLI agents in tmux sessions, seo-growth offers traffic-growth playbooks, and karaoke-captions and visual-flow-gif help with subtitles and clips. It installs as a plugin marketplace and connects through /plugin commands.

Who it is for. For engineers and founders who set up autonomous and looping agents on their codebase.

Good fit when

  • You need to make a repo ready for an agent to run, test and ship code
  • You need to set up a loop where an agent picks up work and verifies the result
  • You need to audit an agent's context or delegate work to several CLI agents

Not a fit when

  • You need a single one-off skill rather than a whole set for loops and a harness
  • You do not use Claude Code plugins

Example request

Make my repo agent-ready and set up a loop that picks up work and verifies the result on its own

Limitations

The set is built around the Claude Code plugin system. Some skills rely on external tools: tmux for delegation, docker and crabbox cloud boxes, and ffmpeg and python for video and subtitle work. There is no license file at the repository root, though plugin.json states MIT.

How to disable. Uninstall the plugin and remove the marketplace via /plugin.

FAQ

Which agent is this set for?

For Claude Code; it is packaged as a plugin marketplace.

Is a cloud box required?

No. The crabbox cloud boxes are for parallel loops, while local run, e2e and verify-before-ship work without them.

Discussion

No questions or reviews yet.

Plugins

A Claude Code plugin marketplace with ready sets of agents, slash commands, hooks and skills, plus a search site

PluginExtended access3.7KRepository stars

A tool that builds tested skills from a real workflow and governs their lifecycle through your own marketplace

PluginExtended access2.4KRepository stars

A large kit for Claude Code: subagents, skills, commands, hooks, rules, templates and MCP configs in one plugin marketplace

PluginExtended access2.8KRepository stars

Claude Code plugin with 60 subagents and 62 team presets, plus a browser designer for planning agent teams visually.

PluginExtended access110Repository stars

A collection of 14 portable skills for long agent runs: work planning, live app QA, search across past sessions and a phone call

PluginExtended access136Repository stars
Editors’ pick

Multi-agent orchestration for Claude Code: teams, roles, autopilot and task routing across skills and subagents

PluginBroad access40.8KRepository stars

README in short

The README presents a Claude Code plugin marketplace from AI Builder Club for building looping agents that pick up work, finish it and verify it. Two main sets: a codebase harness that makes a repo ready to run, test and ship code, including an isolated cloud box per agent, and loops with a file-based knowledge base for compounding cycles. Standalone skills include agent-context-audit, open-agent-teams, seo-growth, karaoke-captions and visual-flow-gif. It installs via /plugin marketplace add and /plugin install, and some skills need external tools such as tmux, docker, ffmpeg and python. The MIT license is stated in plugin.json.

README badge

Report a problem