Fat Agent

FAT Agent with Superpowers (Fix, Audit, Test) — a post-launch quality assurance agent that systematically audits deployed websites and web applications using modular, auto-detected check categories. Triggers whenever a user mentions "FAT agent", "post-launch audit", "site audit", "audit my site", "check my deployment", "post-deploy check", "QA my site", "launch checklist", or any request to review a live or recently deployed website for issues. Also triggers after a successful deploy (on any platform — Netlify, Vercel, Cloudflare Pages, AWS, shared hosting, whatever) when the user asks "what s

40 stars 4 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add spruikco/fat-agent-skill

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add spruikco/fat-agent-skill --skill fat-agent
Manual install
git clone --depth 1 https://github.com/spruikco/fat-agent-skill.git /tmp/fat-agent-skill
mkdir -p ~/.claude/skills
cp -r /tmp/fat-agent-skill/plugins/fat-agent/skills/fat-agent ~/.claude/skills/fat-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# FAT Agent with Superpowers — Fix, Audit, Test

A post-launch quality assurance agent that performs a comprehensive, modular
audit of deployed websites and guides users through fixing every issue found.

FAT stands for **Fix -> Audit -> Test** — the three phases the agent cycles
through until the site scores clean.

## Philosophy

Most post-launch issues fall into predictable categories. Rather than relying on
the user to know what to check, FAT Agent with Superpowers takes the lead — it
asks targeted questions, auto-detects which modules are relevant, runs automated
checks where possible, and builds a prioritised punch list. Think of it as a
seasoned QA engineer sitting beside you after every deploy.

---

## When to Trigger

Activate FAT Agent with Superpowers when:
- A user says "run FAT agent", "audit my site", "post-launch check", etc.
- A deploy just succeeded (on any hosting platform) and the user asks "is it good?" or similar
- The user pastes a URL and asks Claude to "check it" or "review it"
- After any deploy, if the user hasn't mentioned running QA

---

## Phase 0 — Gather Context & Module Detection

Before auditing anything, FAT Agent with Superpowers needs to understand the
project and determine which audit modules to run.

### Step 1: Collect Project Details

Ask the user for the following (skip anything already known from conversation
context or memory):

#### Required
1. **Live URL** — The production URL to audit (e.g., `https://example.com`)
Read the full skill on GitHub

Details

Skill name
fat-agent
Path
plugins/fat-agent/skills/fat-agent/SKILL.md
License
MIT
Repo updated
30 October 2026

FAQ

What does the Fat Agent skill do?

FAT Agent with Superpowers (Fix, Audit, Test) — a post-launch quality assurance agent that systematically audits deployed websites and web applications using modular, auto-detected check categories. Triggers whenever a user mentions "FAT agent", "post-launch audit", "site audit", "audit my site", "check my deployment", "post-deploy check", "QA my site", "launch checklist", or any request to review a live or recently deployed website for issues. Also triggers after a successful deploy (on any platform — Netlify, Vercel, Cloudflare Pages, AWS, shared hosting, whatever) when the user asks "what s

How do I install the Fat Agent skill?

Claude Code plugin: /plugin marketplace add spruikco/fat-agent-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Fat Agent popular?

It lives in spruikco/fat-agent-skill, which has 40 GitHub stars and 4 forks.

Related skills

Fat Design

40

spruikco/fat-agent-skill

FAT Design, the design-taste department of FAT Agent (Fix, Audit, Test). Runs a six-lens audit (product design, copywriting, typography, craft, interaction, animation) over a screen, URL, screenshot or frontend code to find the last 10% that makes an interface feel considered instead of generated. Names each weak decision in the lens's vocabulary, ranks findings by cost (harm x frequency x reach), writes three-part briefs, and can implement the highest-value repair then verify it. Where fat-agent checks SEO, security, speed and accessibility as code, fat-design checks whether the thing feels d

Frontend & Design

Install Dsh Origin

49

Fantasality/dsh-origin-plugin

帮用户把 dsh-origin-plugin(AI 驱动 OriginLab Origin 画图的 MCP 插件)装好并验证可用。当用户说"帮我装 Origin 插件""配置 MCP""让 AI 能画 Origin 图"或遇到装到旧版本/连不上 Origin 时使用。

AI, LLMs & Agents

Cleanddd Modeling

49

zhouda1fu/Ncp.Admin

基于 cleanddd-requirements-analysis 结果,输出符合 CleanDDD 的聚合、命令、事件、查询、API 端点(Endpoints)、定时任务模型;用于从已拆解的需求快速得到建模蓝图

AI, LLMs & Agents12

Kanban AI

26

mattjoyce/kanban-skill

Manage a Markdown-based Kanban board using card files in a kanban/ directory (including kanban/archived/ for completed cards). Use when the user asks to create, move, view, list, or manage tasks or cards on a kanban board, or when tracking work items across statuses like backlog, todo, doing, done, or archive.

AI, LLMs & AgentsIn 1 list

Aftereffects Motion

43

LobzyJay/motion-design-with-claude-and-codex

Use this skill whenever Adobe After Effects is the working tool. Triggers on "After Effects", "AE", ".aep", "ExtendScript", "JSX", "composition", "comp", "keyframe in AE", "AE expression", "render queue", "wiggle", "loopOut", "Trim Paths", or any AE-driven motion graphics task. Also triggers when the user is mid-session with the AE MCP bridge active (mcp-bridge-auto.jsx), or mentions "Higgsfield", "remove background", "reframe", "upscale", "Draw to Edit", or "generate footage" in an AE context. Pair with motion-design (foundation skill) for principles, timing, and taste. AE MCP server: TheLlam

AI, LLMs & Agents

Mcwander

43

Sirius0o0/McWander

Plan a local Citywalk with McDonald's rest stops using the McWander project, Amap walking routes and McDonald's MCP menu and price queries. Use for city strolls with time, walking-distance and dining-budget limits.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.