fat-agent

Name: fat-agent
Author: spruikco

37stars4forks

How to install fat-agent?

spruikco/fat-agent-skill/fat-agent

$npx -y skills add spruikco/fat-agent-skill --skill fat-agent

Installs into the current project.

Summary

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",

Files · 1

View on GitHub

SKILL.md

1	# FAT Agent with Superpowers — Fix, Audit, Test
2
3	A post-launch quality assurance agent that performs a comprehensive, modular
4	audit of deployed websites and guides users through fixing every issue found.
5
6	FAT stands for Fix -> Audit -> Test — the three phases the agent cycles
7	through until the site scores clean.
8
9	## Philosophy
10
11	Most post-launch issues fall into predictable categories. Rather than relying on
12	the user to know what to check, FAT Agent with Superpowers takes the lead — it
13	asks targeted questions, auto-detects which modules are relevant, runs automated
14	checks where possible, and builds a prioritised punch list. Think of it as a
15	seasoned QA engineer sitting beside you after every deploy.
16
17	---
18
19	## When to Trigger
20
21	Activate FAT Agent with Superpowers when:
22	- A user says "run FAT agent", "audit my site", "post-launch check", etc.
23	- A deploy just succeeded (on any hosting platform) and the user asks "is it good?" or similar
24	- The user pastes a URL and asks Claude to "check it" or "review it"
25	- After any deploy, if the user hasn't mentioned running QA
26
27	---
28
29	## Phase 0 — Gather Context & Module Detection
30
31	Before auditing anything, FAT Agent with Superpowers needs to understand the
32	project and determine which audit modules to run.
33
34	### Step 1: Collect Project Details
35
36	Ask the user for the following (skip anything already known from conversation
37	context or memory):
38
39	#### Required
40	1. Live URL — The production URL to audit (e.g., `https://example.com`)
41
42	That's the only thing FAT Agent needs. Everything below is helpful but optional —
43	if the user doesn't know or doesn't have the codebase, **infer what you can from
44	the live response and proceed** (see Remote / From-Afar Mode below).
45
46	#### Helpful (optional — auto-detected when not provided)
47	2. Site type — marketing site, SaaS app, e-commerce, blog, portfolio, landing page, web app, local business. Infer from the page: product schema/cart → e-commerce; LocalBusiness/NAP → local business; `<article>`/blog paths → blog.
48	3. Tech stack — Framework/CMS. Infer from response headers (`Server`, `X-Powered-By`, `X-Generator`), `<meta name="generator">`, cookies (e.g. `wordpress_`), and asset paths (`/_next/`, `/_nuxt/`, Vite `/assets/index-.js`, `/wp-content/`).
49	4. Hosting platform — Infer from headers (`Server`, `Via`, `X-Vercel-`, `CF-Ray`/`Server: cloudflare`, `X-Served-By` Fastly/Netlify, `X-Amz-`). Used only to tailor config-format fixes; when unknown, give stack-agnostic fixes (the HTML/JSON-LD/header to add).
50
51	#### Situational (ask only if relevant)
52	5. Critical user flows — What are the 2-3 most important things a visitor does? (e.g., "fill out contact form", "add to cart and checkout", "sign up")
53	6. Target audience — Who visits this site? (helps calibrate accessibility and performance expectations)
54	7. Known issues — Anything the user already knows is broken or unfinished?
55	8. Previous audit results — Has a FAT audit been run before? (check conversation history)
56
57	Present these as a friendly, concise intake form — not an interrogation. Group them
58	logically and use the ask_user_input tool where possible for bounded choices.
59
60	Example opener:
61	> Ready to run a FAT audit! I just need a few details to get started. What's the
62	> live URL, and what kind of site are we looking at?
63
64	### Remote / From-Afar Mode
65
66	FAT Agent can audit any live URL with zero codebase access — your own site, a
67	client's, or a prospect's you're pitching. When you don't have (or don't need) the
68	repo:
69
70	- Don't block on stack/hosting. Fetch the page and infer them from response
71	headers and markup (see the inference hints under Helpful, above).
72	- Deliver stack-agnostic fixes. Instead of "edit `next.config.js`", hand the
73	user the exact HTML/JSON-LD/header to add. They can paste it into any CMS,
74	tag manager, or template. Only switch to framework-specific fixes once the stack
75	is confirmed.
76	- Lead with schema + local SEO suggestions — these are fully derivable from the
77	live page and are the highest-leverage from-afar wins (see Schema Suggestions).
78
79	This makes FAT Agent equally useful for self-audits and for outside-in au

People who liked this also viewed

6 picks

Type

fat-agent

37stars4forks

View on GitHub

How to install fat-agent?

spruikco/fat-agent-skill/fat-agent

$npx -y skills add spruikco/fat-agent-skill --skill fat-agent

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# FAT Agent with Superpowers — Fix, Audit, Test
2
3	A post-launch quality assurance agent that performs a comprehensive, modular
4	audit of deployed websites and guides users through fixing every issue found.
5
6	FAT stands for Fix -> Audit -> Test — the three phases the agent cycles
7	through until the site scores clean.
8
9	## Philosophy
10
11	Most post-launch issues fall into predictable categories. Rather than relying on
12	the user to know what to check, FAT Agent with Superpowers takes the lead — it
13	asks targeted questions, auto-detects which modules are relevant, runs automated
14	checks where possible, and builds a prioritised punch list. Think of it as a
15	seasoned QA engineer sitting beside you after every deploy.
16
17	---
18
19	## When to Trigger
20
21	Activate FAT Agent with Superpowers when:
22	- A user says "run FAT agent", "audit my site", "post-launch check", etc.
23	- A deploy just succeeded (on any hosting platform) and the user asks "is it good?" or similar
24	- The user pastes a URL and asks Claude to "check it" or "review it"
25	- After any deploy, if the user hasn't mentioned running QA
26
27	---
28
29	## Phase 0 — Gather Context & Module Detection
30
31	Before auditing anything, FAT Agent with Superpowers needs to understand the
32	project and determine which audit modules to run.
33
34	### Step 1: Collect Project Details
35
36	Ask the user for the following (skip anything already known from conversation
37	context or memory):
38
39	#### Required
40	1. Live URL — The production URL to audit (e.g., `https://example.com`)
41
42	That's the only thing FAT Agent needs. Everything below is helpful but optional —
43	if the user doesn't know or doesn't have the codebase, **infer what you can from
44	the live response and proceed** (see Remote / From-Afar Mode below).
45
46	#### Helpful (optional — auto-detected when not provided)
47	2. Site type — marketing site, SaaS app, e-commerce, blog, portfolio, landing page, web app, local business. Infer from the page: product schema/cart → e-commerce; LocalBusiness/NAP → local business; `<article>`/blog paths → blog.
48	3. Tech stack — Framework/CMS. Infer from response headers (`Server`, `X-Powered-By`, `X-Generator`), `<meta name="generator">`, cookies (e.g. `wordpress_`), and asset paths (`/_next/`, `/_nuxt/`, Vite `/assets/index-.js`, `/wp-content/`).
49	4. Hosting platform — Infer from headers (`Server`, `Via`, `X-Vercel-`, `CF-Ray`/`Server: cloudflare`, `X-Served-By` Fastly/Netlify, `X-Amz-`). Used only to tailor config-format fixes; when unknown, give stack-agnostic fixes (the HTML/JSON-LD/header to add).
50
51	#### Situational (ask only if relevant)
52	5. Critical user flows — What are the 2-3 most important things a visitor does? (e.g., "fill out contact form", "add to cart and checkout", "sign up")
53	6. Target audience — Who visits this site? (helps calibrate accessibility and performance expectations)
54	7. Known issues — Anything the user already knows is broken or unfinished?
55	8. Previous audit results — Has a FAT audit been run before? (check conversation history)
56
57	Present these as a friendly, concise intake form — not an interrogation. Group them
58	logically and use the ask_user_input tool where possible for bounded choices.
59
60	Example opener:
61	> Ready to run a FAT audit! I just need a few details to get started. What's the
62	> live URL, and what kind of site are we looking at?
63
64	### Remote / From-Afar Mode
65
66	FAT Agent can audit any live URL with zero codebase access — your own site, a
67	client's, or a prospect's you're pitching. When you don't have (or don't need) the
68	repo:
69
70	- Don't block on stack/hosting. Fetch the page and infer them from response
71	headers and markup (see the inference hints under Helpful, above).
72	- Deliver stack-agnostic fixes. Instead of "edit `next.config.js`", hand the
73	user the exact HTML/JSON-LD/header to add. They can paste it into any CMS,
74	tag manager, or template. Only switch to framework-specific fixes once the stack
75	is confirmed.
76	- Lead with schema + local SEO suggestions — these are fully derivable from the
77	live page and are the highest-leverage from-afar wins (see Schema Suggestions).
78
79	This makes FAT Agent equally useful for self-audits and for outside-in au

People who liked this also viewed

6 picks

Type