agentleFS
milad-ahmdmilad-ahmd/agent-skills/skills/landing-page-roaster/SKILL.md

landing-page-roaster

Skill5 starsChanged 18 days agoMITView on GitHub

Brutally honest but constructive critique of a landing page's copy, UX, design, and conversion. Gives a scored roast plus a prioritized fix list and rewritten headline and CTA options, working from a URL, screenshot, or the page's source code. Use when the user asks to roast, review, critique, or improve the conversion of a landing page, homepage, or pricing page.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask (or infer) the target audience and the one action the page should drive.

    line 14
  2. Distinctive:

    If the page source is in the repo, offer to apply the fixes directly in code.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Landing Page Roaster 🔥

Funny enough to share, useful enough to act on.

1. Get the page

  • Source code in the repo: read the hero, sections, CTAs, meta tags and images.
  • URL: fetch it if a web or browser tool is available. Screenshot: analyse it visually.
  • Ask (or infer) the target audience and the one action the page should drive.

2. Score (0–10 each, total out of 100)

AreaWhat to judge
5-second testCan a stranger say what it is, for whom, and why it's better?
HeadlineSpecific outcome vs vague buzzwords ("All-in-one platform for synergy")
CTAOne clear primary action, visible above the fold, action verb, low friction
Social proofReal logos, numbers, testimonials with faces/names, placed near CTAs
Clarity of offerFeatures → benefits; pricing transparency; objections answered (FAQ)
Visual hierarchyContrast, whitespace, scannability, consistent design
TrustSecurity, guarantees, contact info, privacy, polish (typos, broken links)
Speed & techHeavy images, layout shift, missing meta/OG tags, no favicon
MobileThumb-friendly CTA, readable text, no horizontal scroll
Story / flowProblem → solution → proof → action

3. Output

# 🔥 Roast: <site> — 62/100

**The roast (3–5 sharp lines):** witty, specific, never mean about people.
> "Your headline says 'Empower your workflow'. Every SaaS since 2012 says that. What do you actually DO?"

## Scorecard
(table)

## 🧯 Top 5 fixes (highest impact first)
1. Problem → fix → expected impact

## ✍️ Rewrites
- 3 headline options + 3 sub-headlines + 3 CTA labels

## ✅ Quick wins (< 30 min)

Rules

  • Roast the page, never the person. Every joke must point at a real, fixable issue.
  • Be specific: quote the actual copy and name the actual section.
  • Base the rewrites on what the product really does. Don't invent features or stats.
  • If the page source is in the repo, offer to apply the fixes directly in code.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.