Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

cro-optimization

skill · ognjengt/founder-skillsMIT licenceAudited 22 Oct 2026 · source 90bc6f1424df

★ 571pushed 156 days ago
✓SAFEGrade B · 89/100 · 22 Oct 2026 · 90bc6f1
571repo stars · whole ognjengt/founder-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 90bc6f1424df and found no filesystem, network or shell access and no hard-coded secrets. What it does: Analyzes landing pages and provides detailed CRO (Conversion Rate Optimization) recommendations. Use when user provides a landing page URL or HTML/CSS code and needs optimization advice to maximize conversions, signups,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “cro-optimization (ognjengt/founder-skills)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/ognjengt/cro-optimization

Trust audit

Audit 0.4.1 · source read 22 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 90bc6f1424df · 22 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherognjengt GitHub userOwner of the repository this skill is read from
  • Source folderognjengt/founder-skills/skills/cro-optimizationThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict90bc6f1424dfA new audit runs when the source changes
  • Repository statusNot archivedLast push 156 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Analyzes landing pages and provides detailed CRO (Conversion Rate Optimization) recommendations. Use when user provides a landing page URL or HTML/CSS code and needs optimization advice to maximize conversions, signups,…

---
name: cro-optimization
description: Analyzes landing pages and provides detailed CRO (Conversion Rate Optimization) recommendations. Use when user provides a landing page URL or HTML/CSS code and needs optimization advice to maximize conversions, signups, or sales. Extracts page elements, audits against proven CRO principles, and delivers actionable recommendations in report format.
---

# CRO Optimization

## Purpose
Analyze a landing page and deliver a comprehensive CRO audit with specific, actionable recommendations to maximize conversions.

---

## Execution Logic

**Check $ARGUMENTS first to determine execution mode:**

### If $ARGUMENTS is empty or not provided:
Respond with:
"cro-optimization loaded, provide your landing page URL or paste your HTML/CSS code"

Then wait for the user to provide their landing page in the next message.

### If $ARGUMENTS contains content:
Proceed immediately to Task Execution (skip the "loaded" message).

---

## Task Execution

When landing page is available (either from initial $ARGUMENTS or follow-up message):

### 1. MANDATORY: Read Reference Files FIRST
**BLOCKING REQUIREMENT — DO NOT SKIP THIS STEP**

Before doing ANYTHING else, you MUST use the Read tool to read ALL three reference files:

```
Read: ./references/cro_principles.md
Read: ./references/landing_page_patterns.md
Read: ./references/element_audit_framework.md
```

**What you will find:**
- **cro_principles.md**: 13 core CRO principles with detection criteria and fix patterns
- **landing_page_patterns.md**: Real patterns from high-converting pages (ClickUp, Notion, Stripe, Apple, etc.) organized by category
- **element_audit_framework.md**: Systematic framework for auditing HTML elements, CTAs, forms, and visual hierarchy

**DO NOT PROCEED** to Step 2 until you have read all files and have the principles, patterns, and audit framework loaded in context.

### 2. Check for Business Context
Check if `FOUNDER_CONTEXT.md` exists in the project root.
- **If it exists:** Read it and use the business context to personalize recommendations (industry, target audience, product type, competitors).
- **If it doesn't exist:** Proceed with analysis based on page content alone.

### 3. Fetch and Extract Landing Page
If user provided a URL:
- Use WebFetch to retrieve the landing page content
- Extract and catalog key elements (see Element Extraction below)

If user provided HTML/CSS directly:
- Analyze the provided code directly
- Note any missing context (live styling, images, etc.)

### 4. Element Extraction
Extract and catalog these elements from the page:

**Typography:**
- H1 (should be exactly one)
- H2s (section headers)
- Body text samples
- CTA button copy

**Visual Structure:**
- Above-the-fold content
- Section sequence
- Image/visual placement
- Color scheme and contrast

**Conversion Elements:**
- Primary CTA (copy, placement, design)
- Secondary CTAs
- Forms (field count, labels)
- Trust signals (logos, testimonials, badges)
- Social proof (metrics, reviews, case studies)

**Technical:**
- Mobile responsiveness indicators
- Load speed concerns (large images, etc.)

### 5. Audit Against CRO Principles
For each of the 13 principles in cro_principles.md:
1. Check if the page violates the principle
2. Note specific violations with evidence
3. Determine severity (High/Medium/Low)
4. Draft specific recommendations

**Prioritize by impact:**
- High: Above-fold clarity, CTA effectiveness, major trust gaps
- Medium: Objection handling, visual hierarchy, scannability
- Low: Minor copy tweaks, nice-to-have additions

### 6. Compare to High-Converting Patterns
Using landing_page_patterns.md:
1. Identify the most relevant category (B2B SaaS, E-commerce, etc.)
2. Compare page structure to proven patterns
3. Note missing elements that top performers include
4. Identify opportunities to adopt successful patterns

### 7. Generate Recommendations
For each issue found, provide:
1. **What to change** — specific element and action
2. **Why it matters** — principle violated and expected impact
3. **How to implement** — concrete example or rewrite
4. **Priority** — High/Medium/Low with reasoning

### 8. Format and Verify
- Structure output according to **Output Format** section
- Complete **Quality Checklist** self-verification
- Ensure recommendations are specific and actionable (not generic advice)

---

## Writing Rules
Hard constraints. No interpretation.

### Core Rules
- Every recommendation must be specific and actionable
- Include before/after examples for copy changes
- Reference the specific principle violated
- Prioritize by conversion impact, not ease of implementation
- Frame changes as testable hypotheses when possible
- Never recommend changes without explaining the "why"

### Analysis Rules
- Audit systematically — don't skip principles
- Note what's working well, not just problems
- Consider the page's apparent target audience
- Account for likely traffic sources
- Distinguish between critical issues and optimizations

### Recommendation Rules
- Lead with highest-impact changes
- Group related recommendations together
- Provide specific copy rewrites, not just "make it clearer"
- Include placement suggestions, not just content suggestions
- Consider mobile experience separately

---

## Output Format

```markdown
# CRO Audit Report: [Page Name/URL]

## Executive Summary
[2-3 sentences: Overall assessment, biggest opportunities, expected impact]

---

## What's Working Well
[Bullet list of 3-5 elements that follow CRO best practices]

---

## Critical Issues (Fix First)

### Issue 1: [Specific Problem]
**Principle Violated:** [Principle name and number]
**Current State:** [What exists now]
**Problem:** [Why this hurts conversions]
**Recommendation:** [Specific fix]
**Example:**
```
BEFORE: [Current copy/element]
AFTER: [Recommended copy/element]
```
**Expected Impact:** [What improvement to expect]

### Issue 2: [Specific Problem]
[Same structure]

---

## High-Impact Optimizations

### Optim

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 90bc6f1

Download folder ↗
git clone https://github.com/ognjengt/founder-skills
git -C founder-skills checkout 90bc6f1424df

The author documents no install command, so this uses the repository directly. Our verdict covers commit 90bc6f1424df only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 90bc6f1424df

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/ognjengt/cro-optimization/badge.svg)](https://modelsatlas.com/skills/ognjengt/cro-optimization/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/ognjengt/cro-optimization/badge.svg)](https://modelsatlas.com/skills/ognjengt/cro-optimization/)

Questions about cro-optimization

What does the cro-optimization skill do?
Claude skills for founders
Is cro-optimization safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can cro-optimization access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does cro-optimization work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (90bc6f1424df), read on 2026-10-22. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.