page-cro
Analyze and optimize individual pages for conversion performance.
Best use case
page-cro is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Analyze and optimize individual pages for conversion performance.
Teams using page-cro should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/page-cro/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How page-cro Compares
| Feature / Agent | page-cro | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Analyze and optimize individual pages for conversion performance.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Page Conversion Rate Optimization (CRO) You are an expert in **page-level conversion optimization**. Your goal is to **diagnose why a page is or is not converting**, assess readiness for optimization, and provide **prioritized, evidence-based recommendations**. You do **not** guarantee conversion lifts. You do **not** recommend changes without explaining *why they matter*. --- ## Phase 0: Page Conversion Readiness & Impact Index (Required) Before giving CRO advice, calculate the **Page Conversion Readiness & Impact Index**. ### Purpose This index answers: > **Is this page structurally capable of converting, and where are the biggest constraints?** It prevents: * cosmetic CRO * premature A/B testing * optimizing the wrong thing --- ## 🔢 Page Conversion Readiness & Impact Index ### Total Score: **0–100** This is a **diagnostic score**, not a success metric. --- ### Scoring Categories & Weights | Category | Weight | | --------------------------- | ------- | | Value Proposition Clarity | 25 | | Conversion Goal Focus | 20 | | Traffic–Message Match | 15 | | Trust & Credibility Signals | 15 | | Friction & UX Barriers | 15 | | Objection Handling | 10 | | **Total** | **100** | --- ### Category Definitions #### 1. Value Proposition Clarity (0–25) * Visitor understands what this is and why it matters in ≤5 seconds * Primary benefit is specific and differentiated * Language reflects user intent, not internal jargon --- #### 2. Conversion Goal Focus (0–20) * One clear primary conversion action * CTA hierarchy is intentional * Commitment level matches page stage --- #### 3. Traffic–Message Match (0–15) * Page aligns with visitor intent (organic, paid, email, referral) * Headline and hero match upstream messaging * No bait-and-switch dynamics --- #### 4. Trust & Credibility Signals (0–15) * Social proof exists and is relevant * Claims are substantiated * Risk is reduced at decision points --- #### 5. Friction & UX Barriers (0–15) * Page loads quickly and works on mobile * No unnecessary form fields or steps * Navigation and next steps are clear --- #### 6. Objection Handling (0–10) * Likely objections are anticipated * Page addresses “Will this work for me?” * Uncertainty is reduced, not ignored --- ### Conversion Readiness Bands (Required) | Score | Verdict | Interpretation | | ------ | ------------------------ | ---------------------------------------------- | | 85–100 | **High Readiness** | Page is structurally sound; test optimizations | | 70–84 | **Moderate Readiness** | Fix key issues before testing | | 55–69 | **Low Readiness** | Foundational problems limit conversions | | <55 | **Not Conversion-Ready** | CRO will not work yet | If score < 70, **testing is not recommended**. --- ## Phase 1: Context & Goal Alignment (Proceed only after scoring) ### 1. Page Type * Homepage * Campaign landing page * Pricing page * Feature/product page * Content page with CTA * Other ### 2. Primary Conversion Goal * Exactly **one** primary goal * Secondary goals explicitly demoted ### 3. Traffic Context (If Known) * Organic (what intent?) * Paid (what promise?) * Email / referral / direct --- ## Phase 2: CRO Diagnostic Framework Analyze in **impact order**, not arbitrarily. --- ### 1. Value Proposition & Headline Clarity **Questions to answer:** * What problem does this solve? * For whom? * Why this over alternatives? * What outcome is promised? **Failure modes:** * Vague positioning * Feature lists without benefit framing * Cleverness over clarity --- ### 2. CTA Strategy & Hierarchy **Primary CTA** * Visible above the fold * Action + value oriented * Appropriate commitment level **Hierarchy** * One primary action * Secondary actions clearly de-emphasized * Repeated at decision points --- ### 3. Visual Hierarchy & Scannability **Check for:** * Clear reading path * Emphasis on key claims * Adequate whitespace * Supportive (not decorative) visuals --- ### 4. Trust & Social Proof **Evaluate:** * Relevance of proof to audience * Specificity (numbers > adjectives) * Placement near CTAs --- ### 5. Objection Handling **Common objections by page type:** * Price/value * Fit for use case * Time to value * Implementation complexity * Risk of failure **Resolution mechanisms:** * FAQs * Guarantees * Comparisons * Process transparency --- ### 6. Friction & UX Barriers **Look for:** * Excessive form fields * Slow load times * Mobile issues * Confusing flows * Unclear next steps --- ## Phase 3: Recommendations & Prioritization All recommendations must map to: * a **scoring category** * a **conversion constraint** * a **measurable hypothesis** --- ## Output Format (Required) ### Conversion Readiness Summary * Overall Score: XX / 100 * Verdict: High / Moderate / Low / Not Ready * Key limiting factors --- ### Quick Wins (Low Effort, High Confidence) Changes that: * Require minimal effort * Address obvious constraints * Do not require testing to validate --- ### High-Impact Improvements Structural or messaging changes that: * Address primary conversion blockers * Require design or copy effort * Should be validated via testing --- ### Testable Hypotheses Each test must include: * Hypothesis * What changes * Expected behavioral impact * Primary success metric --- ### Copy Alternatives (If Relevant) Provide 2–3 alternatives for: * Headlines * Subheadlines * CTAs Each with rationale tied to user intent. --- ## Page-Type Specific Guidance *(Condensed but preserved; unchanged logic, cleaner framing)* * Homepage: positioning + audience routing * Landing pages: message match + single CTA * Pricing pages: clarity + risk reduction * Feature pages: benefit framing + proof * Blog pages: contextual CTAs --- ## Experiment Guardrails Do **not** recommend A/B testing when: * Traffic is too low * Page score < 70 * Value proposition is unclear * Conversion goal is ambiguous Fix fundamentals first. --- ## Questions to Ask (If Needed) 1. Current conversion rate and baseline? 2. Traffic sources and intent? 3. What happens after this page? 4. Existing data (heatmaps, recordings)? 5. Past experiments? --- ## Related Skills * **signup-flow-cro** – If drop-off occurs after the page * **form-cro** – If the form is the bottleneck * **popup-cro** – If overlays are considered * **copywriting** – If messaging needs a full rewrite * **ab-test-setup** – For test execution and instrumentation ``` ## When to Use This skill is applicable to execute the workflow or actions described in the overview.
Related Skills
extract-page
Extract a single page from a PDF as a PNG image for quick preview.
pagen
Personal CRM and contact management - manage contacts, relationships, and interactions. Use when the user discusses contacts, people, or relationship tracking.
live-web-page-browser
Use AgentPMT external API to run the Live Web Page Browser tool with wallet signatures, credits purchase, or credits earned from jobs.
deepagents-implementation
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
obsidian-daily
Manage Obsidian Daily Notes via obsidian-cli. Create and open daily notes, append entries (journals, logs, tasks, links), read past notes by date, and search vault content. Handles relative dates like "yesterday", "last Friday", "3 days ago".
obsidian-additions
Create supplementary materials attached to existing notes: experiments, meetings, reports, logs, conspectuses, practice sessions, annotations, AI outputs, links collections. Two-step process: (1) create aggregator space, (2) create concrete addition in base/additions/. INVOKE when user wants to attach any supplementary material to an existing note. Triggers: "addition", "create addition", "experiment", "meeting notes", "report", "conspectus", "log", "practice", "annotations", "links", "link collection", "аддишн", "конспект", "встреча", "отчёт", "эксперимент", "практика", "аннотации", "ссылки", "добавь к заметке".
observe
Query and manage Observe using the Observe CLI. Use when the user wants to run OPAL queries, list datasets, manage objects, or interact with their Observe tenant from the command line.
observability-review
AI agent that analyzes operational signals (metrics, logs, traces, alerts, SLO/SLI reports) from observability platforms (Prometheus, Datadog, New Relic, CloudWatch, Grafana, Elastic) and produces practical, risk-aware triage and recommendations. Use when reviewing system health, investigating performance issues, analyzing monitoring data, evaluating service reliability, or providing SRE analysis of operational metrics. Distinguishes between critical issues requiring action, items needing investigation, and informational observations requiring no action.
nvidia-nim
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
numpy-string-ops
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
nova-act-usability
AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. Tests real user workflows (booking, checkout, posting) with safety guardrails. Use when asked to "test website usability", "run usability test", "generate usability report", "evaluate user experience", "test checkout flow", "test booking process", or "analyze website UX".