Wireframe Reviewer

Wireframe Reviewer

• Reviewing a page = checking whether it tells a clear story that pulls one scroll toward one action.
• Critique against five axes, then return structured findings + a concrete fix for each.
• Built on the six levers — see storytelling-hooks. Recap: 1. Curiosity gap · 2. Emotional mirror · 3. Conflict engine · 4. Relatability · 5. Pattern + surprise · 6. Three-act.

When to Use

• Reviewing a wireframe, mockup, or live landing/sales/home page.
• Diagnosing low conversion, confusing flow, or "it just feels off".
• Giving a designer/marketer structured, actionable feedback.
• Any niche or business. To build a new structure, use wireframe-writer.

The Five Review Axes (Quick Reference)

| Axis | Question | Common failure | |------|----------|----------------| | Narrative flow | Does each section earn the next scroll? | Sections in random order; no loop | | Visual hierarchy | Does the eye land on what matters first? | Everything equal weight; buried CTA | | Clarity | Is the message understood in 5 seconds? | Vague hero; jargon; feature dump | | Conversion path | Is there one obvious next action? | Many/competing CTAs; no CTA above fold | | Friction | What makes a visitor hesitate or leave? | Unanswered objections; cognitive load |

Intake (Before Reviewing)

• A review without context grades against guesses. Know before reviewing: the page's one conversion goal, the target visitor in a sentence, and the main traffic source.
• If these are inferable from the request (a freelancer's services page → goal is inquiries), state your assumptions inline and proceed; only ask first when the goal is genuinely undecidable — don't block a review on intake theater.

Review Process

1. 5-second test: Look only at the hero. Can you state what it offers and what to do next? If not, that's finding #1.
2. Scroll the arc: Does it move hook → problem → solution → proof → offer → objections → CTA? Note any missing or out-of-order section.
3. Score each axis per section (works / weak / missing) — an internal diagnostic pass, not a grid to render in the output.
4. Trace the eye: Is hierarchy guiding to headline → value → CTA? Or competing for attention?
5. Find the friction: List every reason a visitor hesitates (unanswered question, weak proof, too many choices).
6. Write findings: For each issue — what's wrong, why it hurts, the fix.

Findings Format

• For each issue, return:
• Section — where it is.
• Severity — critical (blocks conversion) / major (leaks conversions) / minor (polish).
• Issue — what's wrong.
• Why it matters — impact on flow/conversion.
• Fix — concrete change (and which lever it restores, where one applies — pure-polish fixes don't need a lever tag).
• Order by severity first, position second (hero/CTA issues usually are the critical ones, but a critical mid-page issue outranks a minor hero one). Cap the list at the ~5–8 findings that matter; a 20-item list buries the critical three. Missing objection-handling before the CTA is usually worth a slot — don't let polish findings crowd it out.
• End with the single change you'd make first if only one were allowed.

What to Flag

• Hero: no curiosity gap or promise; CTA missing above the fold; headline about the company, not the visitor.
• Problem: doesn't mirror the visitor's pain → no relatability, no conflict.
• Proof: absent, generic, or placed far from the claims it supports.
• Benefits: feature lists instead of outcomes/feelings.
• Objections: common "buts" left unaddressed before the CTA.
• CTA: multiple competing actions; vague labels; high friction.
• Hierarchy: uniform weight, no focal point, CTA visually lost.
• Flow: a section that closes a loop without opening the next (dead end where users drop).
• Bookend: ending doesn't echo the opening promise.

Review Checklist

• [ ] Passes the 5-second hero test?
• [ ] Sections follow a deliberate narrative arc?
• [ ] Clear visual focal point per section guiding to the CTA?
• [ ] One primary action, obvious and repeated?
• [ ] Proof sits beside its claims?
• [ ] Top objections handled before the final CTA?
• [ ] Every finding paired with a concrete fix (+ the lever it restores, where applicable)?

Related

• wireframe-writer — build the structure this skill critiques.
• storytelling-hooks — the six levers (read for depth).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: yaxeen
• Source: yaxeen/storytelling-skills
• License: MIT

Install and usage instructions live in the source repository linked above.