# Wireframe Reviewer

> Use when reviewing or critiquing an existing website wireframe, landing page, or page structure for any niche or business — when you need structured feedback on narrative flow, visual hierarchy, clarity, and conversion path, plus concrete fixes per section. For building a new page structure from scratch, use wireframe-writer.

- **Type:** Skill
- **Install:** `agentstack add skill-yaxeen-storytelling-skills-wireframe-reviewer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [yaxeen](https://agentstack.voostack.com/s/yaxeen)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [yaxeen](https://github.com/yaxeen)
- **Source:** https://github.com/yaxeen/storytelling-skills/tree/main/skills/wireframe-reviewer

## Install

```sh
agentstack add skill-yaxeen-storytelling-skills-wireframe-reviewer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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](https://github.com/yaxeen)
- **Source:** [yaxeen/storytelling-skills](https://github.com/yaxeen/storytelling-skills)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-yaxeen-storytelling-skills-wireframe-reviewer
- Seller: https://agentstack.voostack.com/s/yaxeen
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.