wireframe-reviewer

wireframe-reviewer is a skill for Claude Code, Codex from yaxeen/storytelling-skills. It costs 69 tokens per session (1,106 once invoked), scanned A, original, MIT.

A guide for reviewing a website page or wireframe, which is a rough plan of a page's sections and layout, for clarity, visual priority, and the path toward one action.

In plain words
What is it for?
Use it to critique a landing page, sales page, home page, mockup, or wireframe, especially when visitors are confused or few take the intended action.
Why use it?
It finds confusing page order, buried important information, competing buttons, and messages visitors cannot understand quickly. Each finding is paired with a concrete change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to critique a landing page, sales page, home page, mockup, or wireframe, especially when visitors are confused or few take the intended action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yaxeen/storytelling-skills/wireframe-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yaxeen/storytelling-skills --skill wireframe-reviewer
Clone the repo
git clone --depth 1 https://github.com/yaxeen/storytelling-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wireframe-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/wireframe-reviewer/github.svg)](https://agentmods.dev/skills/yaxeen/storytelling-skills/wireframe-reviewer)
Your own site
<a href="https://agentmods.dev/skills/yaxeen/storytelling-skills/wireframe-reviewer"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/wireframe-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wireframe-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaxeen/storytelling-skills/wireframe-reviewer"><img src="https://agentmods.dev/badge/skills/yaxeen/storytelling-skills/wireframe-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01106
Opus 5 $0.00034 $0.00553
Sonnet 5 $0.00014 $0.00221
Haiku 4.5 $0.00007 $0.00111

Measured 12d ago against content hash d067d17587b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wireframe-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/wireframe-reviewer/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Read the full file on GitHub · 80 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 80 lines · 69 tokens per session scan A d067d17587b4

Subscribe to this mod's changes

wireframe-reviewer is a skill published in the GitHub repository yaxeen/storytelling-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,106 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.