audit-a-surface

audit-a-surface is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 64 tokens per session (2,276 once invoked), scanned A, original, MIT.

An audit that reviews one marketing area: website SEO, visibility in AI search tools, a landing page, or a form. It ranks the findings by their likely effect and how easy they are to fix.

In plain words
What is it for?
Use it to check technical and on-page SEO, see whether your company appears in ChatGPT, Perplexity, Gemini, or Google AI Overviews, review a landing page, or reduce friction in a lead or checkout form.
Why use it?
It turns a broad marketing problem into a short, ordered list of changes. This helps you focus on the issues most likely to affect search visibility, page performance, or form completion.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to check technical and on-page SEO, see whether your company appears in ChatGPT, Perplexity, Gemini, or Google AI Overviews, review a landing page, or reduce friction in a lead or checkout form.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/audit-a-surface
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 akiotanaka847/qaio-desktop --skill audit-a-surface
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

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 audit-a-surface

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-a-surface/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-a-surface)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-a-surface/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 audit-a-surface

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-a-surface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,276 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 $0.00064 $0.02276
Opus 5 $0.00032 $0.01138
Sonnet 5 $0.00013 $0.00455
Haiku 4.5 $0.00006 $0.00228

Measured 10d ago against content hash e76df89db702, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-a-surface 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 10d 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.

store/agents/marketing/.agents/skills/audit-a-surface/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit A Surface

Four possible audit surfaces. surface param picks probe;

Parameter: surface

  • site-seo - on-page + technical + content audit of configured domain via Semrush / Ahrefs / Firecrawl.
  • ai-search - ChatGPT / Perplexity / Gemini / Google AI Overviews visibility probe + GEO recs.
  • landing-page - fetch via Firecrawl, score 6 dimensions 0-3, prioritized fix list.
  • form - flag unnecessary fields, rewrite labels + helper text, sequence by friction (non-signup forms - demo / contact / lead / checkout).

User names surface in plain English ("SEO audit", "GEO", "teardown my landing page", "fix my demo form") -> infer. Ambiguous -> ask ONE question naming 4 options.

When to use

  • Explicit: "run an SEO audit", "audit AI search visibility", "GEO audit", "critique {URL}", "audit my lead form".
  • ai-search triggers: "do I show up in ChatGPT?", "are we visible in Perplexity / Gemini for our category?", "who shows up when someone asks about {category} in ChatGPT?".
  • form triggers: "audit my demo form", "my contact form is leaking", "this lead form is too long - what can I cut?", "rewrite the labels on this form", "review the fields on the application / checkout form".
  • Implicit: inside plan-a-campaign (paid / launch) when routed landing page needs sharpening, or inside check-my-marketing (content-gap) when baseline site health unknown.
  • Per-surface cadence: site-seo weekly max, ai-search monthly max, landing-page on demand, form on demand.

Connections I need

I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing -> I name the category, ask you to connect it from the Integrations tab, stop.

  • Web scrape (Firecrawl) - optional. If not connected I fall back to basic HTTP fetch for landing-page, form, and the on-page pass of site-seo, rougher but workable on static pages.
  • SEO (Semrush or Ahrefs) - on-page audit, indexation, content-fit, ranking data. Required for site-seo - no fallback, that data is proprietary.
  • AI search (Perplexity / search providers) - probe ChatGPT / Perplexity / Gemini / AI Overviews for your visibility. Required for ai-search - no useful fallback, the engines need API access.

Read the full file on GitHub · 164 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. 10d ago First seen · 164 lines · 64 tokens per session scan A e76df89db702

Subscribe to this mod's changes

audit-a-surface is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 2,276 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.

Related

Other skills, from other repositories

magazine-web-ppt

For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.

nexu-io/open-design · 67 tokens

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens

ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…

coreyhaines31/marketingskills · 175 tokens

attribution

When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…

coreyhaines31/marketingskills · 220 tokens

co-marketing

When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…

coreyhaines31/marketingskills · 92 tokens

offers

When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment structure. Also use when the user mentions 'offer,' 'offer design,' 'build an offer,' 'grand slam offer,' 'irresistible offer,'…

coreyhaines31/marketingskills · 233 tokens