seo-geo-report-engine: Skill for Claude Code

.agents/skills/geo-audit/SKILL.md

geo-audit is a skill for Claude Code from prashishh/seo-geo-report-engine. It costs 166 tokens per session (2,301 once invoked), scanned A, original, MIT.

A skill for checking how often and accurately a brand appears in answers from AI search tools such as ChatGPT, Perplexity, Google AI Overviews, Claude, and Copilot. It uses Ahrefs Brand Radar, a measurement tool for brand visibility, to produce a prioritized list of fixes.

In plain words
What is it for?
Use it to measure AI search visibility, compare a brand with competitors, review mentions and citations, validate gaps, and create an ordered GEO fix list. GEO means improving how a brand is found and represented in AI search.
Why use it?
It shows where AI-generated answers fail to mention, cite, or describe a brand correctly. This turns an unclear visibility problem into specific changes to investigate and make.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is prashishh/seo-geo-report-engine's own configuration. It tells Claude Code how to work on seo-geo-report-engine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seo-geo-report-engine configures →

Part of the seo-geo-report-engine plugin — 33 skills, 8 commands, 5 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to prashishh/seo-geo-report-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prashishh/seo-geo-report-engine/main/.agents/skills/geo-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/prashishh/seo-geo-report-engine

Made for: Claude Code.

Or install seo-geo-report-engine, the plugin that ships this one along with the rest of its 33 skills, 8 commands, 5 agents.

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 geo-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/geo-audit/github.svg)](https://agentmods.dev/skills/prashishh/seo-geo-report-engine/geo-audit)
Your own site
<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/geo-audit"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/geo-audit/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 geo-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/geo-audit"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/geo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,301 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 $0.00166 $0.02301
Opus 5 $0.00083 $0.01151
Sonnet 5 $0.00033 $0.00460
Haiku 4.5 $0.00017 $0.00230

Measured 11d ago against content hash abaf60a13b51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

geo-audit 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 11d 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.

.agents/skills/geo-audit/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

geo-audit

Measures how a brand shows up in AI answers and turns the gaps into a falsifiable fix list. The engine is Ahrefs Brand Radar (see knowledge/ahrefs-mcp-map.md); the methodology is playbooks/geo-playbook.md. House method: PERCEIVE → ANALYZE → VALIDATE → ACT. Data priority everywhere: Ahrefs MCP > CLI connectors > web spot-checks.

Inputs

  • projects/<client>/client.yml — domain, competitors, target keywords, market. Brand Radar ids come from ahrefs.brand_radar_report_id (and ahrefs.project_id).
  • Existing research in projects/<client>/research/.

If brand_radar_report_id is missing, list reports with management-brand-radar-reports and the prompts with management-brand-radar-prompts, pick the right one, and write the id into client.yml.

Workflow

1. PERCEIVE — measure current AI visibility (Brand Radar)

Always doc a tool before first use. Pull, for the client + each competitor:

  • brand-radar-sov-overview + brand-radar-sov-history — AI share of voice now and its trend.
  • brand-radar-mentions-overview + brand-radar-mentions-history — mention volume + direction.
  • brand-radar-impressions-overview — AI impression scale for the topic set.
  • brand-radar-ai-responses + brand-radar-ai-responses-entities — the actual answer text and the entities co-cited with the brand (surfaces wrong facts and missing associations).
  • brand-radar-cited-domains + brand-radar-cited-pageswho AI cites for the topic (the sources to get mentioned on or out-cite).
  • site-explorer-ai-responses-count — how often the client's domain appears in AI answers vs rivals.

From the same Brand Radar pulls, derive two first-class citation signals per engine:

  • AI-citation frequency — how often the brand is cited per engine (from ai-responses / cited-pages); a brand mentioned but never cited is a citability gap, not a presence gap.
  • Cross-engine citation — count distinct engines that cite the brand; treat cited by ≥3 engines as the durable-visibility bar (single-engine citation is fragile to one model's ranking change).

Read the full file on GitHub · 130 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. 11d ago First seen · 130 lines · 166 tokens per session scan A abaf60a13b51

Subscribe to this mod's changes

geo-audit is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 166 tokens to every session and 2,301 once invoked, about $0.0008 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

content-amplifier

Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…

aaron-he-zhu/aaron-marketing-skills · 202 tokens

email-sequence-designer

Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…

aaron-he-zhu/aaron-marketing-skills · 197 tokens

reactivation-specialist

Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm /…

aaron-he-zhu/aaron-marketing-skills · 215 tokens

campaign-planner

Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…

aaron-he-zhu/aaron-marketing-skills · 124 tokens

product-feed-optimizer

Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…

aaron-he-zhu/aaron-marketing-skills · 144 tokens

cold-outbound-sequencer

Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…

aaron-he-zhu/aaron-marketing-skills · 172 tokens