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.
npx skills add TheSmokeDev/geo-skills --skill geo-platform-optimizergit clone --depth 1 https://github.com/TheSmokeDev/geo-skillsWrote 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.
[](https://agentmods.dev/skills/thesmokedev/geo-skills/geo-platform-optimizer)<a href="https://agentmods.dev/skills/thesmokedev/geo-skills/geo-platform-optimizer"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/geo-platform-optimizer/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.
<a href="https://agentmods.dev/skills/thesmokedev/geo-skills/geo-platform-optimizer"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/geo-platform-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.05700 |
| Opus 5 | $0.00017 | $0.02850 |
| Sonnet 5 | $0.00007 | $0.01140 |
| Haiku 4.5 | $0.00003 | $0.00570 |
Grade A, and why
geo-platform-optimizer 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Platform Optimizer
Core Insight
Only 11% of domains are cited by BOTH ChatGPT and Google AI Overviews for the same query. Each AI search platform uses different indexes, ranking logic, and source preferences. A page optimized for Google AI Overviews may be invisible to ChatGPT, and vice versa. Platform-specific optimization is not optional — it is the foundation of any serious GEO strategy.
How to Use This Skill
- Collect the target URL and the site's primary topic/industry
- Run each platform checklist below against the site
- Score each platform on the 0-100 rubric
- Generate GEO-PLATFORM-OPTIMIZATION.md with per-platform scores, gaps, and action items
Platform 1: Google AI Overviews (AIO)
How AIO Selects Sources
- Only 38% of AIO-cited URLs rank in the organic top 10 — down from 76% (Ahrefs, 863K SERPs / 4M URLs, Mar 2026). 31% of citations come from positions 11-100 and 31% from beyond position 100. The cause is Gemini 3 (Jan 2026) query fan-out pulling from sub-query SERPs — page-3 organic is NOT disqualifying
- Fan-out coverage is the new meta-factor (Zyppy scores it 9.3/10, Jun 2026): engines rewrite one prompt into a cluster of sub-queries and retrieve per sub-query. Win the cluster, not the head term
- AIO strongly favors pages with clean structure, direct answers, and scannable formatting
- Featured snippet optimization has meaningful overlap with AIO optimization
- AIO prefers concise, factual, unambiguous answers — hedging and filler reduce citation probability
- Google AI Mode is a separate surface, not a bigger AIO: AIO↔AI Mode URL overlap is only 13.7%, and AI Mode has 1B MAU (AIO 2.5B) with scarcer citation slots — 4.3 citations per response vs 10.3 in classic search (Shadow, Jul 2026 — ⚠️ secondary source). Optimize for them as distinct targets
2026 Citation Surfaces Beyond the AIO Box
Google's citation real estate now extends beyond AIO and AI Mode themselves:
- Preferred Sources — users can star favorite outlets and get boosted Top Stories placement plus a dedicated "From your sources" section (Google Search blog, Aug 2025, US/India English launch; broader rollout through 2026). This is a Top Stories surface, NOT an AIO mechanism — but for news-adjacent queries it is part of the brand's total Google citation footprint. Earning a user's "preferred" star compounds like a subscription; publishers can link directly to a follow flow.
- "Highly Cited" badges, Community Perspectives, and link carousels — additional in-SERP citation modules attributed to the Google I/O May 2026 announcements. ⚠️ Thin-sourced: this comes from rival skill-pack I/O 2026 notes and we have NOT independently confirmed rollout status or the exact selection mechanics. Treat as watch items — if these modules appear in your SERPs, they are additional extractable surfaces — but do not score them in the rubric until the mechanics are verified.
- Common thread: every new surface still extracts from the same primitives — direct answers, tables, dated authorship, entity clarity. Optimizing the fundamentals covers surfaces that ship faster than any checklist can track.
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.
- 12d ago First seen · 287 lines · 34 tokens per session scan A 135c680316ed
geo-platform-optimizer is a skill published in the GitHub repository TheSmokeDev/geo-skills (22 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 5,700 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ganhuo-geo-engineer
Use this Skill when the user provides an existing article, product page, tutorial, FAQ, or knowledge note and wants to rebuild it into a GEO or AI-search-friendly content asset. Use it for old-content refresh, citation-readiness improvement, answer-first restructuring, GEO upgrades, and Ganhuo AI content workflows. Do…
ai-answer-trace
Ask Claude, ChatGPT, and Gemini a question and capture the full evidence trail behind each answer: the search queries each engine ran, the pages it retrieved, and the sources it cited. The raw material of GEO measurement. Needs AI engine API keys, not an Xpoz account.
geo-visibility-check
One-shot GEO audit: does your brand appear in Claude, ChatGPT, and Gemini answers for the buyer questions that matter? Runs a prompt panel through the engines with citation tracing and reports per-prompt verdicts, who wins instead, and which sources the answers come from.
crazyseo
Measure and fix whether AI assistants (ChatGPT, Gemini, Perplexity) recommend a website. Use when someone asks "am I visible in AI search", "does ChatGPT recommend us", "why doesn't AI mention my brand", "GEO/AEO audit", "AI SEO", "llms.txt", "is my site readable by AI crawlers", or wants to know which sources AI…
xerj-code
Reference-coding with XERJ. Clone the libraries that already solved your problem, index them locally, and retrieve the exact implementation before writing code — so the agent reads passages instead of re-deriving algorithms across retry loops. Use when starting a task in an unfamiliar API, porting an algorithm, or…