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 yaojingang/yao-geo-skills --skill yao-geo-page-auditgit clone --depth 1 https://github.com/yaojingang/yao-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/yaojingang/yao-geo-skills/yao-geo-page-audit)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-page-audit"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-page-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.
<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-page-audit"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-page-audit.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 | $0.00041 | $0.01001 |
| Opus 5 | $0.00020 | $0.00500 |
| Sonnet 5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
yao-geo-page-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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yao-geo-page-audit
Use this skill when the user wants a GEO Page Audit, website/page GEO diagnosis, page technical audit, AI extractability audit, schema/HTML module advice, or code/content repair list for a URL.
Job
Given a target URL or website, diagnose the homepage, a representative first-level page, and a representative second-level page when possible. Output development-ready and content-ready recommendations that improve how public pages can be discovered, parsed, cited, and summarized by search-driven AI systems. By default, analyze public page readiness and public evidence coverage only; do not estimate AI-platform recall, rankings, citation share, or internal platform behavior unless the user provides platform sampling data.
Workflow
- Read
references/research-foundation.md,references/authority-reference-model.md, andreferences/report-module-taxonomy.md. Frame the audit as a five-stage chain: discovery, retrieval candidate, main-content extraction, evidence quality, generated citation. - Identify page type and sample scope. If the input is a homepage, select homepage, one representative first-level page, and one representative second-level page. State the selection basis and unresolved input gaps.
- Build an evidence ledger. Prefer official pages, official docs, schema/source code, standards, and peer-reviewed or arXiv research before third-party commentary. Mark each finding as observed, official, standard, research, inferred, or input gap.
- Check crawlability and renderability: status code, robots, sitemap, canonical, meta robots, mobile-first parity, JavaScript dependency, and whether primary content appears in initial HTML.
- Check structural quality: H1-H3,
main/article, summary, table of contents, FAQ, tables, lists, breadcrumbs, internal links, anchor text, accessibility headings, and schema. - Check content evidence: conclusions first, full entity names, data, citations, cases, dates, author/source, freshness, objectivity, price, service boundaries, regional constraints, and source accountability.
- Check AI extractability and public-answer material coverage: key-value facts, atomic facts, comparison tables, steps, Q&A, context-independent summary, paragraph independence, entity graph, sameAs links, and chunk-level citation readiness. Convert domestic platform concerns into high-intent question material gaps, not platform recall claims.
- Produce code-layer fixes, content-layer fixes, page-module suggestions, schema/HTML snippets, priority, owner, acceptance test, risk, and estimated cost.
- Deliver Word, PDF, sticky-menu HTML, and Markdown from one Markdown content source. Use the
kamieditorial report style inreferences/report-formatting-spec.mdandreferences/output-layout-policy.md. - After DOCX generation, run
scripts/polish_docx.pyto apply Kami-style Word typography, margins, and table formatting. - Run
scripts/review_report_layout.pyandreferences/quality-gates.mdbefore claiming completion.
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/interface.yaml 2.2 KB
- evals/expected_artifacts.json 1.2 KB
- evals/quality_cases.json 1.2 KB
- evals/trigger_cases.json 717 B
- examples/example-site-demo/example-site-geo-page-audit.docx 20 KB
- examples/example-site-demo/example-site-geo-page-audit.html 28 KB
- examples/example-site-demo/example-site-geo-page-audit.md 10.0 KB
- examples/example-site-demo/example-site-geo-page-audit.pdf 372 KB
- examples/example-site-demo/quality-report.json 1.2 KB
- examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.docx 22 KB
- examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.html 35 KB
- examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.md 13 KB
- examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.pdf 383 KB
- examples/hubspot-domestic-ai-demo/quality-report.json 1.2 KB
- examples/hubspot-domestic-ai-demo/README.md 836 B
- examples/README.md 1.0 KB
- manifest.json 905 B
- references/authority-reference-model.md 3.1 KB
- references/output-layout-policy.md 2.1 KB
- references/page-audit-method.md 3.4 KB
- references/quality-gates.md 2.4 KB
- references/report-formatting-spec.md 2.2 KB
- references/report-module-taxonomy.md 3.2 KB
- references/research-foundation.md 3.1 KB
- reports/artifact-design-profile.md 1.3 KB
- reports/output-risk-profile.md 1.2 KB
- scripts/polish_docx.py 6.8 KB runs code
- scripts/review_report_layout.py 6.3 KB runs code
- templates/brief-template.md 1.1 KB
- templates/report.css 3.0 KB
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 · 60 lines · 41 tokens per session scan A a8308fc3b954
yao-geo-page-audit is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,001 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
pipefy-process-intelligence
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…
c
OpenPaw coordinator — routes requests to skills, manages memory, knows what's installed. Use /c for any task.
-21risk-automation
Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
-2chat-automation
Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
ably-automation
Automate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas.
abstract-automation
Automate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas.