Agent skill

Geo Site Diagnose

by yaojingang in yaojingang/GEOHub

Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report.

AGPL-3.0Auto-check passedMarketing & SEO

Install Geo Site Diagnose

skills CLI
$ npx skills add yaojingang/GEOHub --skill geo-site-diagnose -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yaojingang/GEOHub geo-site-diagnose --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yaojingang/GEOHub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/geo-site-diagnose .claude/skills/geo-site-diagnose && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
geo-site-diagnose
GitHub stars
165
Token cost
~515 tokens
SKILL.md length
200 words
Files
35 (incl. scripts, references, assets)
Skills in repo
9
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report.

  • Works in 6 steps: Read… → Extract the single public URL. Ask only… → Run python3 scripts/run_site_diagnose.py… → …
  • 网站 GEO 诊断、全站 GEO 体检、网站 GEO 审计
  • SKILL.md covers Workflow, Output contract and Boundaries
  • Runs JavaScript scripts from its folder; calls python3

What it does

Geo Site Diagnose is an agent skill from yaojingang/GEOHub. Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report. Use for 网站 GEO 诊断、全站 GEO 体检、网站 GEO 审计, or requests such as “帮我诊断网站GEO并附上网址”. Excludes single-page or brand-only diagnosis, live AI ranking or citation measurement, authenticated sites, and website modification.

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 40 other files, including scripts, reference files and assets (for example `agents/interface.yaml`, `assets/echarts.min.js` and `assets/report.js`).

It sits in Marketing & SEO, covering AI search optimization and Citation management. It works with Python. The repository describes itself as: GEOHub: open, evidence-bounded GEO and SEO agent skills for AI Search, with research-grounded discovery, diagnosis, content, measurement, and one-line SEO planning. The licence is AGPL-3.0.

When your agent uses it

  • 网站 GEO 诊断、全站 GEO 体检、网站 GEO 审计
  • Requests such as 帮我诊断网站GEO并附上网址

Example prompts

  • “帮我诊断网站GEO并附上网址”
  • “/geo-site-diagnose”

Requirements

  • Python 3
  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read references/site-diagnosis-method.md, references/crawler-policy.md, and references/scoring-policy.md.
  2. Extract the single public URL. Ask only for the URL when it is missing.
  3. Run python3 scripts/run_site_diagnose.py --url --output --locale --max-pages 10 --render auto.
  4. Inspect quality-report.json, diagnostic confidence, source gaps, and limitations before presenting scores.
  5. Validate the report against references/report-module-contract.md and references/report-design-system.md.
  6. Deliver the complete Artifact Bus run directory and open report.html for the user.

What it can do on your machine

Read from SKILL.md and the folder at commit 2210f7f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Geo Site Diagnose loads about 515 tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 200 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~515
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from yaojingang/GEOHub at commit 2210f7f, republished under its AGPL-3.0 licence (© yaojingang). 200 words, ~515 tokens.

Download SKILL.mdSave it as .claude/skills/geo-site-diagnose/SKILL.md (or your agent's skills folder). This skill also uses 34 other files; get the full folder from GitHub.
name
geo-site-diagnose
description
Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report. Use for 网站 GEO 诊断、全站 GEO 体检、网站 GEO 审计, or requests such as “帮我诊断网站GEO并附上网址”. Excludes single-page or brand-only diagnosis, live AI ranking or citation measurement, authenticated sites, and website modification.

GEOHub Website Diagnosis

Workflow

  1. Read references/site-diagnosis-method.md, references/crawler-policy.md, and references/scoring-policy.md.
  2. Extract the single public URL. Ask only for the URL when it is missing.
  3. Run python3 scripts/run_site_diagnose.py --url <URL> --output <runs-root> --locale <locale> --max-pages 10 --render auto.
  4. Inspect quality-report.json, diagnostic confidence, source gaps, and limitations before presenting scores.
  5. Validate the report against references/report-module-contract.md and references/report-design-system.md.
  6. Deliver the complete Artifact Bus run directory and open report.html for the user.

Output contract

Return a bounded run containing source snapshots, crawl and sampling manifests, structured site and page diagnoses, evidence ledger, remediation backlog, quality and lineage artifacts, and one offline report.html. Read references/report-contract.md for the file contract and report format boundary.

The offline report runtime is packaged under assets/. Governed trigger and output cases are stored under evals/.

Boundaries

Fetch only public HTTP(S) resources on the approved canonical host. Discovery is bounded to 500 inventory URLs, five sitemaps, ten representative pages, 15 MB, and 90 seconds. Preserve blocked or unavailable pages as source_gap. Scores describe observed readiness signals and never claim live AI ranking, recall, citations, traffic, or business effects.

Do not use this Skill for single-page diagnosis, brand-only diagnosis, authenticated sources, live citation measurement, or website modification.

© yaojingang, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 34 other files (scripts, references, assets) in skills/geo-site-diagnose of yaojingang/GEOHub.

  • SKILL.md
  • agents/interface.yaml
  • assets/ECHARTS-LICENSE.txt
  • assets/ECHARTS-NOTICE.txt
  • assets/echarts.min.js
  • assets/report-shell.html
  • assets/report.css
  • assets/report.js
  • evals/output/cases.jsonl
  • evals/output/fixtures/visual-quality.json
  • evals/semantic_config.json
  • evals/trigger_cases.json
  • manifest.json
  • references/crawler-policy.md
  • references/input-example.json
  • … and 20 more

Open the folder on GitHubat commit 2210f7f

Compare with similar skills

Geo Site Diagnose next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Geo Site Diagnose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Geo Site Diagnose this skillyaojingang/GEOHub165—~515Automated safety check: PassAGPL-3.0
Aeoalirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
SEO ProfoundAgriciDaniel/claude-seo19k1 repos~441Automated safety check: PassMIT
Citation Source Gap Finderirinabuht12-oss/marketing-skills4.1k—~601Automated safety check: PassNone
Beyondseobeyondtahir/beyondseo161—~4.3kAutomated safety check: PassMIT
Universal SEO AnalysisAgriciDaniel/claude-seo19k—~4.9kAutomated safety check: PassMIT

Similar skills

  • Aeo

    alirezarezvani/claude-skills

    Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources.

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • SEO Profound

    AgriciDaniel/claude-seo

    Profound LLM citation tracker (extension). An agent skill from AgriciDaniel/claude-seo.

    19k GitHub starsUsed in 1 repo~441 tokens
    Marketing & SEOAuto-check passed
  • Citation Source Gap Finder

    irinabuht12-oss/marketing-skills

    Find the exact pages AI assistants cite when answering questions in your category, and identify which ones you can get into.

    4.1k GitHub stars~601 tokensUpdated 17 days ago
    Marketing & SEOAuto-check passed
  • Beyondseo

    beyondtahir/beyondseo

    Audit websites, apply authorised SEO improvements and plan content, competitors and backlinks with evidence, design checks and optional project monitoring.

    161 GitHub stars~4.3k tokensUpdated 16 days ago
    Marketing & SEOAuto-check passed
  • Universal SEO Analysis

    AgriciDaniel/claude-seo

    Hub for site-wide SEO work: audits, technical checks, schema, content quality, local, hreflang and AI-search readiness, run through slash commands.

    19k GitHub stars~4.9k tokensUpdated 6 days ago
    Marketing & SEOAuto-check passed
  • GEO Schema Auditor

    zubair-trabzada/geo-seo-claude

    Audits a page's Schema.org structured data for AI discoverability, validates it, generates JSON-LD to fill gaps and writes a GEO-SCHEMA-REPORT.md.

    11k GitHub starsUsed in 2 repos~3.7k tokens
    Marketing & SEOAuto-check: notes

More from yaojingang/GEOHub

All 9 skills in this repo
  • Geo

    yaojingang/GEOHub

    Route GEO and generative engine optimization requests to an available GEOHub capability.

    165 GitHub stars~364 tokensUpdated 1 mo ago
    Auto-check passed
  • Geo Content

    yaojingang/GEOHub

    Create evidence-lined GEO titles, explainers, neutral comparisons, method-backed rankings, page blueprints, refinements, and article-friendly Markdown.

    165 GitHub stars~390 tokensUpdated 1 mo ago
    Auto-check passed
  • Geo Diagnose

    yaojingang/GEOHub

    Diagnose a brand, website, or page for evidence-backed GEO gaps and opportunities from user-supplied URLs, HTML, or evidence.

    165 GitHub stars~434 tokensUpdated 1 mo ago
    Auto-check passed
  • Geo Discover

    yaojingang/GEOHub

    Discover evidence-aware GEO questions, query rewrites, intent clusters, and prioritized content opportunities from a structured brief.

    165 GitHub stars~419 tokensUpdated 1 mo ago
    Auto-check passed
  • Geo Knowledge

    yaojingang/GEOHub

    Build and query an evidence-lined GEO knowledge graph from approved source bundles.

    165 GitHub stars~349 tokensUpdated 1 mo ago
    Auto-check passed
  • Geo Measure

    yaojingang/GEOHub

    Measure GEO visibility from an approved, file-backed engine observation bundle.

    165 GitHub stars~348 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Geo Site Diagnose

What does Geo Site Diagnose do?

Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report. Geo Site Diagnose is an agent skill from yaojingang/GEOHub. Crawl one public website from a supplied URL, select up to ten representative page types, score evidence-lined GEO readiness, and generate a standalone visual HTML report.

When should I use Geo Site Diagnose?

Geo Site Diagnose fits situations like: 网站 GEO 诊断、全站 GEO 体检、网站 GEO 审计; requests such as 帮我诊断网站GEO并附上网址.

How do I install Geo Site Diagnose in Claude Code?

Run `npx skills add yaojingang/GEOHub --skill geo-site-diagnose -a claude-code`. Or copy the skill folder (skills/geo-site-diagnose in yaojingang/GEOHub) into .claude/skills/geo-site-diagnose in your project. Claude Code loads it when a task matches its description.

How do I install Geo Site Diagnose in Codex?

Run `npx skills add yaojingang/GEOHub --skill geo-site-diagnose -a codex`. Or copy the skill folder (skills/geo-site-diagnose in yaojingang/GEOHub) into .agents/skills/geo-site-diagnose in your project. Codex loads it when a task matches its description.

Can I use Geo Site Diagnose in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yaojingang/GEOHub --skill geo-site-diagnose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/geo-site-diagnose, .gemini/skills/geo-site-diagnose, .github/skills/geo-site-diagnose and .opencode/skills/geo-site-diagnose in your project.

What does Geo Site Diagnose need to run?

Going by SKILL.md and its folder, Geo Site Diagnose needs JavaScript for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; Node.js.

Does Geo Site Diagnose access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Geo Site Diagnose safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Geo Site Diagnose use?

Geo Site Diagnose is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Geo Site Diagnose use?

About 515 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.

What are the alternatives to Geo Site Diagnose?

Skills that share tags, products or a category with Geo Site Diagnose: Aeo (alirezarezvani/claude-skills, 28k stars), SEO Profound (AgriciDaniel/claude-seo, 19k stars), Citation Source Gap Finder (irinabuht12-oss/marketing-skills, 4.1k stars) and Beyondseo (beyondtahir/beyondseo, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Geo Site Diagnose?

yaojingang (a GitHub user) maintains it in yaojingang/GEOHub, which has 165 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 31, 2026.

Source: yaojingang/GEOHub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.