agentleFS
Sign inStart free
GhanyteGhanyte/geo-seo-audit/skills/geo-audit/SKILL.md

geo-audit

Skill9 starsChanged 7 months agoMITView on GitHub

Run a full multi-page GEO audit on a website. Sequential pipeline: locale detection → multi-page sampling → robots.txt crawler audit → per-page schema + content-health checks → optional RRF measurement on Google + Brave (when --positioning is supplied) → unified report with per-LLM action plan. Output: a single Markdown audit at site-client/<slug>/audits/<date>-audit.md. Use when the user asks for a full audit on a URL.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use seo-local and seo-schema.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • mangollcSkill

    seo-local

    Local SEO optimization: Google Business Profile post generation, 30-day posting calendars, NAP consistency checks, local citation audits, review response templates, local keywords.

    Also in 3 projects that use this

  • megastepSkill

    seo-schema

    Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All modules under scripts/checks/, scripts/serp/, plus scripts/rrf.py, scripts/fanout.py, scripts/llm_impact.py, scripts/i18n.py, …

    line 82

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

geo-audit — multi-page GEO audit

The main entry point of the toolkit. One command, one Markdown report.

Command

python3 -m scripts.run_audit <url> \
  [--positioning "<query>"] \
  [--vs comp1.com,comp2.com] \
  [--engines google,brave] \
  [--max-pages 8] \
  [--output-lang fr|en]

Pipeline (5 sequential phases)

PhaseModuleWhat runs
1. Locale detectionscripts/site_locale.pyHTML lang → Content-Language → TLD → fallback en
2. Multi-page samplingscripts/site_crawler.pysitemap-aware + strategic diversity (home + service + article + about + case-study)
3. Crawler auditscripts/checks/crawlers.pyrobots.txt parse, 3-category bot taxonomy (training / RAG / user-request)
4. Per-page schema + content healthscripts/checks/{schema,content_health}.pyJSON-LD validity + EEP visible-facts coverage; BLUF + Mount AI patterns
5. RRF measurement (optional)scripts/rrf.py + scripts/serp/{google,brave}.pywhen --positioning is supplied, runs 10 fan-out queries × 2 engines

Output structure

The audit lands at site-client/<slug>/audits/<YYYY-MM-DD>-audit.md. Path resolved by scripts/client_paths.py (per-client folder convention).

1. État des lieux par LLM        ← verdict table + 5 LLM detail blocks
2. Plan d'action                  ← unified, per-LLM impact tags
3. Ce que l'audit ne mesure pas

Annexes techniques:
  A. RRF mesuré (détail)
  B. Crawlers IA (robots.txt)
  C. Schema multi-page
  D. Content health multi-page
  E. Findings — vue agrégée

Glossaire technique

When NOT to use this skill

  • Single-page schema-only or content-only checks → invoke scripts/checks/schema.py or scripts/checks/content_health.py directly.
  • RRF-only measurement on existing fan-out queries → use the geo-rrf skill or scripts/rrf.py directly.
  • Per-client folder management (without a fresh audit) → use geo-client.

Examples

# Full audit, French output, positioning mode
python3 -m scripts.run_audit "https://example.fr/" \
  --positioning "agence de design" \
  --vs concurrent1.fr,concurrent2.fr \
  --output-lang fr

# Audit without RRF (on-page only, no SERP scrapes)
python3 -m scripts.run_audit "https://example.com/"

Dependencies

  • scripts/run_audit.py (orchestrator)
  • All modules under scripts/checks/, scripts/serp/, plus scripts/rrf.py, scripts/fanout.py, scripts/llm_impact.py, scripts/i18n.py, scripts/site_crawler.py, scripts/site_locale.py, scripts/client_paths.py
  • Python deps: requests, beautifulsoup4, lxml (see requirements.txt)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free