agentleFS
Sign inStart free
diego-ndiego-n/SEO-OPTIMIZER/SKILL.md

seo-analyzer

Skill1 starsChanged 8 months agoMITView on GitHub

Use this skill when the user asks to audit, analyze, score, or improve

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. refly-ai/refly-skills★ 204same name
    2. smithjohn78390/smith--skills★ 41same name
    3. yangliu2060/smith--skills★ 40same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for the URL or local file path of the page to be audited, if not provided.

    line 20
  2. Distinctive:

    Ask if they want a quick audit (metadata + content, ~2 min) or a full audit (including Core Web Vitals via PageSpeed API, ~5 min).

    line 21
  3. Distinctive:

    If a PageSpeed audit is requested, ask for the optional Google PageSpeed API key (or proceed without it using Lighthouse CLI).

    line 22
  4. Distinctive:

    After collecting the JSON outputs, run the report generator with the appropriate language flag.

    line 38
  5. Distinctive:

    If the user asks to apply fixes to a local file:

    line 46
  6. Distinctive:

    After editing, re-run the audit and report the updated score delta.

    line 49
  7. Distinctive:

    Language Consistency: If the user asks in Portuguese, all responses and reports must be in Portuguese.

    line 54
  8. Distinctive:

    NEVER guess or hallucinate tag values.

    line 55
  9. Distinctive:

    NEVER apply fixes to a remote/production URL.

    line 56
  10. Distinctive:

    If no API key is provided for PageSpeed, skip Core Web Vitals and calculate the final score over 80 total points.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

SEO Analyzer & Score Improver

Goal

Perform a complete SEO audit on a given URL or local HTML file, generate a numeric score (0–100) broken into 5 weighted categories, and produce a prioritized action plan with ready-to-apply fixes in the user's preferred language (English or Portuguese).

Instructions

Phase 1 — Language & Target Collection

  1. Detect Language: Detect if the user is communicating in English or Portuguese. Use --lang en for English and --lang pt for Portuguese in subsequent script calls.
  2. Ask the user for the URL or local file path of the page to be audited, if not provided.
  3. Ask if they want a quick audit (metadata + content, ~2 min) or a full audit (including Core Web Vitals via PageSpeed API, ~5 min).
  4. If a PageSpeed audit is requested, ask for the optional Google PageSpeed API key (or proceed without it using Lighthouse CLI).

Phase 2 — Run the Audit Scripts

Execute the scripts in order. Do NOT skip steps.

Step 2a — Technical & On-Page Scrape

python scripts/seo_audit.py "<URL_OR_FILE>"

Step 2b — Core Web Vitals (Full Audit only)

python scripts/core_web_vitals.py "<URL>"

Phase 3 — Score & Generate Report

After collecting the JSON outputs, run the report generator with the appropriate language flag.

Step 3 — Generate Final Report

python scripts/generate_report.py "<JSON_AUDIT>" ["<JSON_VITALS>"] --lang <en|pt>

Phase 4 — Apply Fixes (Optional)

If the user asks to apply fixes to a local file:

  • Apply only the changes explicitly listed in the audit report.
  • Make a backup of the original file as <filename>.seo-backup before editing.
  • After editing, re-run the audit and report the updated score delta. If the language is Portuguese, say something like "Score melhorado de 61 → 78 ✅".

Constraints

  • Language Consistency: If the user asks in Portuguese, all responses and reports must be in Portuguese. If in English, all in English.
  • NEVER guess or hallucinate tag values. Only report what the scripts return.
  • NEVER apply fixes to a remote/production URL. Local files only.
  • If no API key is provided for PageSpeed, skip Core Web Vitals and calculate the final score over 80 total points.

Examples

Example 1 — Quick Audit (English) User: "Analyze the SEO of https://mysite.com" Agent:

  1. Runs seo_audit.py
  2. Runs generate_report.py ... --lang en
  3. Responds in English.

Example 2 — Auditoria (Português) Usuário: "Analisa o SEO de https://meusite.com.br" Agente:

  1. Executa seo_audit.py
  2. Executa generate_report.py ... --lang pt
  3. Responde em Português.

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