Captura un snapshot base del estado SEO de un dominio o URL y luego compara el estado actual para detectar regresiones. Rastrea autoridad, tráfico, keywords, backlinks y contenido on-page. Tres subcomandos: baseline, compare, history.
en todo el repo
0–100, la ruta de este skill
último commit aquí
últimos 90 días
108 tok en reposo
18 KB
Funciona con cualquier agente que lea SKILL.md
npx -y skills add seranking/seo-skills --skill seo-drift --agent claude-codeSe instala solo en este repositorio.
Di cualquiera de estas frases y el agente debería cargar este skill.
Example output: examples/seo-drift-wix-com-20260514/compare/DRIFT-REPORT.md
Git for SEO. Capture a snapshot of a domain or URL's SEO state ("baseline"), then on later runs diff the current state against the baseline and surface regressions. Catches the things that get worse silently after a deploy, redesign, or content cull.
Acknowledgements: drift-as-an-SEO-skill framework originated in
claude-seoby AgriciDaniel (with the original concept credited to Dan Colta, Pro Hub Challenge). MIT-licensed both directions; this implementation is independent but the framing is theirs.
WebFetch tool available (for URL-mode page fingerprinting).baseline, compare, history).| Flag | Mode | Effect |
|---|---|---|
--no-firecrawl |
baseline, compare | Skip Firecrawl-based <head> + JSON-LD capture even when Firecrawl is installed (saves credits at the cost of canonical / robots / og:* / JSON-LD diff coverage). |
--skip-cwv |
baseline, compare | Skip the Google CrUX capture (step 4b) even when google-api.json is configured. Useful when you only care about content/structural drift, or when CrUX rate-limit concerns outweigh CWV coverage. Mirrors theirs at seo-drift/SKILL.md:107, 131. |
--baseline-id <n> |
compare | Compare against a specific baseline by ID rather than the most recent. |
--limit <n> |
history | Cap the number of historical entries shown. |
baseline <target>Capture the current SEO state and write it to a snapshot file. No diff produced.
compare <target>Load the most recent baseline for the target. Capture the current state. Diff. Produce DRIFT-REPORT.md.
history <target>List all stored baselines for the target with their dates and key metrics (DA, traffic, keyword count). No diff produced.
example.com; URL = anything starting with http(s)://.python3 -c "from scripts.google_auth import validate_url; import sys; sys.exit(0 if validate_url('{target}') else 1)" (or import validate_url directly in any helper script). Reject loopback (127.0.0.1, ::1, localhost), private IP ranges (10/8, 172.16/12, 192.168/16), link-local (169.254/16), and Google metadata endpoints. If validation fails, abort with a clear error and don't proceed to fetch — feeding an unvalidated URL into Firecrawl / WebFetch / Google APIs would risk SSRF against internal services. Mirrors theirs at seo-drift/SKILL.md:97.skills/seo-firecrawl/references/preflight.md for the canonical 3-stage preflight (credit balance, Firecrawl availability, Google APIs). Skill-specific notes:<head> + JSON-LD content so canonical / robots / og:* / JSON-LD changes are detectable on diff. Without it the snapshot is partial. Pass --no-firecrawl to skip Firecrawl even when available (saves credits at the cost of diff coverage).indexStatusVerdict, googleCanonical, lastCrawlTime) so subsequent compares can flag field-data and indexation drift. See skills/seo-google/references/cross-skill-integration.md § "seo-drift" for the full recipe.DATA_getDomainOverviewWorldwide — DA, traffic, organic + paid keyword counts.DATA_getDomainKeywords — top 100 organic keywords with positions.DATA_getBacklinksSummary — backlinks total, referring domains total.DATA_getBacklinksRefDomains — top 20 referring domains with authority.WebFetch (always) + mcp__firecrawl-mcp__firecrawl_scrape (when available)<title>, all <h1..h6>, lang, word count, internal-link count, image count, body markdown for prose-level diff.<head> and <script> content WebFetch strips:metadata: canonical URL, robots meta, og:title, og:description, og:image, twitter:card.html: every <script type="application/ld+json"> block. Capture both detected @types and a hash of the full block content (so any schema-content change is detected on diff, not just type-list changes).--no-firecrawl passed): only WebFetch fields enter the fingerprint. BASELINE.md notes: Snapshot fields recovered via WebFetch only — canonical, robots, og:*, twitter:*, and JSON-LD changes will not be detected on subsequent compares. Install Firecrawl for full coverage.DATA_getPageAuthority.
4b. Google field-data snapshot (only if google-api.json is present AND --skip-cwv not set)python3 scripts/pagespeed_check.py "{target}" --crux-only --json (URL mode) or python3 scripts/pagespeed_check.py "https://{domain}" --crux-only --json (domain mode, origin-level CrUX). Store the resulting p75 LCP / INP / CLS / FCP / TTFB and the source label ("URL" or "origin").python3 scripts/crux_history.py "{target_or_origin}" --json for the 25-week trend window snapshot — store as crux_history_baseline. Subsequent compares can detect drift against the most recent week.python3 scripts/gsc_inspect.py "{target_url}" --site-url "{config.default_property}" --json. Store indexStatusVerdict, coverageState, googleCanonical, userCanonical, lastCrawlTime.--skip-cwv was passed, skip this step entirely and store null for cwv / crux_history fields. The compare-mode rules then surface "Field-data drift: skipped — --skip-cwv flag passed at baseline."null for the affected metrics and continue.seo-drift-{target-slug}-{YYYYMMDD}/snapshot.json.seo-drift-{target-slug}/baselines.json — append {date, snapshot_path} entry.seo-drift-{target-slug}/baselines.json.validate_url() check as baseline mode. Refuses to fetch private/loopback/metadata addresses.references/drift-thresholds.md:not comparable — Firecrawl-only fields missing from {baseline | current} snapshot rather than as a green pass.INDEXED to anything else → red.googleCanonical changed → yellow.lastCrawlTime >60 days old → yellow.Field-data / indexation drift: not comparable — Google fields missing from {baseline | current} snapshot.DRIFT-REPORT.md — red findings first, then yellow, then green/positive deltas. End with a "what to investigate first" recommendation.baselines.json.HISTORY.md with the table.seo-drift-{target-slug}-{YYYYMMDD}/:
seo-drift-{target-slug}-{YYYYMMDD}/
├── snapshot.json (the captured state)
└── BASELINE.md (one-page human summary of what was captured)
seo-drift-{target-slug}-{YYYYMMDD}/:
seo-drift-{target-slug}-{YYYYMMDD}/
├── DRIFT-REPORT.md (synthesised: red/yellow/green changes — primary deliverable; inlines 01-domain-deltas, 02-keyword-churn, 03-backlink-deltas, 04-page-deltas as sections)
└── evidence/
├── baseline-snapshot.json (the prior reference — kept for replay)
├── current-snapshot.json (today's state — kept for replay)
├── 01-domain-deltas.md (DA, traffic, keyword count changes — raw step output)
├── 02-keyword-churn.md (top-100 entries/exits)
├── 03-backlink-deltas.md (new + lost backlinks/domains)
└── 04-page-deltas.md (URL mode only: HTML fingerprint diff)
Top-level: DRIFT-REPORT.md only. The four delta step files are inlined into named sections in DRIFT-REPORT.md; evidence/ keeps the raw delta dumps and both snapshot JSONs so a future re-diff or audit can replay against them.
DRIFT-REPORT.md shape:
# Drift Report: {target}
> Baseline: {baseline date} · Current: {today's date}
## RED — investigate today
- {finding} ({severity rationale})
- ...
## YELLOW — investigate this week
- {finding}
- ...
## GREEN — positive deltas
- {finding}
- ...
## Field-data drift (CrUX + URL Inspection)
- LCP p75: {baseline} → {current} ms ({Δ%}) {↑ red / ↑ yellow / stable / ↓ green}
- INP p75: {baseline} → {current} ms ({Δ%}) {…}
- CLS p75: {baseline} → {current} ({Δ absolute}) {…}
- Indexation status: {baseline INDEXED → current EXCLUDED} (URL mode)
- googleCanonical: {baseline → current} (if changed)
- (Or: `Field-data / indexation drift: not configured` / `not comparable — missing from {snapshot}`)
## What to investigate first
1. {prioritised action with reasoning}
2. ...
seo-drift-{target-slug}-{YYYYMMDD}/HISTORY.md:
# History: {target}
| Date | DA | Traffic | Keywords | Top-3 |
|---|---|---|---|---|
| 2026-04-27 | 42 | 18,500/mo | 1,247 | 89 |
| 2026-03-15 | 41 | 17,200/mo | 1,213 | 85 |
| ...
DATA_getCreditBalance before running. Domain baseline ~10–15 SE Ranking credits; URL baseline ~15–20 SE Ranking credits + 1 Firecrawl credit; compare ~20–30 SE Ranking credits + 1 Firecrawl credit (current-state capture).seo-drift-{target-slug}/ directory in a shared filesystem or commit it to a private repo. Baselines are JSON — git-friendly.DATA_getPageAuthorityHistory (URL mode) or DATA_getDomainAuthorityHistory returns flat-zero values across the window, treat as "insufficient history" — don't compute a delta or surface a regression based on missing data. Cross-check the current-value endpoint (DATA_getPageAuthority / DATA_getDomainOverviewWorldwide) — if the current value is meaningful but history is flat, surface that as a data-quality flag in DRIFT-REPORT.md rather than fabricating a trend.Reproducido de seranking/seo-skills bajo licencia MIT. Leer esta página en markdown.
2 archivos en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.
Requiere el servidor MCP de SE Ranking conectado y la herramienta WebFetch de Claude para el fingerprinting de páginas en modo URL; Firecrawl y google-api.json son opcionales para cobertura completa.
Este repo incluye 32 skills. Si instalas uno, normalmente ya tienes los demás. Ver el pack seo-skills entero y su comando de instalación
Encuentra los prompts y temas de búsqueda con IA donde una marca es invisible o pierde frente a competidores en SE Ranking, y convierte esos vacíos en una campaña social en Planable con seguimiento antes/después.
Construye una propuesta de onboarding de cliente basada en datos, combinando un audit SEO + búsqueda IA de SE Ranking con un análisis en Planable del rendimiento social actual del cliente.
Combina el seguimiento de rankings por ciudad de SE Ranking con contenido social local en Planable, incluyendo publicaciones de Google Business Profile.
Genera un único reporte de rendimiento que une rankings SEO, visibilidad en búsquedas IA (SE Ranking) y engagement social (Planable): resumen en el chat más un informe HTML interactivo autónomo.
Arquitecto de integración con la API de SE Ranking: cubre la Data API y la Project API, responde cualquier duda de endpoints, credit cost o auth, y genera recetas cURL/Python/TypeScript/MCP.
Scraping ad-hoc, mapeo de sitios y crawling completo vía Firecrawl MCP: devuelve HTML crudo, metadatos, DOM renderizado por JS y screenshots que WebFetch no puede obtener.
Encuentra los prompts y temas de búsqueda con IA donde una marca es invisible o pierde frente a competidores en SE Ranking, y convierte esos vacíos en una campaña social en Planable con seguimiento antes/después.
Construye una propuesta de onboarding de cliente basada en datos, combinando un audit SEO + búsqueda IA de SE Ranking con un análisis en Planable del rendimiento social actual del cliente.
Combina el seguimiento de rankings por ciudad de SE Ranking con contenido social local en Planable, incluyendo publicaciones de Google Business Profile.
