Index of every page on this site: llms.txt
All skills
ryze-ai-adgent avatar

/rank-tracking

@f587b0a
Run it yourself

Rank tracking without a tracker subscription — position movers between any two periods from real Search Console data. Use when asked "how are my rankings", "what moved this week/month", "track my keywords", or "did the update hit me".

Use this Skill: https://skilld.dev/gh/ryze-ai-adgent/open-seo-mcp-skills/rank-tracking

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈63 tokens for metadata: the name and description. ≈523 when used: this file.

Description uses 3.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈250 characters, or 3.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Rank Tracking

Requires

The free Ryze MCP connector (https://connector.get-ryze.ai/mcp). Claude Code: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp. claude.ai / Desktop / Cursor: add it as a custom connector with the same URL. Setup: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp?utm_source=github&utm_content=open-seo-mcp-skills

Rank trackers estimate your position by scraping SERPs daily. Search Console records the position Google actually served you at. Use the real number.

Workflow

  1. Property. google_search_console__listSites → pick the user's domain.
  2. Two windows. Default: last 28 days vs previous 28. If the user names an event ("since the March update"), split around that date. GSC data lags ~2 days — never include today.
  3. Pull both periods. google_search_console__runRawSearchAnalytics, dimensions ["query"], rowLimit high enough to cover the site (start 5000). Repeat with ["page"] for page-level movement.
  4. Join and diff. Match queries across periods, compute position delta, clicks delta, impressions delta.
  5. Classify:
    • Winners — position improved ≥ 2 spots on queries with real impressions
    • Losers — dropped ≥ 2 spots (sort by clicks lost, not by delta — a 4→7 drop on a money query beats a 40→80 crash on a nothing query)
    • New — queries appearing only in the recent period
    • Lost — queries that vanished
  6. Spot-verify (optional). For the 3–5 most important losers, if DataForSEO SERP tools are exposed in the workspace, pull the live SERP to see who took the spot. Skip if unavailable.

Output

Verdict first (net up/down and the single biggest move), then four tables: Winners, Losers, New, Lost — query, positions before→after, clicks delta. If the user asked about a specific algorithm update, answer that question explicitly with the before/after evidence.

Recurring

If the user wants this weekly, suggest scheduling it (Claude Code scheduled tasks / a routine) rather than re-running by hand.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning24d3 checks · Risk SAFE
  • Gen Agent Trust Hub24d

    The skill is designed for SEO rank tracking and is safe for its intended purpose. It requires the installation of a specific vendor-provided connector to access Google Search Console data. It involves processing external search query strings, which presents a common but low-risk surface for indirect prompt injection.

  • Socket24d

    No alerts

  • Snyk24d

    Risk: MEDIUM · 1 issue

Signed by skilld at f587b0a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated 4 weeks ago

README badge

README badge for ryze-ai-adgent/open-seo-mcp-skills/rank-tracking