mikefutia/seo-consultant/dashboard

Claude Code and agent skill by mikefutia/seo-consultant

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Build a self-contained HTML SEO dashboard from live GSC + GA4 data — health score, branded-dependency donut, quick wins, 3 priorities. Trigger on "seo dashboard", "build my dashboard", or /seo-os:dashboard.

Install

npx vskill@latest install mikefutia/seo-consultant/dashboard

SKILL.md

SEO Dashboard

Pull live data and render a single-file HTML dashboard that looks like a $200/mo SaaS product. Save to runs/seo-dashboard.html and open it in the browser when done.

Data (pull all of it live — last 28 days + prior 28 for deltas)

  1. Topline cards with deltas: GSC clicks, impressions, avg position, CTR + GA4 organic sessions, engagement rate
  2. SEO health score (0–100) computed from three weighted parts — show the breakdown bars:
  • Trend direction (30): clicks/impressions/sessions momentum
  • CTR vs. expected CTR at current positions (30): standard curve (pos 1 ≈ 28%, 3 ≈ 11%, 8 ≈ 3%, 12 ≈ 1.5%)
  • Branded dependency (40): % of clicks from brand-name queries — heavy weight because it measures whether SEO is actually working
  1. Branded vs. non-branded donut — make the branded % the most prominent number after the score; for most sites it's the wake-up call
  2. Quick-wins table: position 4–20, scored by impressions × CTR-gap to position 3, with each ranking page's current title. If the site is thin, relax to ≥5 impressions and say so. Flag rows that should be deindexed rather than optimized (thank-you pages, opt-in pages).
  3. Top pages (GA4 sessions) × top query (GSC) side by side — flag mismatches where a page ranks for something it isn't optimized for
  4. "This Week's 3 Priorities" panel at the top — each tied to a number from the data, never generic advice

Design rules

  • Dark theme (#0d1117-ish), ONE accent color, big numerals, generous whitespace
  • Conic-gradient score ring; green/red delta arrows; subtle card borders
  • All CSS inline, zero external dependencies, works offline forever
  • Date range and "generated [date]" in the header
  • Animate the score ring filling on load (CSS only)

Rules

  • Every number comes from the live pull — if a connection fails, render the dashboard with that section greyed out and labeled "not connected," never with invented data
  • Segment branded vs. non-branded everywhere; branded rankings are table stakes, not wins
  • After rendering, give a 3-sentence chat summary: the score, the single biggest finding, and what to run next (usually /seo-os:quick-wins)

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mikefutia/seo-consultant/dashboard/badge)](https://verified-skill.com/skills/mikefutia/seo-consultant/dashboard)

Something wrong with this skill or its page? Tell us.