Skip to content

pantyuhov9-web/agentic-workflow-template / .claude/skills/analytics

analytics

Verified

Website analytics audit — tracking verification, SEO check, performance metrics, conversion path analysis

Site Analytics — tracking, SEO, and performance audit

You are running the analytics skill. Your job: audit a website's analytics implementation, SEO health, or performance, then help the user pick ONE thing to fix.

Architecture

Layer 1 (deterministic Python): python3 tools/site_analytics.py --root <path> --mode <mode> — scans HTML files for tracking IDs, SEO tags, and performance signals. Generates .tmp/site_analytics_map.json.

Layer 2 (Opus subagent): For seo and full modes, spawn an Explore subagent to check live indexation and competitive signals via WebSearch.

Step-by-step

Step 0 — Parse arguments

Parse $ARGUMENTS for the mode and optional path:

  • First word should be one of: tracking, seo, performance, full
  • Remaining text is the site root path
  • Default mode: full. Default path: current working directory (else ask for the site root)

Step 1 — Run Layer 1

python3 tools/site_analytics.py --root "<site_root>" --mode <mode>

Step 2 — Layer 2 (SEO and full modes only)

For seo or full modes, spawn an Explore subagent:

subagent_type: "Explore"
model: "opus"
description: "Layer 2 SEO analysis"

The subagent should:

  1. Read .tmp/site_analytics_map.json
  2. Use WebSearch to check: site:<domain> indexation, search for the site's target keywords
  3. Assess whether structured data meets Google Rich Results requirements
  4. Return findings in the standard format:
[CONCEPTUAL] <category>
    <path>
    → <description>
    Fix: <fix>

Step 3 — Combine and present

Same format as site-audit: numbered findings list, user picks ONE.

Step 4 — Wait, then fix ONE

Same discipline: one fix per invocation.

Mode details

  • tracking — GA4/Pixel/Clarity ID consistency, duplicate init, CAPI presence, consent banner
  • seo — sitemap, robots.txt, canonical, JSON-LD, title/description quality and uniqueness
  • performance — page weight, external requests, render-blocking scripts, image optimization, preconnect
  • full — all three combined

See also

rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 193kUpdated Claude CodeCodexVerifiedInstall