seed-skills/qaskills-analytics-check/SKILL.md
Pull weekly/monthly performance metrics for qaskills.sh from Google Analytics 4 (GA4) and Google Search Console (GSC) via Claude in Chrome. Returns traffic, channels, top queries, top pages, growth deltas in a single report.
npx skillsauth add PramodDutta/qaskills QASkills.sh Analytics Performance CheckInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an expert at pulling site performance data for qaskills.sh from Google Analytics 4 and Google Search Console. Use Claude in Chrome browser tools to navigate, capture, and synthesize metrics into a single weekly/monthly report. Goal: detect growth trends, traffic source health, ranking opportunities, and content gaps without manual clicking.
| Tool | ID / URL |
|------|----------|
| GA4 Property | qaskillssh — property ID 528788664 (account btc scrolltest / 107190665) |
| GA4 Measurement ID | G-DBRNT5VNQ3 |
| Search Console | Domain property sc-domain:qaskills.sh |
| Site URL | https://qaskills.sh |
| Login email | [email protected] (or [email protected] for GSC if access needed) |
browser_batch — Each report is navigate + wait + screenshot. Batch saves 3-5x time.qaskills*, qa skills*. Non-brand reveals true SEO health.mcp__Claude_in_Chrome__tabs_context_mcp({ createIfEmpty: true })
Navigate to:
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/intelligenthome
Wait 5s for chart to render, screenshot. Extract:
From Home, click "Traffic acquisition" tile (recently accessed) OR navigate sidebar: Generate leads → Traffic acquisition.
Wait 5s. Close any "Add annotations" or "Generate leads reports" popup with X. Scroll down to reveal data table.
Extract for each channel: Sessions, Engaged sessions, Engagement rate, Avg engagement time, Events:
| Channel | Sessions | % | Engagement Rate | Avg Time | |---------|----------|---|-----------------|----------| | Organic Search | ... | ... | ... | ... | | Direct | ... | ... | ... | ... | | Referral | ... | ... | ... | ... | | Organic Social | ... | ... | ... | ... | | Email | ... | ... | ... | ... | | Unassigned | ... | ... | ... | ... |
Also capture any AI anomaly insight banner at top (e.g. "X surged on date Y").
Click sidebar: Search Console → Queries. Wait 5s, scroll down to data table.
Extract top 10 queries with:
| # | Query | Clicks | Impressions | CTR | Avg Position | |---|-------|--------|-------------|-----|--------------| | 1 | ... | ... | ... | ... | ... |
Also note:
qaskill vs all othersClick sidebar: Generate leads → Landing page. Wait 5s. Scroll to data table.
Extract top 10 landing pages:
| # | Landing Page | Sessions | Active Users | Avg Time | Notes | |---|--------------|----------|--------------|----------|-------| | 1 | / | ... | ... | ... | homepage |
Flag pages with avg time < 20s as possible bounce issue.
Output single markdown report with sections:
# QASkills.sh Performance Report — [Date Range]
## Top-Line Metrics (28d)
| Metric | Value | Δ vs Prior 28d |
|--------|-------|---------------|
| Active Users | ... | ... |
| Sessions | ... | ... |
| Engagement Rate | ... | ... |
| Total Events | ... | ... |
## Today's Snapshot
- Active users today: X (Y% vs yesterday)
- Realtime: N users
- Top countries: ...
## Traffic Channels (28d)
[channel table]
## Search Console (28d)
- Total clicks: ... | Impressions: ... | CTR: ...% | Avg pos: ...
- Total queries indexed: ...
- Brand share: X% | Non-brand share: Y%
### Top 10 Queries
[query table]
## Top Landing Pages
[landing page table]
## Anomalies & Insights
- [Anomaly 1 from GA4 banner]
- [Page with bounce signal]
- [Growing query opportunities]
## Next Actions
- [Specific SEO/content recommendations based on data]
For comparison/sanity check — this is what healthy growth looked like:
| Metric | 28d (Mar 16 - Apr 12) | 28d (Apr 23 - May 20) | Growth | |--------|----------------------|----------------------|--------| | Sessions | 5,945 | 9,101 | +53% | | Organic Search | 1,384 | 4,399 | +218% | | Direct | 3,811 | 3,844 | flat | | Referral | 534 | 512 | flat | | GSC clicks | 717 | 869 | +21% | | GSC impressions | ~8,800 | 14,869 | +69% | | GSC queries indexed | 134 | 1,312 | +879% |
Top GSC queries (28d, May 20):
Top landing pages (28d, May 20):
# GA4 Home
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/intelligenthome
# Traffic Acquisition
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/explorer?r=lifecycle-traffic-acquisition-v2
# Pages and Screens
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/explorer?r=all-pages-and-screens&collectionId=business-objectives
# Landing Page
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/explorer?r=landing-page&collectionId=business-objectives
# Search Console Queries (in GA4)
https://analytics.google.com/analytics/web/#/a107190665p528788664/reports/explorer?r=search-query&collectionId=search-console
# Google Search Console (native)
https://search.google.com/search-console/performance/search-analytics?resource_id=sc-domain%3Aqaskills.sh
qaskill* traffic is brand recall. Non-brand is true SEO health.browser_batch for navigation — Cuts wall time by 3-5x vs individual clicks./Users/promode/qaskills/.analytics-reports/YYYY-MM-DD.md for history.browser_batch or direct deeplinks.# Save analytics report to dated file
mkdir -p ~/qaskills/.analytics-reports
date_today=$(date +%Y-%m-%d)
# (paste markdown report content here)
Use when user asks:
development
Generate test data from the schemas you already have. Read OpenAPI, JSON Schema, SQL DDL, or TypeScript models and produce deterministic factories, boundary and negative cases, relational datasets with valid foreign keys, cleanup scripts, and PII-safe synthetic data. Production records never leave the machine.
development
Diagnose flaky test failures from Playwright reports, traces, and rerun history. Classify each failure as product, test, environment, data, or unknown with cited evidence and a proposed fix. Never auto-modifies code without opt-in.
tools
Test LLM, RAG, MCP, and agentic systems end to end. Build golden datasets, run deterministic checks and LLM judges, score retrieval, probe prompt injection, verify tool use, and gate CI on thresholds. Orchestrates DeepEval, Ragas, promptfoo, and Langfuse.
development
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.