Diagnostics

Use for structured technical SEO audits, incident response, and validation.

Published by @gtmagents·from gtmagents/gtm-agents·0 agent reads / 30d·0 saves·

Technical Diagnostics Toolkit Skill

When to Use

  • Investigating crawl/index anomalies, traffic drops, or Core Web Vitals regressions.
  • Running scheduled audits ahead of major launches or migrations.
  • Validating fixes before/after engineering deployments.

Framework

  1. Signal Triangulation – combine Search Console, log files, crawler output, and analytics deltas.
  2. Replication Scripts – document steps to reproduce issues (user agents, locales, device types).
  3. Root Cause Hypotheses – map symptoms to likely causes (render blocking, redirects, robots, schema errors).
  4. Fix Design – outline remediation options, risk level, dependencies, and testing approach.
  5. Validation & Monitoring – specify metrics and alerts to confirm resolution.

Templates

  • Diagnostics worksheet (symptom, evidence, hypothesis, owner, next action).
  • Crawl + render checklist per environment.
  • Validation log capturing metrics pre/post change.

Tips

  • Keep historical baselines to quickly detect regressions.
  • Pair with engineering release notes to correlate incidents.
  • Automate recurring crawls and lighthouse runs to catch issues early.

More on the bench

SKILL0

Draft Response

Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue.

customer-success+2
31
SKILL0

Design Clinical Campaign

Produces clinical-grade campaign brief with targeting, creative guidance, and review plan.

marketing-growth-copy+2
30
SKILL0

Observability Designer

Design production-ready observability strategies combining metrics, logs, and traces. Includes SLI/SLO design, golden-signals monitoring, alert optimization. Use when adding observability to a new service, refactoring alerting that is too noisy, or designing an SLO program before scaling production load.

software-engineering+2
1