What the Crash, ANR and device-health analysis prompt does

Act as a game reliability engineer, mobile performance analyst and release-quality lead.

The prompt will, at minimum:

  • Validate datasets, definitions, time windows, market scope and source-of-truth ownership before assessing crash, anr and device-health analysis
  • Examine crash-free users and sessions, ANR or hang rate, affected builds, operating systems, device models, GPU and memory tiers, stack traces, breadcrumbs, startup time, frame pacing, thermal and battery signals, network errors, reproduction paths, release changes, severity, reach and data-quality gaps; preserve original identifiers and show the derivation of every finding
  • Segment only when evidence supports the split. Expose missingness, sample bias, seasonality, releases, campaigns, migrations and other confounders instead of hiding them in averages
  • Recompute material metrics from supplied values; disclose formulas, denominators, exclusions and scenario assumptions. Never invent benchmarks, market sizes or competitor performance
  • Turn evidence into an evidence-linked stability scorecard, issue clusters, reproducibility matrix, release-risk assessment and prioritised remediation plan; assign owner, priority, dependency, expected signal, verification method and human-approval point to each action

Who it is for

Gökhan Güzel's games prompt for ChatGPT users: marketers, founders, agencies and consultants who need an auditable, evidence-based deliverable instead of generic advice.

What you get

  • Executive summary and data-quality report
  • Crash, ANR and device-health analysis methodology and evidence ledger
  • Segmented findings, calculations and scoring
  • Prioritised action backlog with owners and validation criteria
  • Sources, limitations, confidence and QA report

Variables

PlaceholderPurpose
{{analysis_window}}Date, time or period value; state ISO format, time zone, start/end boundary and comparison period
{{anr_reports}}Structured dataset or source file; state fields, data types, period, units, currency, time zone and provenance
{{build_versions}}Required input value; state source, data type, format, unit, period, market and locale where applicable
{{crash_reports}}Structured dataset or source file; state fields, data types, period, units, currency, time zone and provenance
{{device_catalog}}Structured dataset or source file; state fields, data types, period, units, currency, time zone and provenance
{{game_name}}Verified identifier or text value; state exact spelling, source, status and validity scope
{{known_incidents}}Required input value; state source, data type, format, unit, period, market and locale where applicable
{{performance_traces}}Required input value; state source, data type, format, unit, period, market and locale where applicable
{{release_notes}}Required input value; state source, data type, format, unit, period, market and locale where applicable
{{session_telemetry}}Required input value; state source, data type, format, unit, period, market and locale where applicable
{{severity_rules}}Approved rule, policy or constraint; state owner, version, scope, jurisdiction and effective date
{{success_metrics}}Numeric value or table; state formula, numerator, denominator, unit, currency, tax treatment, period and source
{{target_markets}}Target markets
{{target_platforms}}Target platforms, consoles or standards

How to use

Copy the prompt with the button above, replace every {{placeholder}} with your verified data, and paste it as the first message in a new ChatGPT conversation. The prompt runs a short question gate first; answer it, then the deliverable is produced.

Run Crash, ANR and device-health analysis in ChatGPT

Open a new ChatGPT chat, paste the filled-in Crash, ANR and device-health analysis prompt and answer the short question gate. ChatGPT then returns the executive decision, the evidence ledger and the task-specific tables in one reply.

Source

Original file in the multilingual prompt library on GitHub: