perfetto-sql

Translate natural language performance questions into validated Perfetto SQL queries.

Updated Apr 5, 2026

Search Tags:#sql #android #performance profiling #perfetto #trace analysis #trace processor

Ready to run

npx skills add https://github.com/inehemiasm/AiAssistant --skill perfetto-sql-inehemiasm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: perfetto-sql
Source: https://github.com/inehemiasm/AiAssistant/tree/main/skills/perfetto-sql
Command: npx skills add https://github.com/inehemiasm/AiAssistant --skill perfetto-sql-inehemiasm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps Android performance engineers analyze complex Perfetto traces by translating natural language questions into reliable Perfetto SQL and avoiding common query mistakes.

Core Features & Use Cases

Natural Language to SQL: Converts performance analysis goals into syntactically valid Perfetto SQL queries for trace_processor execution.
Trace Schema Guidance: Uses Perfetto standard library references to identify tables, modules, columns, and best-practice query patterns.
Use Case: Analyze an Android application startup trace by finding expensive slices, thread activity, CPU behavior, or memory-related events with validated queries.

Quick Start

Use the perfetto-sql skill to find the total duration of expensive rendering slices in the attached Android Perfetto trace.

Frequently Asked Questions about perfetto-sql

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I write Perfetto SQL queries to analyze Android trace performance?▼

To analyze Android trace performance, you translate natural language analysis goals into validated Perfetto SQL queries. This process uses schema-aware generation against standard library tables to investigate slices, threads, and CPU metrics.

Can I use natural language to find expensive slices in an Android startup trace?▼

You can use natural language to find expensive slices in an Android startup trace by converting your analysis request into validated Perfetto SQL. This automatically applies schema-aware query patterns to identify costly rendering slices.

What Perfetto tables are needed for thread and CPU metric trace analysis?▼

Perfetto trace analysis relies on standard library tables containing slices, threads, and CPU metrics. Query generation uses schema guidance to identify the correct modules and columns for validating complex system performance investigations.

Does Perfetto trace_processor support idempotent SQL for system performance investigations?▼

Perfetto trace_processor supports idempotent SQL patterns for system performance investigations. Validated execution against local trace files ensures queries are syntactically correct and reliably analyze thread activity and memory-related events.

Why do my Perfetto SQL queries fail when analyzing complex Android traces?▼

Perfetto SQL queries often fail due to schema mismatches and common query mistakes when analyzing complex Android traces. Schema-aware query generation avoids these errors by validating syntax against standard library references before execution.

What is the best way to validate Perfetto SQL before executing against a local trace file?▼

The best way to validate Perfetto SQL is by generating syntactically valid queries using standard library references. This ensures schema-aware query generation and idempotent SQL patterns before validated execution against local trace files.