trace-analysis

Analyze Pulp Perfetto trace files to diagnose performance bottlenecks and suggest fixes.

13|1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Generous-Corp/pulp --skill trace-analysis-generous-corp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace-analysis
Source: https://github.com/Generous-Corp/pulp/tree/main/.agents/skills/trace-analysis
Command: npx skills add https://github.com/Generous-Corp/pulp --skill trace-analysis-generous-corp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the "why is this slow?" problem by autonomously investigating performance bottlenecks in Pulp applications, transforming raw trace data into actionable, plain-English insights and fixes.

Core Features & Use Cases

  • Automated Investigation: Executes a hypothesis-driven loop to identify performance regressions, stuttering, or high CPU usage without requiring manual SQL expertise.
  • Domain-Specific Diagnostics: Provides expert-level analysis for DSP, frame-pipeline, GPU, and JavaScript bridge performance issues using Pulp-specific heuristics.
  • Use Case: When a plugin stutters during UI interaction, this skill analyzes the .pftrace file to determine if the bottleneck is a JS bridge dispatch, a layout invalidation, or a GPU submit stall, and suggests a concrete code fix.

Quick Start

Use the trace-analysis skill to explain why my plugin is slow to open by analyzing the provided trace file.

Frequently Asked Questions about trace-analysis

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

FAQPage Schema
How do I find the root cause of stuttering in a Pulp application trace?

Perfetto trace analysis autonomously investigates Pulp .pftrace files to identify performance bottlenecks, diagnosing latency across DSP, UI frame-pipeline, GPU, and JavaScript bridge domains to provide actionable code fixes.

Why does my plugin have high CPU usage during UI interaction?

High CPU usage during UI interaction often stems from a JS bridge dispatch, layout invalidation, or GPU submit stall. Analyzing the Pulp trace file isolates the specific domain causing the regression.

Do I need to write SQL queries to diagnose latency issues in Pulp traces?

No, you do not need to write SQL queries or have manual expertise to diagnose latency issues. The analysis executes an automated hypothesis-query-drill-down methodology on the .pftrace file to ensure evidence-based performance reporting.

What performance domains are covered when analyzing Pulp Perfetto trace files?

Analyzing Pulp Perfetto trace files covers DSP, UI frame-pipeline, GPU, and JavaScript bridge domains. It uses Pulp-specific heuristics to diagnose latency and stuttering issues across these specific performance areas.

Can I use this trace analysis for performance regressions outside the Pulp ecosystem?

No, this trace analysis is restricted to the Pulp ecosystem. It utilizes Pulp-specific heuristics and domain diagnostics tailored exclusively to Pulp's DSP, frame-pipeline, GPU, and JavaScript bridge architectures.