skills.rest
HabibTorjmen
HabibTorjmenCOMMUNITY
Explore all skills by this author →
GitHub

profile-chonk

Generate Perfetto-compatible traces for Chonk prover profiling.

Updated May 14, 2026
Search Tags:#profiling#tracing#wasm#perfetto#chonk#ivc prover#remote benchmarking
One-click install
npx skills add https://github.com/HabibTorjmen/Blockchain --skill profile-chonk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: profile-chonk
Source: https://github.com/HabibTorjmen/Blockchain/tree/main/aztec-packages/barretenberg/.claude/skills/profile-chonk
Command: npx skills add https://github.com/HabibTorjmen/Blockchain --skill profile-chonk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the challenge of understanding where time goes during Chonk (client-IVC) proving by producing an inspectable Perfetto trace instead of only raw timing numbers.

Core Features & Use Cases

  • Remote visual profiling with Perfetto traces: Runs the Chonk prover on a shared EC2 benchmarking machine and outputs Perfetto-compatible JSON suitable for flame/zone-style inspection.
  • Native and WASM runtime coverage: Profiles both the native and WASM runtimes via the same input flows so you can compare threading and hotspots.
  • One-click sharing workflow: Generates a public Perfetto UI link (via a public gist) for fast team collaboration and review.

Quick Start

Run the profile-chonk Skill with the flow you care about (for example, transfer_1) and optionally add --wasm to produce a Perfetto UI link you can open and share.

Frequently Asked Questions about profile-chonk

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

FAQPage Schema
How do I profile Chonk IVC prover performance bottlenecks?▼

Profile Chonk IVC prover bottlenecks by generating Perfetto-compatible performance traces that visualize proving flows as flame and zone-style charts for inspectable analysis.

Can I trace both native and WASM runtime proving performance?▼

Yes, you can trace both native and WASM runtime proving performance using the same input flows, allowing direct comparison of threading behavior and hotspots across both runtime environments.

What SSH credentials do I need to run remote benchmarking for proving traces?▼

Remote benchmarking requires non-empty BB_SSH_KEY, BB_SSH_INSTANCE, and BB_SSH_CPP_PATH environment variables to execute the bb prove command on a shared EC2 machine and retrieve Perfetto trace outputs.

How do I share Perfetto traces with my team for proving performance review?▼

Share Perfetto traces by publishing the resulting trace output as a public gist, which generates a public Perfetto UI link for fast team collaboration and review of proving performance data.

What is the best way to visualize where time goes during client-IVC proving?▼

The best way to visualize client-IVC proving time is generating Perfetto-compatible JSON traces from representative end-to-end proving flows, providing inspectable flame and zone-style charts instead of raw timing numbers.

Related Skills

Explore More Software Engineering Skills→
sluongngsluongng
6

buildbuddy-action-reproduce

Generate a deterministic bb execute replay from a BuildBuddy invocation.

Community
Advanced
androidandroid
6.6k

perfetto-trace-analysis

Analyze Perfetto traces to locate Android app latency, memory, and jank root causes.

Official
Advanced
ricablericable
1

ruvector-onnx-embeddings-wasm

Generate text embeddings with ONNX Runtime in WebAssembly.

Community
Intermediate
esafirmesafirm
4

perfetto-sql

Convert natural language performance questions into Perfetto SQL and run them on local trace files.

Community
Advanced