Perfetto Performance Analysis
Perfetto trace analysis with a pinned trace_processor and 235 query graphs
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Aug 10, 2026
- Environment
- Claude Code 2.x (agent harness)
Bootstrapped its own Perfetto v57.2 trace_processor and verified the binary's SHA-256 against the bundled lock file, then ran startup_analysis end to end on a real 2 MB Android warm-start trace in 13.7 seconds. One command returned a 15-step evidence graph: a 156.5 ms warm start of androidx.benchmark.integration.macrobenchmark.target, activityResume holding 68% of it with only 2.2 ms of self time, 11 synchronous main-thread binder calls into system_server (14.8% of startup), 89.8% of the main thread asleep, and a data-quality flag (R008_TTFD_GT_DUR) on the TTFD figure. The honest no-skill baseline, hand-written SQL through the official perfetto Python library, found the package name and a 144 ms launching slice but no self-time, thread-state or binder attribution and no quality warning. The bundled SQL guardrail also rejected a bare span_join call on the spot, which is exactly the Perfetto footgun it advertises. Only rough edge: some result strings come back in Chinese despite English-only documentation.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Perfetto Performance Analysis does
Analyzes Android, Linux and Chromium Perfetto traces by running deterministic SQL against a checksum-pinned trace_processor_shell instead of guessing from symptom names. Bundles 235 runnable analysis graphs plus 14 workflow guides covering startup, jank and scrolling, input latency, ANR and binder blocking, CPU scheduling, memory and GC, GPU and SurfaceFlinger, power and thermal. Triggers when you hand Claude a .pftrace or perfetto-trace and ask why an app is slow, janky, or regressed between two builds.
How to install Perfetto Performance Analysis
git clone --depth 1 https://github.com/Gracker/Perfetto-Skills.git
mkdir -p ~/.claude/skills
cd Perfetto-Skills && cp -r skills/perfetto-performance-analysis ~/.claude/skills/perfetto-performance-analysis
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Perfetto Performance Analysis
-
/perfetto-performance-analysisPerfetto trace analysis with a pinned trace_processor and 235 query graphs
It also activates on plain-language prompts like these:
-
Analyze this Perfetto trace and find the app's startup duration -
What's causing jank and scroll latency in this trace file? -
Find the top main-thread blocking contributors in this trace
Frequently asked questions
- Is the Perfetto Performance Analysis skill free?
- Yes. The skill itself is free from Gracker/Perfetto-Skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Perfetto Performance Analysis work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Aug 10, 2026. Verdict: Tested · Works. Bootstrapped its own Perfetto v57.2 trace_processor and verified the binary's SHA-256 against the bundled lock file, then ran startup_analysis end to end on a real 2 MB Android warm-start trace in 13.7 seconds. One command returned a 15-step evidence graph: a 156.5 ms warm start of androidx.benchmark.integration.macrobenchmark.target, activityResume holding 68% of it with only 2.2 ms of self time, 11 synchronous main-thread binder calls into system_server (14.8% of startup), 89.8% of the main thread asleep, and a data-quality flag (R008_TTFD_GT_DUR) on the TTFD figure. The honest no-skill baseline, hand-written SQL through the official perfetto Python library, found the package name and a 144 ms launching slice but no self-time, thread-state or binder attribution and no quality warning. The bundled SQL guardrail also rejected a bare span_join call on the spot, which is exactly the Perfetto footgun it advertises. Only rough edge: some result strings come back in Chinese despite English-only documentation.
- What is the Perfetto Performance Analysis SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Perfetto Performance Analysis?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Perfetto Performance Analysis with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.