j6-ucp-perfetto-trace-analysis

j6-ucp-perfetto-trace-analysis is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 133 tokens per session (1,642 once invoked), scanned A, original, Apache-2.0.

A tool for analysing Perfetto trace files from Horizon Robotics' UCP model-inference software. Perfetto is a performance-tracing system; the tool looks for delays and bottlenecks in the inference pipeline.

In plain words
What is it for?
Use it to investigate UCP inference latency, find hotspots, examine handoff gaps, and produce a repeatable Markdown analysis report.
Why use it?
It narrows a large trace to likely causes of slow inference, such as pipeline stalls, CPU/BPU gaps, or delayed operations and responses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate UCP inference latency, find hotspots, examine handoff gaps, and produce a repeatable Markdown analysis report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HorizonRobotics/OE-Skills --skill j6-ucp-perfetto-trace-analysis
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for j6-ucp-perfetto-trace-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for j6-ucp-perfetto-trace-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-perfetto-trace-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00133 $0.01642
Opus 5 $0.00067 $0.00821
Sonnet 5 $0.00027 $0.00328
Haiku 4.5 $0.00013 $0.00164

Measured 12d ago against content hash 0ffc14bec087, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

j6-ucp-perfetto-trace-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_trace.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

horizon/skills/ucp/j6-ucp-perfetto-trace-analysis/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UCP Perfetto Inference Analysis

Version: v1.1.0

Use this skill for UCP model inference Perfetto traces when the goal is to quickly find, triage, and explain likely performance issues in the inference path.

It is intentionally scoped: the skill is optimized for fast bottleneck localization inside UCP inference traces, then maps that work onto a fixed set of validated analysis directions so the output stays repeatable instead of drifting into generic Perfetto exploration.

What this skill is for

Use this skill when the user wants to:

  • analyze a UCP inference .pftrace / Perfetto trace
  • quickly find likely bottlenecks, hotspots, or latency contributors in the UCP inference path
  • investigate slow inference, critical-path delay, CPU/BPU handoff gaps, OpInfer delay, dispatch / response delay, or low effective occupancy
  • run one of the validated UCP bottleneck directions in this skill
  • generate the default four-direction Markdown report

Do not use this skill for:

  • generic Perfetto profiling with no UCP inference focus
  • arbitrary performance investigations outside UCP inference
  • UI-only trace browsing with no SQL, filtering, or scripted analysis
  • non-UCP CPU profiling or unrelated workloads

Supported directions

These four directions are the entire scope of the skill’s default report workflow:

  • UCP Critical Path Slice Analysis (Excluding BPU and CPU Operators)
  • UCP CPU Operator Slice Analysis
  • BPU flow dispatch / response delay
  • Corrected BPU effective occupancy

Internal CLI values used by the bundled script:

  • all (default report mode)
  • dnn_name
  • opinfer_desc_flow
  • bpu_flow_delay
  • bpu_effective_occupancy

Read references/directions.md for the exact rule definitions, thresholds, grouping semantics, and output expectations.

Default workflow

The bundled analyzer is scripts/analyze_trace.py. Prefer it before writing new automation.

Default behavior:

  1. Probe the trace schema and relevant argument structure.
  2. Run all four validated directions.
  3. Export one Markdown report.
  4. Return the report path and a short completion note.
  5. Stop unless the user explicitly asks for deeper follow-up analysis.

Read the full file on GitHub · 164 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 164 lines · 133 tokens per session scan A 0ffc14bec087

Subscribe to this mod's changes

j6-ucp-perfetto-trace-analysis is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,642 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens