ascend-moe-optimizer-trace-analyzer

ascend-moe-optimizer-trace-analyzer is a skill for Claude Code, Codex from XiaoLuoLYG/GOD. It costs 115 tokens per session (3,175 once invoked), scanned A, original, Apache-2.0.

A tool for turning Chrome or Perfetto trace files into grouped timing statistics, charts, and a Markdown performance report. These trace files record timed events from software execution.

In plain words
What is it for?
Use it to analyze Ascend MoE or FusedDeepMoe traces by phase, category, core group, thread, and operation name, with optional written analysis.
Why use it?
It reduces the manual work of inspecting traces and helps reveal time distribution, overlap, idle gaps, and likely bottlenecks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to analyze Ascend MoE or FusedDeepMoe traces by phase, category, core group, thread, and operation name, with optional written analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer
About the project

GOD is a control room for observing and directing societies of language-model agents running in simulated worlds. It lets researchers inspect replays, question individual agents, alter future events, reset simulations, and export experiments for reuse. The catalogue entries are skills and agents for operating and investigating these simulations.

XiaoLuoLYG/GOD · 1,102 stars · on GitHub · xiaoluolyg.github.io

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 XiaoLuoLYG/GOD --skill ascend-moe-optimizer-trace-analyzer
Clone the repo
git clone --depth 1 https://github.com/XiaoLuoLYG/GOD

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 ascend-moe-optimizer-trace-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer/github.svg)](https://agentmods.dev/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer)
Your own site
<a href="https://agentmods.dev/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer/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 ascend-moe-optimizer-trace-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/ascend-moe-optimizer-trace-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,175 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00115 $0.03175
Opus 5 $0.00057 $0.01588
Sonnet 5 $0.00023 $0.00635
Haiku 4.5 $0.00012 $0.00317

Measured 5d ago against content hash 5ff28d84022a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ascend-moe-optimizer-trace-analyzer 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 5d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (analyzers/__init__.py, analyzers/diagnosis.py, analyzers/llm_analysis.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.

jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/ascend-moe-optimizer-trace-analyzer/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ascend MoE 性能 Trace 分析

分析 Chrome/Perfetto 风格的 trace.json,把原始 trace event 转换为结构化统计表、图表和 Markdown 报告,用于替代人工在 Perfetto 中做第一轮耗时分布和瓶颈定位。本 skill 的内置名称为 ascend-moe-optimizer-trace-analyzer;当前目录为 ascend-moe-optimizer-trace-analyzer

何时使用

  • 用户需要分析 算子或 runtime 打点 导出的 Chrome/Perfetto trace.json,关注 phase 分布、category、Ascend core group、线程 tid、overlap、bubble
  • 调优 Ascend 上 MoE / FusedDeepMoe(如 fused_deep_moe 或需沿用本仓库默认 config/phase_map.yaml 的场景。
  • 需要 确定性自动诊断,或可选的 --llm-analysis 二次解读。

脚本位置

  • 用户安装后的 skill 根目录:<ASCEND_MOE_OPTIMIZER_SKILL> = ~/.jiuwenclaw/agent/jiuwenclaw_workspace/skills/ascend-moe-optimizer-trace-analyzer
  • 入口:<ASCEND_MOE_OPTIMIZER_SKILL>/app.py
  • 从本仓库资源运行时,将上述路径换为 jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/ascend-moe-optimizer-trace-analyzer(相对仓库根目录)。

执行命令前请先 cd<ASCEND_MOE_OPTIMIZER_SKILL>,或使用下文绝对路径形式的 python3 .../app.py

能力概览

本 skill 面向的核心对象是 trace.json,不是某一个固定算子。它本身负责:

  • 解析 trace 中的完整区间事件。
  • 将原始 trace name 映射为可稳定统计的 phase。
  • 按 phase、category、core group、tid、raw name 聚合耗时。
  • 计算 phase overlap 和外层阶段 bubble。
  • 生成统计图、文字化统计摘要和 Markdown 报告。
  • 生成稳定、可复现的自动诊断。
  • 可选调用外部 LLM,把统计上下文扩写成专家分析段落。

当前仓库默认携带的 config/phase_map.yaml 和部分诊断规则来自 UMDK FusedDeepMoe trace 的实践经验。因此,默认配置对 FusedDeepMoe 最友好;如果要分析其他来源的 trace,应替换或扩展 phase/category 映射配置,并逐步沉淀对应领域的诊断规则。

Agent 执行原则

执行本 skill 时,agent 不应把文档中的示例路径当成固定输入。应先从用户请求或当前工作区中确认以下上下文,并把它们替换到命令中:

  • TRACE_JSON:必需,用户要分析的 trace 文件。
  • OUTPUT_DIR:必需或由 agent 选择,建议按本次任务命名,例如 output/<case_name>
  • PHASE_MAP:可选,phase/category 映射配置。若用户指定算子或已有对应配置,应使用对应配置;否则使用默认 config/phase_map.yaml
  • SOURCE_ROOT:可选,算子源码工程目录,例如某个 UMDK 工程。当前 CLI 尚未消费该参数,但 agent 可以用它阅读源码、理解打点语义和辅助维护 phase map。
  • OPERATOR:可选,用户指定的算子名,例如 fused_deep_moe。当前 CLI 尚未消费该参数,但 agent 应用它选择或维护对应的 phase/category 规则和诊断上下文。

如果用户只提供 trace.json,按 trace-only 模式分析。如果用户同时提供源码目录和算子名,agent 应先阅读相关源码打点,再决定是否需要补充或调整 PHASE_MAP

执行命令

<ASCEND_MOE_OPTIMIZER_SKILL> 目录下执行(以下 <ASCEND_MOE_OPTIMIZER_SKILL> 含义见「脚本位置」):

Read the full file on GitHub · 218 lines

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. 5d ago First seen · 218 lines · 115 tokens per session scan A 5ff28d84022a

Subscribe to this mod's changes

ascend-moe-optimizer-trace-analyzer is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,102 stars, last pushed 13d ago), licensed Apache-2.0. It adds 115 tokens to every session and 3,175 once invoked, about $0.0006 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 2026-09-03.

Related

Other skills, from other repositories

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens

adk-debug

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…

google/adk-python · 191 tokens

claw-admin

Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.

x-cmd/x-cmd · 48 tokens

session-investigator

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…

evalstate/fast-agent · 68 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

optimize

Review code for efficiency and performance. Triggered by "/optimize" when user wants to identify bottlenecks or improve performance.

x-cmd/x-cmd · 29 tokens