vllm-ascend-workspace: Skill for Claude Code

.agents/skills/ascend-profiling-collection/SKILL.md

ascend-profiling-collection is a skill for Claude Code, Codex from maoxx241/vllm-ascend-workspace. It costs 131 tokens per session (3,045 once invoked), scanned A, original, MIT.

A workflow for collecting one performance trace from an Ascend NPU, a processor used for AI workloads, with the PyTorch profiler. It starts a profiled vLLM service, runs a workload, saves the profiling data, checks that the output exists, and writes a manifest.

In plain words
What is it for?
Capturing traces for a chosen model, mode, tensor or data parallel setup, and workload so a separate analysis workflow can inspect the results.
Why use it?
It standardizes the steps needed to capture a usable profiling case and confirms that the device-side data was actually collected.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is maoxx241/vllm-ascend-workspace's own configuration. It tells Claude Code and Codex how to work on vllm-ascend-workspace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vllm-ascend-workspace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/ascend-profiling-collection/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspace

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-profiling-collection

README.md
[![agentmods](https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection/github.svg)](https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection)
Your own site
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection/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-profiling-collection

Your own site · 80×15
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/ascend-profiling-collection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,045 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 $0.00131 $0.03045
Opus 5 $0.00066 $0.01522
Sonnet 5 $0.00026 $0.00609
Haiku 4.5 $0.00013 $0.00304

Measured 7d ago against content hash 25f3b1681e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ascend-profiling-collection 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 7d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_common.py, scripts/collect_torch_profile_case.py, scripts/profile_control.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.

.agents/skills/ascend-profiling-collection/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ascend Profiling Collection

Collect one torch-profiler case on a workspace-managed remote Ascend NPU container.

Remote substrate rule: use .remote-dev remote tools for ad hoc remote read/edit/bash/search/patch work around profile setup and output inspection. Use this skill for the domain collection workflow and keep its scripts as the compatibility backend for managed VAWS sessions.

This skill is only about collection: start a profiled service, bracket a workload with /start_profile and /stop_profile, run torch_npu.profiler.profiler.analyse(...), verify the device-side data actually landed, and write a manifest. Interpreting the resulting kernel_details.csv is a separate concern owned by the analysis skill.

Use this skill when

  • the user asks to collect / capture an Ascend torch-profiler trace for a specific config
  • another skill (the analysis skill) needs a fresh profiling root with verified outputs
  • the user wants to reproduce an existing root with a new model / mode / TP / DP

Do not use this skill when

  • the task is performance benchmarking only — use vllm-ascend-benchmark
  • the task is HBM / memory analysis — use ascend-memory-profiling
  • the task is analysing an already-collected profiling root (no need to re-collect)
  • the machine is not yet ready in inventory — use machine-management

Boundary with other skills

Skill Owns This skill uses it for
vllm-ascend-serving Service lifecycle, --profiler-config passthrough serve_start.py / serve_stop.py only; serving is agnostic to the profiler window
remote-code-parity Local-to-container code sync Implicit — invoked by serve_start.py
vllm-ascend-benchmark vllm bench serve performance numbers Not used; benchmark skill must not learn the profiler control plane
ascend-memory-profiling HBM attribution via msprof Independent; not invoked

/start_profile and /stop_profile exist because of profiling, so the control-plane client lives here, not in vllm-ascend-serving.

Read the full file on GitHub · 194 lines

Files

What ships with it

7 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. 7d ago Changed · +1 lines 25f3b1681e11
  2. 11d ago First seen · 193 lines · 131 tokens per session scan A 7bb6c9d78cc0

Subscribe to this mod's changes

ascend-profiling-collection is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 6d ago), licensed MIT. It adds 131 tokens to every session and 3,045 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