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.
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-ascend-op-mfu-calculatorgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote 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.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ascend-op-mfu-calculator)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ascend-op-mfu-calculator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ascend-op-mfu-calculator/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.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ascend-op-mfu-calculator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-ascend-op-mfu-calculator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00152 | $0.00850 |
| Opus 5 | $0.00076 | $0.00425 |
| Sonnet 5 | $0.00030 | $0.00170 |
| Haiku 4.5 | $0.00015 | $0.00085 |
Grade A, and why
huawei-cloud-ascend-op-mfu-calculator 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.
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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Ascend Operator MFU Calculator
Overview
This skill calculates MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process.
Architecture: Input Validation → FLOPs Calculation → Achieved TFLOPs/s → MFU Calculation → Result Analysis
Related Skills:
huawei-cloud-ascend-profiler-db-explorer- Profiling data analysis for operator performance data
Prerequisites
- Python 3.8+ installed
- Basic understanding of FLOPs calculation concepts
Usage Scenarios
Typical Problem Scenarios:
- Evaluating how well an operator utilizes Ascend NPU compute power
- Comparing performance of different operator implementations
- Identifying optimization opportunities for matrix operations
Typical User Utterances:
- "Calculate MFU for my GEMM operator"
- "What's the machine FLOP utilization for FlashAttention?"
- "Analyze my matmul operator performance efficiency"
Workflow
- Input Collection: Gather operator parameters (matrix dimensions, data types, execution time)
- FLOPs Calculation: Compute theoretical FLOPs for the operation
- Achieved Performance: Calculate achieved TFLOPs/s from execution time
- MFU Calculation: Apply formula MFU = Achieved FLOPs / Peak FLOPs
- Result Analysis: Provide interpretation and optimization suggestions
MFU Calculation Formula
MFU = (Achieved FLOPs / Peak FLOPs) × 100%
Where:
- Achieved FLOPs = Operation FLOPs / Execution Time
- Peak FLOPs = Hardware-specific peak performance (e.g., Ascend 910B: 256 TFLOPs for FP16)
Reference Documents
| Document | Description |
|---|---|
| Ascend 910B Series Technical Specifications | Official Ascend 910B series product specifications |
| MFU Calculation Methodology | Detailed MFU calculation formulas and examples |
| FlashAttention Technical Paper | Original FlashAttention research paper |
What ships with it
2 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.
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.
- 12d ago First seen · 83 lines · 152 tokens per session scan A b395d703d9e0
huawei-cloud-ascend-op-mfu-calculator is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 850 once invoked, about $0.0008 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.
Other skills, from other repositories
ai-for-science-diffsbdd
A migration skill for moving an equivariant diffusion model for structure-based drug design from NVIDIA CUDA to Huawei Ascend NPUs. It covers setup, dependency installation, compiling torchscatter, code adaptation, and new-molecule inference checks.
ai-for-science-generator
A migration skill for moving DNA-sequence generation models from NVIDIA CUDA to Huawei Ascend NPUs. It covers setup, dependencies, code changes, multiprocessing, and sequence-recovery checks for models built with Hugging Face Transformers.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…