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-cloudrobo-model-workflowgit 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-cloudrobo-model-workflow)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cloudrobo-model-workflow"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cloudrobo-model-workflow/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-cloudrobo-model-workflow"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cloudrobo-model-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00156 | $0.07185 |
| Opus 5 | $0.00078 | $0.03592 |
| Sonnet 5 | $0.00031 | $0.01437 |
| Haiku 4.5 | $0.00016 | $0.00719 |
Grade A, and why
huawei-cloud-cloudrobo-model-workflow scanned grade A with 1 finding 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudRobo Model Development Orchestration Workflow
Orchestrate the pipeline: asset query → model training → inference deployment → real-robot evaluation → result output. Use CLI commands throughout; Python SDK is prohibited.
Windows / PowerShell: Examples use bash syntax. To run on Windows PowerShell:
- Flatten
\line continuations to a single line, or end lines with a backtick.- Set env vars with
$env:NAME="value"instead ofexport NAME="value".- Single-quoted JSON
'{"a":"b"}'works as-is.
Overview
Pipeline Stages
Stage 0: Use Case Parsing → Extract robot type + task, select model; parse dataset source
Stage 1: Asset Query & Dataset → Query model/algorithm/dataset assets; get default hyperparams and confirm; OpenPI model constructs data.rename_map
Stage 2: Model Training → CLI create-task creates training task, poll until complete
Stage 3: Inference Deployment → CLI infer create deploys inference service
Stage 4: Real-Robot Evaluation → CLI dispatch create-task dispatches task to real robot (session_id=workspace_id, no session creation needed)
Stage 5: Result Output → Output evaluation score and report
Execution Modes
| Mode | User Intent Example | Stages |
|---|---|---|
| Full pipeline | "用 so101 训练插笔任务并评测" | Stage 0→5 |
| Train+Deploy | "训练完帮我部署推理服务" | Stage 0→3 |
| Deploy+Eval | "我模型训练好了，帮我部署评测" | Stage 3→5 |
Stage dependencies cannot be skipped: Evaluation depends on inference service RUNNING, deployment depends on training FINISHED, training depends on asset info. When starting from an intermediate stage, user must provide preceding output parameters.
Skip-Stage Input Requirements
| Start Stage | User Must Provide | Prompt |
|---|---|---|
| Stage 2 | base_model_asset_id, dataset_asset_id |
"Please provide base model asset_id and dataset asset_id" |
| Stage 3 | output_model_asset_id, output_model_version_id |
"Please provide training output model asset_id and version_id" |
| Stage 4 | service_id |
"Please provide inference service service_id" |
What ships with it
11 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.
- references/acceptance-criteria.md 3.2 KB
- references/cli-installation-guide.md 2.8 KB
- references/constraints.md 6.4 KB
- references/dataflow-diagram.md 9.1 KB
- references/fault-recovery.md 4.2 KB
- references/iam-policies.md 3.7 KB
- references/model-ext-metadata.md 7.5 KB
- references/openpi-rename-map.md 5.6 KB
- references/pipeline-templates.md 9.7 KB
- references/robot-selection-guide.md 5.3 KB
- references/verification-method.md 5.5 KB
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.
- yesterday First seen · 555 lines · 156 tokens per session scan A 0ecdb59d84f6
huawei-cloud-cloudrobo-model-workflow is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 156 tokens to every session and 7,185 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
tao-validate-recipe-transfer
Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. Use this whenever someone wants to reproduce a CV paper, run a paper's repo on their own images, fine-tune a published…
atc-model-converter
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full…
diffusers-ascend-pipeline
A guide for running image and video generation pipelines on Huawei Ascend NPUs with the Diffusers library. Diffusers is a software library for using generative models, and the guide covers model pipelines, memory settings, LoRA adapters, and multi-card inference.
mle-workflow
Production ML engineering workflow — data contracts, reproducible training, evaluation gates, deployment, and monitoring. Use when building, reviewing, or hardening ML systems beyond notebooks.
lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.