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-modelarts-training-managementgit 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-modelarts-training-management)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-modelarts-training-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-modelarts-training-management/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-modelarts-training-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-modelarts-training-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00163 | $0.04820 |
| Opus 5 | $0.00081 | $0.02410 |
| Sonnet 5 | $0.00033 | $0.00964 |
| Haiku 4.5 | $0.00016 | $0.00482 |
Grade A, and why
huawei-cloud-modelarts-training-management 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 9d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud ModelArts Training Management
Full lifecycle management for ModelArts training jobs and related resources via hcloud CLI — 52 API interfaces across 8 functional domains.
Overview
This skill enables users to manage Huawei Cloud ModelArts training jobs and related resources through the hcloud CLI. It covers the complete training lifecycle including training job CRUD, algorithm management, training experiments, auto search (hyperparameter tuning), model import, and training image save.
Architecture
User Request → Agent → hcloud ModelArts <Operation> --cli-region={region} [--params] → Huawei Cloud ModelArts API
Applicable Scenarios
- Training Job Management: Create, list, show, stop, delete training jobs; query logs, metrics, engines, flavors, quotas
- Algorithm Management: Create, list, show, update, delete training algorithms; publish to gallery
- Training Job Tags: Create, show, delete tags for training jobs
- Training Experiments: Create, list, show, update, delete, check training experiments
- Training Job Events: Query job events, stages, tasks; list system events and scheduled events
- Model Import: Import, list, show, delete AI models; create ModelArts agency
- Auto Search: Query hyperparameter search trials, parameters analysis, yaml templates
- Training Image Save: Create and query training job image save tasks
Prerequisites
- hcloud CLI installed and authenticated — Reference: https://support.huaweicloud.com/qs-hcli/hcli_02_003.html
- Huawei Cloud AK/SK configured via hcloud (see Security & Credential Check below)
- ModelArts service enabled in the target region
- IAM permissions — See references/iam-policies.md
Security & Credential Check
⚠️ CRITICAL: This section defines the agent's security boundary. Follow it strictly.
🔒 Security Rules (MANDATORY)
- 🚫 NEVER read, echo, or print AK/SK values (e.g.,
cat ~/.hcloud/config.json,echo $HW_ACCESS_KEYis FORBIDDEN) - 🚫 NEVER read or cat credential files such as
~/.hcloud/config.jsonor any file that may contain secrets - 🚫 NEVER ask the user to input AK/SK directly in the conversation or command line
- 🚫 NEVER execute
hcloud configure set --cli-access-key=... --cli-secret-key=...— credential configuration is the user's responsibility, done outside the agent session - 🚫 NEVER pass
--cli-access-key/--cli-secret-keyon every API call — they will be exposed in process listings (ps aux) for the entire request duration - ✅ ALWAYS use
hcloud configure listto check credential status (presence check only, not values) - ✅ If no valid profile exists, STOP and instruct the user to configure credentials outside this session
- ✅ Recommend using IAM user with minimal permissions instead of main account
What ships with it
10 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 3.1 KB
- references/api-paths.md 6.0 KB
- references/cli-command-examples.md 20 KB
- references/cli-installation-guide.md 2.2 KB
- references/dataflow-diagram.md 3.6 KB
- references/iam-policies.md 6.1 KB
- references/known-issues.md 13 KB
- references/pricing-inquiry.md 10 KB
- references/verification-method.md 7.0 KB
- scripts/query-pricing.sh 8.2 KB runs code
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.
- 9d ago Changed · +200 lines a8c75dba2361
- 12d ago First seen · 187 lines · 163 tokens per session scan A 1f48e79a7cc7
huawei-cloud-modelarts-training-management is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 4,820 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
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).