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-sac-yologit 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-sac-yolo)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-sac-yolo"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-sac-yolo/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-sac-yolo"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-sac-yolo.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 Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.02304 |
| Opus 5 | $0.00032 | $0.01152 |
| Sonnet 5 | $0.00013 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
huawei-cloud-sac-yolo 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s http://<EIP>:8001` returns 200 How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud YOLO Training Platform
Overview
Deploy the "Quickly Build YOLO Visual Model Training Platform" solution end-to-end on Huawei Cloud. The platform provides GPU-accelerated ECS for YOLO model training, with full infrastructure provisioning via Terraform.
Architecture: ECS (GPU, P2s/Pi2) and VPC and Subnet and Security Group (ICMP/SSH/HTTP) and EIP (300 Mbit/s) and EVS (100 GB system + 500 GB data) and CBR (backup vault + policy). Cloud-init installs Docker and launches the YOLO container on GPU.
Tool chain: Playwright CLI (solution info extraction) + Python 3.8+ (helper scripts) + Terraform 1.15.4+ (declarative deployment). No KooCLI — all resource operations through Terraform.
Prerequisites
- Python 3.8+, Playwright CLI, Terraform 1.15.4+ — see CLI Installation Guide
- Huawei Cloud AK/SK via environment variables (
HW_ACCESS_KEY,HW_SECRET_KEY); if not set, prompt user to manually editterraform.auto.tfvars.jsonto fill in AK/SK - IAM user with sufficient permissions or
rf_admin_trustagency — see IAM Policies
Security
- 🚫 Never expose AK/SK in conversation or output
- 🚫 Never ask user to type AK/SK in chat
- ✅ Prefer IAM users over primary account
- ✅ Modification ops (
apply,destroy) require explicit user confirmation
Core Commands
Placeholder values (see Parameters for per-OS resolution):
| Placeholder | Linux / macOS | Windows |
|---|---|---|
<python> |
python3 |
python |
<script_dir> |
./scripts |
./scripts |
<temp_dir> |
/tmp |
$env:TEMP |
# 1. Extract solution info
<python> <script_dir>/extract_sac_deploy_info.py \
--url "https://www.huaweicloud.com/solution/implementations/quickly-build-a-yolo-training-platform.html" \
--out <temp_dir>/sac_selected.json
# 2. Download and normalize template
<python> <script_dir>/download_tf_template_file.py \
--url "https://documentation-samples.obs.cn-north-4.myhuaweicloud.com/solution-as-code-publicbucket/solution-as-code-moudle/quickly-build-a-yolo-training-platform/quickly-build-a-yolo-training-platform.tf" \
--out-dir <temp_dir>/yolo-workdir
<python> <script_dir>/normalize_tf_providers.py <temp_dir>/yolo-workdir \
--region "cn-north-4"
# 3. List variables for review
<python> <script_dir>/list_tf_variables.py <temp_dir>/yolo-workdir
# 4. Deploy
terraform init
terraform plan
# ⛔ STOP — Review the plan output above. Do NOT auto-apply.
# Confirm with the user (AskUserQuestion or equivalent) before proceeding.
# Only after explicit user confirmation:
terraform apply
# 5. Add YOLO UI security group rule
# Prompt user to manually add an ingress rule for TCP port 8001
# via Huawei Cloud console (VPC > Security Groups > Add Rule).
# Use restricted CIDR — do NOT open to all addresses.
# Wait for user confirmation before continuing.
# 6. Verify
terraform state list
terraform output -json
# 7. Cleanup
terraform destroy
What ships with it
13 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.
- demo/example-input.json 478 B
- references/acceptance-criteria.md 1.5 KB
- references/cli-installation-guide.md 1.7 KB
- references/iam-policies.md 4.8 KB
- references/related-commands.md 2.2 KB
- references/verification-method.md 1.7 KB
- scripts/download_tf_template_file.py 2.1 KB runs code
- scripts/extract_sac_deploy_info.py 8.6 KB runs code
- scripts/list_tf_variables.py 2.9 KB runs code
- scripts/normalize_tf_providers.py 10 KB runs code
- scripts/playwright_utils.py 5.2 KB runs code
- scripts/templates/extract_sac_deploy_info.js 5.1 KB runs code
- templates/terraform.tfvars.template 320 B
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 First seen · 228 lines · 64 tokens per session scan A 5bfbae76cf5a
huawei-cloud-sac-yolo is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 2,304 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
dnanexus-integration
DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
modal-compute
Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman research workflow needs burst remote GPU compute and the Modal CLI is available.
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.