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-deployment-task-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-deployment-task-management)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-deployment-task-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-deployment-task-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-deployment-task-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-deployment-task-management.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 | $0.00202 | $0.05658 |
| Opus 5 | $0.00101 | $0.02829 |
| Sonnet 5 | $0.00040 | $0.01132 |
| Haiku 4.5 | $0.00020 | $0.00566 |
Grade A, and why
huawei-cloud-deployment-task-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 today.
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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud CloudDeploy (CodeArts Deploy)
Overview
This skill operates Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) through the hcloud CLI.
CloudDeploy automates application deployment to ECS/BMS/CCI/Kubernetes and other targets, pulling
artifacts (default source: OBS) and running deployment tasks created from templates. The skill covers:
| Category | Capabilities |
|---|---|
| Query | List deploy applications (huawei_list_clouddeploy_apps), list deployment tasks (huawei_list_clouddeploy_tasks), get task detail (huawei_get_clouddeploy_task) |
| Analyze | Deployment failure root cause (huawei_analyze_clouddeploy_failure — agent offline/timeout/missing artifact/permission), OBS artifact link verification (huawei_analyze_clouddeploy_artifact) |
| Manage | Create application (huawei_create_clouddeploy_app), create deployment task referencing an app (huawei_create_clouddeploy_task), start deployment (huawei_start_clouddeploy_task), delete deployment task (huawei_delete_clouddeploy_task) |
Always run
hcloud CodeArtsDeploy <Operation> --cli-region={region} --helpbefore constructing a command to discover the exact parameter names and required flags for the current KooCLI version. Do not answer from general knowledge — follow the procedures in this document.
Critical Warnings
| Trap | Why |
|---|---|
| Flyway SQL dialect mismatch (H2 dev → MySQL prod) | Spring Boot apps commonly develop with an H2 in-memory DB and deploy to RDS MySQL. Flyway migrations written with H2-specific syntax (DATEADD, CHARACTER_LENGTH, BOOLEAN) silently pass on H2 but fail on MySQL. Before deploying, audit V*__*.sql migration files: replace DATEADD with DATE_ADD, BOOLEAN with TINYINT(1), and drop characterEncoding=utf8mb4 from the Spring Boot datasource URL (RDS sets charset at instance level). Enable Flyway.validate-on-migrate=true in CI to catch dialect issues early. |
Service name is CodeArtsDeploy, not CloudDeploy |
hcloud CloudDeploy <op> reports "Unsupported service" (KooCLI 7.2.12). The real service name is CodeArtsDeploy (metadata directory codeartsdeploy). Always verify with hcloud CodeArtsDeploy ListAllApp --cli-region=cn-north-4 --help. |
| Deployment hosts need the agent installed | Target hosts (ECS/BMS/CCI) must have the CloudDeploy agent (ICAgent-style host agent) installed and online before a task can run. Check host status before starting a task — an offline agent is the #1 cause of "host offline / execution failed" results. |
| Task must reference an application | Create the deploy application first, then create the deployment task. A task without an application cannot be created or started (CreateDeployTaskByTemplate requires the app's project and template). |
| Artifact source defaults to OBS | Most deployment tasks pull artifacts from OBS buckets. Verify the bucket and object path exist and the service account has GetObject permission — otherwise the task fails at artifact download. |
| Parallel deployments may conflict | Multiple tasks deploying to the same host/group concurrently can conflict or deadlock. Use deployment groups, host locking, or serialized pipelines; check for an already running task before starting another. |
| Security baseline | Use IAM roles for deployment permissions, verify artifact integrity (checksum) before deploy, and never store plaintext credentials (AK/SK, DB passwords) in deployment scripts or task parameters (--params with type=encrypt exists for secrets). |
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.
- .markdownlint.json 358 B
- references/acceptance-criteria.md 3.6 KB
- references/cli-installation-guide.md 3.4 KB
- references/dataflow-diagram.md 2.6 KB
- references/iam-policies.md 3.4 KB
- references/test-report.md 3.8 KB
- references/verification-method.md 3.9 KB
- scripts/skill_quality_sdk.py 20 KB runs code
- templates/test-defaults.json 4.9 KB
- templates/test-vars.json 3.8 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.
- today First seen · 406 lines · 202 tokens per session scan A 793c9e4dd599
huawei-cloud-deployment-task-management is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 202 tokens to every session and 5,658 once invoked, about $0.0010 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 2026-09-12.
Other skills, from other repositories
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
securing-helm-chart-deployments
Secure Helm chart deployments by validating chart integrity, scanning templates for misconfigurations, and enforcing security contexts in Kubernetes releases.
pinme-r2
Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.
i18n-lookup
Look up Zeabur platform UI term translations from the dashboard i18n files. Use when writing or reviewing docs that reference UI elements (button labels, tab names, menu items) to ensure docs match the actual platform translations.
github-pages-deployer
Deploy affiliate content to GitHub Pages for free hosting. Triggers on: "deploy to GitHub Pages", "host on GitHub Pages", "free hosting for my affiliate site", "push to GitHub Pages", "GitHub Pages setup", "deploy my landing page to GitHub", "host my bio link on GitHub", "free affiliate website hosting", "github pages…