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-solution-opsgit 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-solution-ops)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-solution-ops"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-solution-ops/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-solution-ops"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-solution-ops.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 | $0.00081 | $0.06903 |
| Opus 5.5 | $0.00032 | $0.02761 |
| Sonnet 5.5 | $0.00016 | $0.01381 |
| Haiku 4.5 | $0.00008 | $0.00690 |
Grade A, and why
huawei-cloud-solution-ops 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 1mo 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Agent Skill
概述(核心定位)
- 单一 skill 覆盖华为云上云、用云、管云场景,默认以租户体验和可验证闭环为中心。
- 云资源默认优先使用
hcloud:它更适合 Agent 做 operation 发现、一次性查询/变更、dry-run 和回读。Agent 仍根据任务意图、运行时能力和证据质量自行选择hcloud、SDK 或 Terraform,详细决策见references/backend-selection.md。 - SDK 是受支持的程序化后端,适合类型化请求、复杂 body、分页/并发、结构化异常,或 hcloud 当前确有覆盖/解析障碍的任务。
hcloud_sdk_readonly.py的 allowlist 只约束该便捷 runner,不限制 Agent 编写任务专用 SDK 代码。 - Terraform 由 IaC 意图触发,用于可重复创建、环境复制、长期纳管、import 或 drift;它不是 hcloud 失败后的普通兜底。前置发现和后置验证优先用 hcloud,也允许等价 SDK/API、data source 和业务探测证据。
- 高频脚本是对上述后端的可选封装,不是第四种后端。脚本覆盖目标时优先复用其版本选择、参数校验、脱敏、输出收敛和错误分类;未覆盖的长尾任务可直接使用有证据的 hcloud、官方 SDK 或 Terraform。
- 文档中的
python3 scripts/<name>.py ...假设当前目录是 Skill 根目录。当前目录不确定时,用bin/hcloud-skill <name> ...;Windows 用bin/hcloud-skill.cmd <name> ...。这个稳定入口只定位当前 Skill 自带脚本并原样传递参数,不替 Agent 选择服务、operation、参数或调用顺序。 - 面向 Agent 的脚本成功结果至少提供布尔
success;默认最终 stdout 是 JSON object。大结果或已选择的结构化入口可进一步提供huaweicloud_skill_public_result_v1artifact 回执,但小型 planner/inspector 不需要机械增加--output-file。显式 Markdown、shell-command 和逐项图片进度模式见references/public-script-contract.md。 hcloud不可用不等于整个 Skill 不可用;如果 SDK 或 Terraform 符合任务且运行条件完备,可以继续。无论使用哪个后端,没有真实执行和回读证据时都不能宣称已经查询、修改或完成。- MaaS 是 API-first 能力面。模型调用使用 MaaS API Key;用量统计是治理查询,按本地 AK/SK 签名规划处理。不要让用户在对话里粘贴密钥。
- 目标不是背命令,而是稳定完成:识别上下文 -> 发现资源/operation -> 构造安全命令 -> 查询或变更 -> 回读验证 -> 处理错误。
什么时候使用
优先在这些场景使用本 skill:
- 用户提到华为云、
hcloud、KooCLI、CLI、命令行、云资源查询、创建、变更、排障或治理。 - 用户需要查看 service/operation、构造
--cli-jsonInput、使用--cli-query、--dryrun、--cli-waiter等 CLI 能力。 - 用户需要华为云认证、region/project、profile、meta cache、网络或输出格式排查。
- 用户明确需要 Terraform/IaC、MaaS 大模型/图像/视频,或华为云 Web/OBS/CDN/ECS 站点资产辅助。
不要把本 skill 当成非华为云的通用云知识问答、无证据 API 猜测器、自动 Terraform apply 器,或非华为模型服务兜底。
hcloud 命令应显式携带当前任务的区域,标准形态为:
hcloud <Service> <Operation>/<version> --cli-region=<region> <business-parameters>
全局服务确认不需要 region 时才可省略;跨区域任务不得依赖 profile 的隐式默认值。
跨服务和多轮任务
本 skill 用少量共享语义帮助不同服务场景保持目标、事实来源和完成口径一致,但它不是任务执行控制器。Agent 仍然负责理解现场情况,并自主选择或调整服务、工具、参数和操作次序。
What ships with it
60 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.
- bin/hcloud-skill 2.2 KB
- bin/hcloud-skill.cmd 497 B runs code
- examples/ecs-create-dryrun.md 2.2 KB
- examples/ecs-create-postpaid-servers.cli-jsonInput.json 747 B
- examples/ecs-create-servers-password.cli-jsonInput.json 778 B
- examples/ecs-create-servers.cli-jsonInput.json 687 B
- examples/eip-acceptance-closure.md 2.6 KB
- examples/README.md 3.0 KB
- examples/terraform/antiddos_stack/main.tf 980 B
- examples/terraform/antiddos_stack/outputs.tf 243 B
- examples/terraform/antiddos_stack/provider.tf 54 B
- examples/terraform/antiddos_stack/README.md 554 B
- examples/terraform/antiddos_stack/terraform.tfvars.example 263 B
- examples/terraform/antiddos_stack/variables.tf 1.2 KB
- examples/terraform/antiddos_stack/versions.tf 179 B
- examples/terraform/aom_stack/main.tf 1.4 KB
- examples/terraform/aom_stack/provider.tf 290 B
- examples/terraform/aom_stack/README.md 4.5 KB
- examples/terraform/aom_stack/terraform.tfvars.example 468 B
- examples/terraform/aom_stack/variables.tf 3.3 KB
- examples/terraform/apig_stack/main.tf 1.9 KB
- examples/terraform/apig_stack/outputs.tf 446 B
- examples/terraform/apig_stack/provider.tf 54 B
- examples/terraform/apig_stack/README.md 472 B
- examples/terraform/apig_stack/terraform.tfvars.example 314 B
- examples/terraform/apig_stack/variables.tf 1.3 KB
- examples/terraform/apig_stack/versions.tf 179 B
- examples/terraform/as_stack/main.tf 3.8 KB
- examples/terraform/as_stack/provider.tf 289 B
- examples/terraform/as_stack/README.md 5.1 KB
- examples/terraform/as_stack/terraform.tfvars.example 763 B
- examples/terraform/as_stack/variables.tf 5.2 KB
- examples/terraform/bms_stack/main.tf 2.4 KB
- examples/terraform/bms_stack/provider.tf 289 B
- examples/terraform/bms_stack/README.md 2.7 KB
- examples/terraform/bms_stack/terraform.tfvars.example 350 B
- examples/terraform/bms_stack/variables.tf 2.6 KB
- examples/terraform/cbh_stack/main.tf 1.7 KB
- examples/terraform/cbh_stack/provider.tf 290 B
- examples/terraform/cbh_stack/README.md 2.6 KB
- examples/terraform/cbh_stack/terraform.tfvars.example 305 B
- examples/terraform/cbh_stack/variables.tf 2.2 KB
- examples/terraform/cbr_stack/main.tf 2.1 KB
- examples/terraform/cbr_stack/outputs.tf 385 B
- examples/terraform/cbr_stack/provider.tf 54 B
- examples/terraform/cbr_stack/README.md 568 B
- examples/terraform/cbr_stack/terraform.tfvars.example 343 B
- examples/terraform/cbr_stack/variables.tf 2.3 KB
- examples/terraform/cbr_stack/versions.tf 179 B
- examples/terraform/cc_stack/main.tf 503 B
- examples/terraform/cc_stack/provider.tf 334 B
- examples/terraform/cc_stack/README.md 2.2 KB
- examples/terraform/cc_stack/terraform.tfvars.example 240 B
- examples/terraform/cc_stack/variables.tf 1.5 KB
- examples/terraform/cce_addon_stack/main.tf 4.3 KB
- examples/terraform/cce_addon_stack/provider.tf 54 B
- examples/terraform/cce_addon_stack/README.md 1.5 KB
- examples/terraform/cce_addon_stack/terraform.tfvars.example 172 B
- examples/terraform/cce_addon_stack/variables.tf 968 B
- examples/terraform/cce_addon_stack/versions.tf 179 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.
- 1mo ago First seen · 171 lines · 81 tokens per session scan A 4205f2ded701
huawei-cloud-solution-ops is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 6,903 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-07.
Other skills, from other repositories
huawei-cloud-apig-instance-management
Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request throttling policies, signature keys, access control (ACL) policies, and public ingress EIP binding, plus read-only diagnosis of public…
huawei-cloud-deployment-task-management
Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) management, execution, and failure analysis using the KooCLI hcloud command-line client. Covers deploy application listing and creation, deployment task listing/detail/creation, task start, task deletion, deployment failure root-cause analysis (agent offline, timeout…
huawei-cloud-gaussdb-instance-management
A Huawei Cloud management and diagnosis tool for GaussDB, a distributed database service compatible with MySQL or based on openGauss. It covers instances, nodes, backups, databases, permissions, and configuration checks.
huawei-cloud-cts-trace-management
A Huawei Cloud CTS (Cloud Trace Service) management and audit tool. CTS records actions performed in cloud services so they can be searched and reviewed later.
huawei-cloud-dds-dcs-instance-management
Huawei Cloud DDS (Document Database Service) and DCS (Distributed Cache Service) unified management skill. Provides 16 operations across five capability domains: (1) Query — list/get DDS/DCS instances, DCS node info, DCS custom templates; (2) Analysis — analyze DDS deployment architecture and DCS security posture; (3)…
huawei-cloud-waf-aad-rule-management
A command-line skill for managing and diagnosing Huawei Cloud WAF and AAD protection. WAF is a web application firewall; AAD is protection against distributed denial-of-service attacks.