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-mrs-host-alarm-diagnosegit 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-mrs-host-alarm-diagnose)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-alarm-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-alarm-diagnose/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-mrs-host-alarm-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-alarm-diagnose.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 100 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 | $0.00207 | $0.06592 |
| Opus 5.5 | $0.00083 | $0.02637 |
| Sonnet 5.5 | $0.00041 | $0.01318 |
| Haiku 4.5 | $0.00021 | $0.00659 |
Grade A, and why
huawei-cloud-mrs-host-alarm-diagnose 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud MRS Alarm Diagnosis Skill
Overview
This skill diagnoses Huawei Cloud MRS (MapReduce Service) cluster alarms. Given alarm information (alarm ID, alarm name, occurrence time, cluster ID, node, related service/role), it locates the root cause and outputs repair steps and a verification method.
Architecture: Caller (Agent) → check_api_mode.py (Python, scripts/) determines the API mode → either lakewatch_api_client.py → LakeWatch API → MRS cluster (node resource data, logs, MRS Manager proxy) or manager_api_client.py → MRS Manager REST API (28443). Per-alarm knowledge base (alarms/<alarm_id>.md in lakewatch mode, alarm_manager/<alarm_id>.md in manager mode) drives the diagnosis flow.
Note on language: This SKILL.md, the documents under
references/, and the per-alarm knowledge base underalarms/andalarm_manager/are all written in English per the repository spec. Commands and code blocks are English throughout.
Applicable Scenarios:
- An MRS cluster raises an alarm and the root cause must be located
- An on-call engineer needs guided, per-alarm diagnostic steps
- Alarm triage where an alarm ID is provided
Typical Use Cases:
- "MRS集群收到12089告警，帮忙诊断一下"
- "PMS进程异常告警，告警ID 12007，集群ID xxx，帮我定位原因"
- "Audit log dump failed alarm 12001, diagnose the root cause"
- "节点间网络互通异常，告警ID 12089，发生时间 2026/06/11 16:00:32 GMT+08:00"
Critical Constraints
Important constraints:
- Read-only: This skill only runs information-gathering commands (view logs, query status). It MUST NOT run any start/stop, modify, or delete operations.
- User confirmation for repair: The skill only provides executable repair steps; it MUST NOT directly execute any repair operation. All repair actions require user confirmation.
- Strict execution: Diagnose strictly according to the per-alarm knowledge base content. Fabricating diagnostic commands outside the knowledge base is prohibited.
Prerequisites
1. Python Requirements
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.
- alarm_manager/12001.md 15 KB
- alarm_manager/12006.md 5.4 KB
- alarm_manager/12007.md 3.3 KB
- alarm_manager/12007/DBService.md 13 KB
- alarm_manager/12007/KrbServer.md 12 KB
- alarm_manager/12007/LdapServer.md 12 KB
- alarm_manager/12016.md 25 KB
- alarm_manager/12017.md 5.1 KB
- alarm_manager/12018.md 4.5 KB
- alarm_manager/12027.md 4.3 KB
- alarm_manager/12033.md 4.4 KB
- alarm_manager/12041.md 5.8 KB
- alarm_manager/12042.md 4.7 KB
- alarm_manager/12052.md 5.0 KB
- alarm_manager/12053.md 3.3 KB
- alarm_manager/12061.md 4.5 KB
- alarm_manager/12063.md 20 KB
- alarm_manager/12067.md 5.6 KB
- alarm_manager/12068.md 5.6 KB
- alarm_manager/12069.md 5.6 KB
- alarm_manager/12070.md 5.8 KB
- alarms/12001.md 14 KB
- alarms/12006.md 7.8 KB
- alarms/12007.md 13 KB
- alarms/12007/DBService.md 12 KB
- alarms/12007/KrbServer.md 12 KB
- alarms/12007/LdapServer.md 13 KB
- alarms/12016.md 27 KB
- alarms/12017.md 4.6 KB
- alarms/12018.md 438 B
- alarms/12027.md 440 B
- alarms/12033.md 17 KB
- alarms/12041.md 11 KB
- alarms/12042.md 12 KB
- alarms/12052.md 3.8 KB
- alarms/12053.md 3.8 KB
- alarms/12061.md 3.9 KB
- alarms/12063.md 19 KB
- alarms/12067.md 7.5 KB
- alarms/12068.md 13 KB
- alarms/12069.md 6.9 KB
- alarms/12070.md 8.4 KB
- references/acceptance-criteria.md 5.6 KB
- references/cli-installation-guide.md 8.1 KB
- references/iam-policies.md 5.8 KB
- references/lakewatch-api-client.md 11 KB
- references/manager-api-client.md 10 KB
- references/related-commands.md 10 KB
- references/verification-method.md 7.0 KB
- scripts/check_api_mode.py 2.2 KB runs code
- scripts/lakewatch_api_client.py 20 KB runs code
- scripts/lakewatch_api_config.yaml 6.9 KB
- scripts/manager_api_apis/alarm.yaml 9.4 KB
- scripts/manager_api_apis/audit.yaml 1.4 KB
- scripts/manager_api_apis/cluster.yaml 2.7 KB
- scripts/manager_api_apis/command.yaml 2.2 KB
- scripts/manager_api_apis/health_check.yaml 1.7 KB
- scripts/manager_api_apis/host.yaml 5.0 KB
- scripts/manager_api_apis/instance.yaml 2.8 KB
- scripts/manager_api_apis/log.yaml 5.8 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.
- 1mo ago Changed · +123 lines · +40 tokens per session a66f1117b7fa
- 1mo ago First seen · 348 lines · 167 tokens per session scan A 64158bb52840
huawei-cloud-mrs-host-alarm-diagnose is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 207 tokens to every session and 6,592 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
seedance-troubleshoot
This skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.
k8s-service-path
Trace the Kubernetes service path — Service to selector to pods to EndpointSlices to readiness, plus Ingress routing. Use when a service is getting no traffic, an ingress is not routing, or someone asks why a workload is unreachable inside a cluster.
k8s-workload-inventory
List Kubernetes workloads and namespaces — pods with their node, phase and readiness, plus events. Use when asked what is running, where it is running, what is failing, or for a general inventory of a cluster.
k8s-dns-failure
A guide for diagnosing and fixing DNS problems in Kubernetes, a system for running containerised applications. It focuses on CoreDNS, the component that helps services find one another and reach external services.
seedance-troubleshoot
This skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.
mpm-doctor
Run diagnostic checks on Claude MPM installation.