agentmods.dev

huawei-cloud-mrs-host-fault-diagnose

huawei-cloud-mrs-host-fault-diagnose is a skill for Claude Code from huaweicloud/huaweicloud-skills. It costs 188 tokens per session (6,170 once invoked), scanned A, original, MIT.

A diagnosis tool for Huawei Cloud MRS, a managed cluster service for big-data processing. It investigates service, instance, and host faults by scanning logs and progressively narrowing the likely cause.

In plain words
What is it for?
It is for diagnosing MRS service, node, and host failures, inspecting logs and resource data, and tracing how a lower-level fault affects higher-level services.
Why use it?
It helps move from a reported unhealthy service or machine to the underlying failure layer instead of checking every part manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

not rated 49repo +4 yesterday A scan SkillSpector: warn 188 tokens original MIT

Good fit It is for diagnosing MRS service, node, and host failures, inspecting logs and resource data, and tracing how a lower-level fault affects higher-level services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose
View source ↗ huaweicloud/huaweicloud-skills
Install

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.

Any agent
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-mrs-host-fault-diagnose
Clone the repo
git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for huawei-cloud-mrs-host-fault-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose/github.svg)](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose)
Your own site
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-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.

agentmods 80×15 button for huawei-cloud-mrs-host-fault-diagnose

Your own site · 80×15
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-mrs-host-fault-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 90
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00188 $0.06170
Opus 5 $0.00094 $0.03085
Sonnet 5 $0.00038 $0.01234
Haiku 4.5 $0.00019 $0.00617

Measured 9d ago against content hash babc50c91702, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

huawei-cloud-mrs-host-fault-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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/lakewatch_api_client.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/bigdata/mrs/huawei-cloud-mrs-host-fault-diagnose/SKILL.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Huawei Cloud MRS Host Fault Diagnosis Skill

Overview

This skill diagnoses Huawei Cloud MRS (MapReduce Service) cluster faults. Given a service name and/or node name, it progressively localizes the root cause: quick log scan first, host troubleshooting when host issues are found, detailed investigation when no conclusion is reached.

Architecture: Caller (Agent) -> lakewatch_api_client.py (Python, scripts/) -> LakeWatch API -> MRS cluster (node resource data, logs, MRS Manager proxy); per-component knowledge base (components/<service_name>.md) drives the diagnosis flow; three fault layers (host -> instance -> service) with propagation chain tracing.

Note on language: This SKILL.md and the documents under references/ are written in English per the repository spec. The knowledge base documents under fault_layer/, scenarios/, components/, and propagation.md are also in English. Commands and code blocks are English throughout.

Applicable Scenarios:

  • A service is reported unhealthy and the root cause must be localized
  • An instance is reported faulty on a specific node
  • A host is reported unreachable or abnormal
  • Progressive fault triage from quick scan to deep investigation

Typical Use Cases:

  • "KrbServer出问题了，帮忙诊断一下" (service fault, no node specified)
  • "8-5-225-6上的KrbServer挂了" (instance fault, service + node specified)
  • "8-5-225-6出问题了" (host fault, node only)
  • "MRS集群KrbServer启动失败，集群ID xxx"
  • "DBService停止异常，节点8-5-225-6"

Critical Constraints

Important constraints:

  1. Read-only: This skill only runs information-gathering commands (view logs, query status, collect resource data). It MUST NOT run any start/stop, modify, or delete operations.
  2. User confirmation for repair: The skill only provides executable repair suggestions; it MUST NOT directly execute any repair operation. All repair actions require user confirmation.
  3. Strict execution: Diagnose strictly according to the knowledge base content under this skill directory. Fabricating diagnostic commands outside the knowledge base is prohibited.

Read the full file on GitHub · 501 lines

Files

What ships with it

27 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.

Changes

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.

  1. 9d ago First seen · 501 lines · 188 tokens per session scan A babc50c91702

Subscribe to this mod's changes

huawei-cloud-mrs-host-fault-diagnose is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 188 tokens to every session and 6,170 once invoked, about $0.0009 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 2026-09-03.

Data and AIDebuggingdiagnosticsfaulthuawei-cloudmrstroubleshooting
Related

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.

Emily2040/seedance-2.0 · 56 tokens

mpm-doctor

Run diagnostic checks on Claude MPM installation.

bobmatnyc/claude-mpm · 13 tokens

systemlens-troubleshooting

Diagnose Windows slowness, crashes, storage, startup, driver, service, network, and peripheral problems using SystemLens read-only evidence. Use when a paired PC can supply relevant telemetry; do not use for changing the PC or for unrelated general Windows advice.

Quod-cmd/SystemLens · 59 tokens

debugging

Systematically diagnose and fix bugs using structured debugging techniques. Use when investigating errors, unexpected behavior, failing tests, or production issues.

asgarovf/locusai · 29 tokens

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.

1370998960-del/https-github.com-Emily2040-seedance-2.0 · 56 tokens

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.

LeoYeAI/seedance-skills · 56 tokens