SKILLEMALL.ai
GitHub ↗ RU Sign in

BB huawei-cloud-modelarts-training-diagnosis

Huawei Cloud ModelArts training job fault diagnosis skill. Uses hcloud CLI to call ModelArts training job log/event APIs, analyzes training job failures/timeouts/stuck jobs, locates customer training code issues, and provides diagnosis conclusions with fix suggestions and confidence levels. Scenarios: training job failure (status.phase=Failed), timeout (Timeout), abnormal (Abnormal), stuck jobs. Triggers: training job failure, training job timeout, training job stuck, ModelArts training diagnosis, 训练任务失败排查, 训练作业异常分析.

ClawHub Agent Skills author: huaweiclouddev-dev v1.0.1 MIT-0 10 files body ≈ 3 367 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

Huawei Cloud ModelArts training job fault diagnosis skill.

As a process B 75/100 · Nearly there — weak spots: when it triggers, running it twice

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
75
Quality 40%
79
Run on models
none yet
Process rating
B
75/100
Nearly there
When it triggers w 12
20
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: huawei-cloud-modelarts-training-diagnosis (ClawHub)

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:49
    Privilege escalation / world-writable permissions
    sudo mv hcloud /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:54
    Privilege escalation / world-writable permissions
    sudo mv hcloud /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:73
    Privilege escalation / world-writable permissions
    sudo mv hcloud /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:78
    Privilege escalation / world-writable permissions
    sudo mv hcloud /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:157
    Privilege escalation / world-writable permissions
    sudo bash ./hcloud_install.sh

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 75/100

  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 79 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3367 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 522: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 79 items
  • +3Output format is stated explicitly
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (8 of 8)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
The skill is mainly a read-only cloud training diagnostic tool, but its setup and cleanup guidance includes risky shell commands and its account-wide discovery is under-scoped.
LLM: suspicious (high) · 12 Aug 2026