AB huawei-cloud-mrs-host-fault-diagnose
Huawei Cloud MRS cluster fault diagnosis skill. Diagnoses service faults, instance faults, and host faults through progressive root cause localization: quick log scan first, host troubleshooting when host issues are found, detailed investigation when no conclusion is reached. Driven by the built-in LakeWatch API client and the per-component knowledge base under components/. No commands outside the knowledge base are fabricated. Applicable to MRS fault diagnosis and root cause localization scenarios where a service name or node name is provided. Trigger words: "故障诊断", "故障定位", "fault diagnosis", "fault diagnose", "MRS故障", "服务故障", "实例故障", "主机故障", "集群排查", "集群诊断", "启动失败", "停止异常", "KrbServer故障", "DBService故障", "fault troubleshooting"
Huawei Cloud MRS cluster fault diagnosis skill.
As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: bashallowed-tools: bash
Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5482 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "trigger" - note
frontmatter-keyunknown frontmatter key "input_schema" - note
frontmatter-keyunknown frontmatter key "output_schema"
Process rating: all ten parameters 70/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5482 tokens
- 85Steps. 48 steps, 3 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 737: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 48 items
- +3Output format is stated explicitly
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.