AB huawei-cloud-mrs-host-alarm-diagnose
Huawei Cloud MRS cluster alarm diagnosis skill. Analyzes the root cause of an MRS alarm based on user-provided alarm information (alarm ID, alarm name, alarm details, occurrence time, node IP, related service and logs), then outputs the root cause, repair steps, and verification method. Diagnosis is driven by the built-in LakeWatch API client and the per-alarm knowledge base under alarms/. No commands outside the knowledge base are fabricated. Applicable to MRS alarm diagnosis and root cause localization scenarios where an alarm ID is provided. Trigger words: "告警诊断", "告警定位", "alarm diagnosis", "alarm diagnose", "MRS告警", "告警原因", "告警ID", "alarm ID", "root cause"
Huawei Cloud MRS cluster alarm diagnosis skill.
As a process B 78/100 · Nearly there — weak spots: when it triggers, 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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: bashallowed-tools: bash
-
low Dangerous commands
cmd-cron-mentionalarms/12016.md:442Mentions editing / listing crontab (quoted — discussed, not commanded)- Scheduled script investigation: `crontab -l` to view the omm user's scheduled tasks, confirm whether abnormal scripts are executing
quoted
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- 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 78/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 42 steps, 1 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
- 100Execution cost. Instruction body is 3854 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 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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 4 example trigger phrases
- +3Description length 668: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.