AB huawei-cloud-cce-auto-remediation-runner
Huawei Cloud CCE auto-remediation runner skill that converts remediation intent into preview-first, confirm-required, post-verify execution plans. Use this skill only when the user asks for a CCE remediation action or a diagnosis result needs a preview-first recovery plan, including Deployment rollback, restart/scale/resize, cordon/drain, reboot, isolation, traffic cutover, vulnerability status change, or cluster hibernate/awake. This skill performs MUTATION actions (drain, cordon, scale, restart, delete, reboot, hibernate) that require preview+confirm workflow. NEVER auto-add confirm=true. Trigger: "auto remediation", "自动恢复", "remediation action", "恢复动作", "node drain", "节点 drain", "node cordon", "节点 cordon", "scale workload", "扩缩容", "restart pod", "重启 Pod", "remediation preview", "恢复预览", "confirm remediation", "确认恢复"
Huawei Cloud CCE auto-remediation runner skill that converts remediation intent into preview-first, confirm-required, post-verify execution plans.
As a process B 70/100 · Nearly there — weak spots: running it twice, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-execpolicy-bypassSKILL.md:52Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)- Windows: `skill action=exec: powershell -ExecutionPolicy Bypass -File skill://scripts/chec…ps1`
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "id"
Process rating: all ten parameters 70/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4609 tokens
- 85Steps. 61 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +3Description length 829: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 61 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.