AB eks-workload-best-practice-assessment
Use when assessing or reviewing Kubernetes workloads running on Amazon EKS for best practice compliance, including pod configuration, security posture, observability, networking, storage, image security, and CI/CD practices. Requires kubectl and awscli access to the target cluster. Triggers on "assess my EKS workloads", "check k8s best practices", "assess container workloads", "evaluate pod security", "workload compliance check", "EKS workload assessment", "检查 K8s 工作负载", "评估容器最佳实践", "审计 EKS 应用", "检查 Pod 配置", "容器安全评估", "工作负载合规检查".
As a process B 67/100 · Nearly there — weak spots: result and completion, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityreferences/check-dimensions.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| SEC-03-hi | **runAsNonRoot enforced** | All containers should set `securityContext.runAsNonRoot: true`. Running as root inside containers is a privilege escalation risk. | High | |
-
low Risky intent
intent-offensive-securityreferences/check-dimensions.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| SEC-11-md | **NetworkPolicy exists** | Every namespace should have at least a default-deny ingress/egress NetworkPolicy. Open network is a lateral movement risk. | Medium | |
detector
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, write, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 66 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2540 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 535: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 66 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.