AC kubevpn
KubeVPN is a cloud-native dev tool to connect local machine to Kubernetes cluster networks. Use this skill when the user mentions: kubevpn, KubeVPN, or any of the following scenarios: (1) Connect local machine to k8s/Kubernetes cluster network or internal services; (2) Access pod IPs, service IPs, or cluster DNS from local; (3) Intercept or proxy inbound traffic of a k8s workload/deployment/service to local PC; (4) Local development against a remote Kubernetes cluster; (5) Debug a k8s service locally while it receives real cluster traffic; (6) Run a Kubernetes pod/deployment locally in Docker with same env vars, volumes, network; (7) Sync local source code into a running cluster workload (hot-reload in cluster env); (8) SSH bastion/jump host to reach a private k8s API server; (9) 本地连接 Kubernetes 集群网络 / 本地调试 k8s 服务 / 拦截集群流量到本地 / 本地运行 k8s workload。
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 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.
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
- 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 Dangerous commands
cmd-pipe-to-shellSKILL.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://kubevpn.dev/install.sh | sh # Linux/macOS
vendor-host
Files scanned: 4. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1280 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 858: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.