SKILLEMALL.ai
GitHub ↗ RU Sign in

BC Kubernetes

Debugs Kubernetes workloads and reviews manifests: pods, probes, resources, rollouts, Services, storage, RBAC. Use when a pod is Pending, CrashLoopBackOff, ImagePullBackOff, OOMKilled or stuck Terminating, when a Service or Ingress serves nothing or returns 502/503/504, when cluster DNS is flaky, a rollout hangs or silently ships a broken version, an HPA refuses to scale, a PVC stays unbound, a node goes NotReady or a drain never finishes, when writing or reviewing YAML, Helm charts or kustomize overlays, when tuning requests, limits, QoS, probes and graceful shutdown, when locking down RBAC, NetworkPolicy, Pod Security and Secrets, when the API server throttles or an admission webhook blocks every create, when a GPU pod never schedules, when a mesh sidecar breaks a Job, or when planning a cluster upgrade, a backup, or a restore. Covers kubectl triage, StatefulSets, Jobs and CronJobs, autoscaling, operators, node drains and DaemonSet agents. Not for building container images — that is `docker`.

ClawHub Agent Skills author: Iván v1.0.5 MIT-0 30 files body ≈ 7 348 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Debugs Kubernetes workloads and reviews manifests: pods, probes, resources, rollouts, Services, storage, RBAC.

As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerKubernetesDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
97
Quality 40%
66
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Running it twice w 4
30
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Risky intent intent-offensive-security security.md:18
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Three profiles: `privileged` (no restrictions), `baseline` (blocks the known escape vectors: privileged, hostPID/IPC/Network, hostPath, most capabilities), `restricted` (baseline plus runAsNonRoot,
  • low Dangerous commands cmd-privilege security.md:54
    Privilege escalation / world-writable permissions (documentation of a security skill)
    | `allowPrivilegeEscalation: true` with a setuid binary | Root inside the container, the starting point for the rest |
    security skill

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 7348 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 61/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 28 mutating operations with no state check
  • 40Consistency. Frontmatter name (Kubernetes) differs from the folder (k8s)
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 7348 tokens
  • 100Steps. 59 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 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 (5 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
  • +3Description length 1009: 120–800 characters recommended
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 59 items
  • +3Output format is stated explicitly

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This Kubernetes troubleshooting skill is not malicious, but it needs review because it combines automatic infrastructure memory with high-privilege cluster debug commands and unfiltered secret-prone output.
LLM: suspicious (high) · VirusTotal: · 10 Sept 2026