SKILLEMALL.ai
GitHub ↗ RU Sign in

CC debug-openshell-cluster

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Kubernetes scheduling, TLS or auth, gateway interceptors, supervisor middleware startup or runtime failures, external compute-driver sockets, VM drivers, or sandbox startup. Trigger keywords - debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, health check failed, sandbox pending, docker driver, podman driver, kubernetes driver, external driver, compute driver socket, gateway interceptor, supervisor middleware, middleware failed, vm driver.

NVIDIA/openshell Agent Skills author: NVIDIA Apache-2.0 2 files body ≈ 23 975 tokens Open the sourcegithub.com↗ analyzed 11 h ago

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes.

As a process C 57/100 · Has gaps — References files that are not bundled: templates/certgen.yaml

IntegrationDockerKubernetesInfrastructuretype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
97
Quality 40%
70
Run on models
none yet
Process rating
C
57/100
Has gaps
References files that are not bundled: templates/certgen.yaml
Tools and files w 18
0
Execution cost w 6
10
Running it twice w 4
30
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.
  2. The text references files that are not there: add them or drop the references.
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 Dangerous commands cmd-background-process SKILL.md:299
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable --now nvidia-cdi-refresh.path
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:300
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable --now nvidia-cdi-refresh.service
    security skill
  • low Risky intent intent-offensive-security SKILL.md:1017
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    privilege escalation, and use `RuntimeDefault` seccomp. The supervisor reaches

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 23975 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: templates/certgen.yaml
  • note edit-residue the text marks something as outdated (lines 110, 134, 136, 481, 1165, 1244): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 57/100

Will not run. References files that are not bundled: templates/certgen.yaml
  • 0Tools and files. 1 referenced file(s) missing: templates/certgen.yaml
  • 10Execution cost. Instruction body is 23975 tokens: crowds the task out of the window
  • 30Running it twice. 89 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 77 steps, 2 vague phrases
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (27 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 699: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 77 items
  • +4Has examples (47 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

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