CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An impressively detailed, actionable debugging runbook with concrete commands and a sequenced workflow, weakened primarily by length and duplicated content across platform sections. Splitting per-platform detail into reference files and deduplicating repeated bullets would materially improve it.

Suggestions

Deduplicate content that recurs across sections: factor the OCI identity-resolution / workspace-validation bullets out of both the Docker and Podman steps, and reconcile the certManager 'UnknownCA' guidance that appears in both Step 6 prose and the Common Failure Patterns table.

Move the large platform-specific deep dives (Docker GPU/CDI, Kubernetes sidecar topology, corporate upstream proxy, cert-manager/SPIRE) into separate reference files under references/ and link to them from SKILL.md, keeping the main file as an overview + quick diagnostics.

Add explicit validate/decision gates between steps (e.g., 'if Step 1 returns No active gateway, jump to registration; otherwise proceed to Step 2') so the branching diagnostic tree is navigable rather than implied by Common findings lists.

DimensionReasoningScore

Conciseness

The body is densely actionable and avoids explaining concepts Claude already knows, but it is very long and contains verbatim duplication (e.g., the OCI identity-resolution bullet repeats in both Docker and Podman steps; the certManager 'UnknownCA' guidance repeats in Step 6 prose and the Common Failure Patterns table).

3 / 5

Actionability

Provides copy-paste-ready, fully executable commands across openshell, docker, podman, helm, kubectl, journalctl, and rg, plus exact jsonpath queries and specific config-key references that cover the common diagnostic cases.

5 / 5

Workflow Clarity

A clear ordered workflow (Steps 1-7) with a 'stop once the root cause is clear' gate and per-step 'Common findings' feedback, but the branching decision-tree nature means validation is expressed as finding lists rather than crisp validate-then-proceed gates, leaving minor checkpoint gaps.

4 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets are absent) and the entire ~640-line body is a single monolithic file; the per-platform deep dives (Docker GPU/CDI, Kubernetes sidecar/proxy/cert-manager) are inlined where separate reference files could aid navigation, though section headers and tables provide reasonable in-page structure.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and answers both what and when with an explicit trigger-keyword list, leaving little ambiguity about when to invoke the skill. It is long but every clause carries trigger or capability information rather than fluff.

DimensionReasoningScore

Specificity

Names the concrete action ('Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes') and comprehensively enumerates specific failure domains (Docker/Podman runtime, Helm, Kubernetes scheduling, TLS/auth, interceptors, middleware, compute-driver sockets, VM drivers, sandbox startup).

5 / 5

Completeness

Clearly answers both 'what' (debug unhealthy/unreachable/sandbox-creation-failed gateway deployments) and 'when' via an explicit 'Use for ...' clause plus concrete trigger phrases, matching the anchor that requires both.

5 / 5

Trigger Term Quality

An explicit 'Trigger keywords' list provides natural phrases a user would say ('debug gateway', 'gateway failing', 'deployment failing', 'helm install failing', 'sandbox pending', 'docker driver', 'vm driver') with good synonym/variation coverage.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (OpenShell gateway deployment debugging) with distinct, domain-specific triggers, making conflict with unrelated skills minimal.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (647 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
NVIDIA/OpenShell
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.