See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhich script within the repository is dedicated to gathering raw CPU, memory, and pod usage metrics from Kubernetes endpoints?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Identifies scripts/metrics-collector.py as the resource metrics gathering script | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md60 lines2 filesincludes scripts
Health Check Monitor — Kubernetes Cluster Monitoring
Purpose
Automated monitoring solution for Kubernetes cluster health, resource utilization, and proactive issue detection. Provides real-time alerts and recommendations for maintaining cluster stability.
When to Use
- Routine Health Checks: Regular cluster status monitoring
- Resource Alerts: When pods are nearing resource limits
- Node Issues: Detecting unhealthy nodes or failed pods
- Capacity Planning: Monitoring resource trends for scaling decisions
- Incident Prevention: Early detection of potential problems
Gotchas
Common Pitfalls
- RBAC Permissions: Health monitoring requires cluster-reader permissions
- Network Policies: Some clusters block metrics collection from pods
- Resource Limits: Monitoring pods themselves need resource limits
- False Positives: Temporary spikes shouldn't trigger alerts
Edge Cases
- Multi-tenant Clusters: Namespaces may have different monitoring requirements
- StatefulSets: Different health criteria than stateless deployments
- Custom Resources: CRDs may need special health checks
Inputs
- cluster: Target cluster name (optional, default: current context)
- namespace: Namespace to monitor (optional, default: all)
- check_types: Types of checks to perform (optional, default: all)
- alert_thresholds: Custom alert thresholds (optional)
Process
- Cluster Discovery: Identify target clusters and namespaces
- Resource Collection: Gather pod, node, and service status
- Health Assessment: Evaluate health metrics against thresholds
- Alert Generation: Create alerts for issues found
- Report Generation: Produce monitoring summary and recommendations
Outputs
- Health Status: Overall cluster health score and status
Track record
Benchmark
22 / 22
test cases passed, vs 15 / 22 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedlloydchang / agentic-reconciliation-engine
core/ai/skills/health-check-monitor/SKILL.md
License AGPLv3Imported 8/1/2026Version v1Bundled 1 file · scripts