kube-medicKubernetes Cluster Triage & Diagnostics — instant AI-powered incident triage via kubectl
Install via ClawdBot CLI:
clawdbot install tkuehnl/kube-medicGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec (Calls external URL not in known-safe list
https://kubernetes.io/docs/tasks/tools/AI Analysis
The skill executes arbitrary bash scripts with kubectl access, enabling cluster-wide read/write operations via the 'confirm_write' flag. While the external reference (kubernetes.io) is benign, the core risk is privilege escalation and destructive actions within the Kubernetes environment, not data exfiltration.
Audited Apr 17, 2026 · audit v1.0
Generated Feb 23, 2026
An SRE receives an alert about a pod crash in a production Kubernetes cluster. Using kube-medic's sweep and pod subcommands, they quickly identify a CrashLoopBackOff pod, correlate OOMKilled events with low memory limits, and diagnose the root cause as insufficient memory allocation, enabling a rapid fix.
A DevOps engineer deploys a new version of an application and notices the rollout is stuck. They use the deploy subcommand to check replica counts, rollout status, and ReplicaSet revisions, identifying an image pull error or resource constraint blocking the update, and take corrective action.
A platform team performs a routine cluster health check to optimize costs. Using the resources subcommand, they analyze node CPU/memory usage, identify pods without resource limits causing contention, and recommend adjustments to improve efficiency and prevent future outages.
During an on-call shift, an engineer manages multiple Kubernetes clusters (e.g., staging and production). They use kube-medic with the context flag to swiftly triage issues across environments, comparing events and pod statuses to isolate problems and maintain service availability.
Offer kube-medic as a cloud-based diagnostic service with tiered subscriptions (e.g., free for basic, paid for advanced features like historical data or multi-cluster support). Revenue is generated through monthly or annual fees from DevOps teams and enterprises.
Sell on-premise or self-hosted licenses to large organizations with strict compliance needs. Include premium support, custom integrations, and training services, generating revenue from one-time license sales and ongoing maintenance contracts.
Provide a free open-source version of kube-medic to build community adoption, then monetize through premium add-ons like automated remediation, advanced analytics, or Discord/Slack bot integrations. Revenue comes from upsells to power users and teams.
💬 Integration Tip
Integrate kube-medic into existing CI/CD pipelines or monitoring dashboards by wrapping its subcommands in scripts or using its JSON output for automated alerts and reporting.
Scored Apr 22, 2026
Essential Docker commands and workflows for container management, image operations, and debugging.
Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use whe...
Define multi-container applications with proper dependency handling, networking, and volume management.
Break any problem down to fundamental truths, then rebuild solutions from atoms up. Use when user says "firstp", "first principles", "from scratch", "what are we assuming", "break this down", "atomic", "fundamental truth", "physics thinking", "Elon method", "bedrock", "ground up", "core problem", "strip away", or challenges assumptions about how things are done.
Chat-based AWS infrastructure assistance using AWS CLI and console context. Use for querying, auditing, and monitoring AWS resources (EC2, S3, IAM, Lambda, ECS/EKS, RDS, CloudWatch, billing, etc.), and for proposing safe changes with explicit confirmation before any write/destructive action.
Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini, and Kiro agents with network proxy controls.