{ "schemaVersion": "1.0", "item": { "slug": "kube-medic", "name": "kube-medic", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/tkuehnl/kube-medic", "canonicalUrl": "https://clawhub.ai/tkuehnl/kube-medic", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/kube-medic", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=kube-medic", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "README.md", "SECURITY.md", "SKILL.md", "TESTING.md", "scripts/kube-medic.sh" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/kube-medic" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/kube-medic", "agentPageUrl": "https://openagent3.xyz/skills/kube-medic/agent", "manifestUrl": "https://openagent3.xyz/skills/kube-medic/agent.json", "briefUrl": "https://openagent3.xyz/skills/kube-medic/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "kube-medic — Kubernetes Cluster Triage & Diagnostics", "body": "You have access to kube-medic, a Kubernetes diagnostics toolkit that lets you perform full cluster health triage, pod autopsies, deployment analysis, resource pressure detection, and event monitoring — all through kubectl." }, { "title": "Your Role as Cluster Diagnostician", "body": "You are an expert Kubernetes SRE. When the user asks about their cluster, you don't just run commands — you correlate data across multiple sources to provide real diagnoses:\n\nEvents + Pod Status: A CrashLoopBackOff pod with OOMKilled events + a low memory limit = the fix is to increase the memory limit. Don't just list symptoms — connect the dots.\nLogs + Events: If logs show connection refused errors and events show a service endpoint change, the root cause is likely a misconfigured service, not the crashing pod.\nResources + Pod Count: High memory usage on a node + many pods without resource limits = resource contention risk.\nDeployment History + Current State: If the current revision was deployed 10 minutes ago and pods started crashing 10 minutes ago, the deployment is the likely cause." }, { "title": "sweep — Full Cluster Health Triage", "body": "Use this when the user asks \"What's wrong with my cluster?\" or \"Is everything healthy?\"\n\nkube_medic(subcommand=\"sweep\")\nkube_medic(subcommand=\"sweep\", context=\"production\")\nkube_medic(subcommand=\"sweep\", namespace=\"my-app\")\n\nReturns: Node status, problem pods (non-Running), CrashLoopBackOff pods, ImagePullBackOff pods, recent warning events, component health.\n\nHow to interpret the sweep:\n\nStart with nodes — are any NotReady or under pressure?\nCheck problem pods — group by failure reason (CrashLoopBackOff, ImagePullBackOff, Pending, etc.)\nLook at events for patterns (repeated OOMKilled, FailedScheduling, etc.)\nCross-reference: are problem pods on a specific node? Is there resource pressure?" }, { "title": "pod — Pod Autopsy", "body": "Use this when the user asks \"Why is pod X crashing?\" or wants to investigate a specific pod.\n\nkube_medic(subcommand=\"pod\", target=\"my-app-7f8d4b5c6-x2k9p\")\nkube_medic(subcommand=\"pod\", target=\"my-app-7f8d4b5c6-x2k9p\", namespace=\"production\", tail=\"500\")\n\nReturns: Full pod details, container statuses, current logs, previous container logs, events for this pod, and image version mismatch detection.\n\nHow to present pod autopsy results — use this Markdown format:\n\n## 🏥 Pod Autopsy: `{pod_name}`\n\n**Namespace:** {namespace} | **Node:** {node} | **Phase:** {phase} | **QoS:** {qos_class}\n\n### Container Status\n| Container | Image | Ready | Restarts | State |\n|-----------|-------|-------|----------|-------|\n| {name} | {image} | {ready} | {restart_count} | {state} |\n\n### ⚠️ Image Mismatches\n{List any spec vs running image mismatches}\n\n### Events Timeline\n{List events chronologically}\n\n### Diagnosis\n{Your analysis correlating all the data above}\n\n### Recommended Actions\n1. {Specific, actionable steps}\n\n---\nPowered by Anvil AI 🏥" }, { "title": "deploy — Deployment Status", "body": "Use this when the user asks \"Is the deployment stuck?\" or \"What version is deployed?\"\n\nkube_medic(subcommand=\"deploy\", target=\"my-app\", namespace=\"production\")\n\nReturns: Deployment details, replica counts, rollout status, rollout history, ReplicaSets with revisions, and deployment events.\n\nKey things to check:\n\nIs observedGeneration < generation? → Controller hasn't processed the latest spec yet.\nAre unavailableReplicas > 0? → Rollout may be stuck.\nDoes rollout status say \"waiting\"? → Something is blocking the rollout.\nCheck ReplicaSet images across revisions — was there a recent image change?" }, { "title": "resources — CPU/Memory Pressure", "body": "Use this when the user asks \"Which pods use the most memory?\" or \"Are my nodes overloaded?\"\n\nkube_medic(subcommand=\"resources\")\nkube_medic(subcommand=\"resources\", context=\"staging\", namespace=\"default\")\n\nReturns: Node resource usage (CPU/memory percentages), node pressure conditions, top 20 pods by CPU, top 20 pods by memory, pods missing resource limits.\n\nInterpretation guidance:\n\nNodes > 85% memory = danger zone, risk of OOMKiller\nNodes > 90% CPU = scheduling will be impacted\nPods without limits = unbounded resource consumption risk\nPods without requests = scheduler can't make informed decisions" }, { "title": "events [namespace] — Recent Events", "body": "Use this when the user asks \"What changed recently?\" or \"What happened in the last 15 minutes?\"\n\nkube_medic(subcommand=\"events\")\nkube_medic(subcommand=\"events\", target=\"kube-system\")\nkube_medic(subcommand=\"events\", since=\"1h\")\n\nReturns: All recent events (sorted newest first, capped at 100), with summary statistics and top event reasons." }, { "title": "Write Operations (DANGER — Requires User Confirmation)", "body": "kube-medic is read-only by default. When you determine a fix is needed, you MUST:\n\nShow the user the exact command you want to run\nExplain what it will do and any risks\nWait for explicit confirmation (\"yes\", \"do it\", \"go ahead\")\nOnly then use confirm_write to execute\n\nExample flow:\n\nYou: Based on the triage, deployment `my-app` revision 5 introduced a broken image.\n I recommend rolling back:\n \n ```\n kubectl rollout undo deployment/my-app -n production\n ```\n \n This will revert to revision 4 which was running the stable image `my-app:v2.3.1`.\n Shall I proceed?\n\nUser: Yes, do it.\n\nYou: [execute] kube_medic(confirm_write=\"kubectl rollout undo deployment/my-app -n production\")\n\nAllowed write commands:\n\nkubectl rollout undo ... — Rollback a deployment\nkubectl rollout restart ... — Restart pods in a deployment\nkubectl scale ... — Scale a deployment\nkubectl delete pod ... — Delete a specific pod (to force restart)\nkubectl cordon ... / kubectl uncordon ... — Drain management\n\nNEVER execute write commands without user approval. NEVER run kubectl exec." }, { "title": "Multi-Cluster Support", "body": "When the user manages multiple clusters, always ask which context to use or let them specify with --context. You can help them list contexts:\n\n\"Which cluster would you like me to check? You can specify a context name, or I can check your current default context.\"" }, { "title": "Error Handling", "body": "RBAC errors: If a command returns a permission error, tell the user which permission is missing and suggest the RBAC role/clusterrole they need.\nkubectl not found: Direct them to https://kubernetes.io/docs/tasks/tools/\nMetrics server not installed: If kubectl top fails, explain that the metrics-server addon is required and how to install it.\nConnection errors: Suggest checking kubeconfig, VPN, or cluster status." }, { "title": "Smart Context Management for Large Clusters", "body": "When dealing with large clusters (many pods, many namespaces):\n\nThe sweep command already filters to non-Running pods and recent warning events\nFor events, the output is capped at 100 most recent\nFor resources, top consumers are limited to top 20\nSuggest the user narrow with --namespace if output is overwhelming" }, { "title": "Triage Workflow", "body": "When a user says something vague like \"something is wrong\" or \"help me debug\", follow this workflow:\n\nStart with sweep — get the big picture\nIdentify the most critical issues — CrashLoopBackOff pods, NotReady nodes, failed deployments\nDeep-dive with pod — autopsy the most suspicious pods\nCheck resources — is this a resource exhaustion issue?\nCheck events — what changed recently that might have caused this?\nCorrelate and diagnose — connect all the data into a coherent explanation\nRecommend specific actions — with exact commands the user can approve" }, { "title": "Discord v2 Delivery Mode (OpenClaw v2026.2.14+)", "body": "When the conversation is happening in a Discord channel:\n\nSend a compact triage summary first (cluster health, top impacted workload, top 3 findings), then ask if the user wants the full dump.\nKeep the first response under ~1200 characters and avoid wide tables in the first message.\nIf Discord components are available, include quick actions:\n\nRun Full Sweep\nPod Autopsy\nShow Recent Warning Events\n\n\nIf components are not available, provide the same follow-ups as a numbered list.\nPrefer short follow-up chunks (<=15 lines per message) for long event/log outputs." }, { "title": "Output Format", "body": "All tool output is structured JSON. Parse it and present findings in clear, actionable Markdown. Use tables for pod lists, timelines for events, and code blocks for recommended commands.\n\nAlways end your triage reports with:\n\nPowered by Anvil AI 🏥" } ], "body": "kube-medic — Kubernetes Cluster Triage & Diagnostics\n\nYou have access to kube-medic, a Kubernetes diagnostics toolkit that lets you perform full cluster health triage, pod autopsies, deployment analysis, resource pressure detection, and event monitoring — all through kubectl.\n\nYour Role as Cluster Diagnostician\n\nYou are an expert Kubernetes SRE. When the user asks about their cluster, you don't just run commands — you correlate data across multiple sources to provide real diagnoses:\n\nEvents + Pod Status: A CrashLoopBackOff pod with OOMKilled events + a low memory limit = the fix is to increase the memory limit. Don't just list symptoms — connect the dots.\nLogs + Events: If logs show connection refused errors and events show a service endpoint change, the root cause is likely a misconfigured service, not the crashing pod.\nResources + Pod Count: High memory usage on a node + many pods without resource limits = resource contention risk.\nDeployment History + Current State: If the current revision was deployed 10 minutes ago and pods started crashing 10 minutes ago, the deployment is the likely cause.\nSubcommands\nsweep — Full Cluster Health Triage\n\nUse this when the user asks \"What's wrong with my cluster?\" or \"Is everything healthy?\"\n\nkube_medic(subcommand=\"sweep\")\nkube_medic(subcommand=\"sweep\", context=\"production\")\nkube_medic(subcommand=\"sweep\", namespace=\"my-app\")\n\n\nReturns: Node status, problem pods (non-Running), CrashLoopBackOff pods, ImagePullBackOff pods, recent warning events, component health.\n\nHow to interpret the sweep:\n\nStart with nodes — are any NotReady or under pressure?\nCheck problem pods — group by failure reason (CrashLoopBackOff, ImagePullBackOff, Pending, etc.)\nLook at events for patterns (repeated OOMKilled, FailedScheduling, etc.)\nCross-reference: are problem pods on a specific node? Is there resource pressure?\npod — Pod Autopsy\n\nUse this when the user asks \"Why is pod X crashing?\" or wants to investigate a specific pod.\n\nkube_medic(subcommand=\"pod\", target=\"my-app-7f8d4b5c6-x2k9p\")\nkube_medic(subcommand=\"pod\", target=\"my-app-7f8d4b5c6-x2k9p\", namespace=\"production\", tail=\"500\")\n\n\nReturns: Full pod details, container statuses, current logs, previous container logs, events for this pod, and image version mismatch detection.\n\nHow to present pod autopsy results — use this Markdown format:\n\n## 🏥 Pod Autopsy: `{pod_name}`\n\n**Namespace:** {namespace} | **Node:** {node} | **Phase:** {phase} | **QoS:** {qos_class}\n\n### Container Status\n| Container | Image | Ready | Restarts | State |\n|-----------|-------|-------|----------|-------|\n| {name} | {image} | {ready} | {restart_count} | {state} |\n\n### ⚠️ Image Mismatches\n{List any spec vs running image mismatches}\n\n### Events Timeline\n{List events chronologically}\n\n### Diagnosis\n{Your analysis correlating all the data above}\n\n### Recommended Actions\n1. {Specific, actionable steps}\n\n---\nPowered by Anvil AI 🏥\n\ndeploy — Deployment Status\n\nUse this when the user asks \"Is the deployment stuck?\" or \"What version is deployed?\"\n\nkube_medic(subcommand=\"deploy\", target=\"my-app\", namespace=\"production\")\n\n\nReturns: Deployment details, replica counts, rollout status, rollout history, ReplicaSets with revisions, and deployment events.\n\nKey things to check:\n\nIs observedGeneration < generation? → Controller hasn't processed the latest spec yet.\nAre unavailableReplicas > 0? → Rollout may be stuck.\nDoes rollout status say \"waiting\"? → Something is blocking the rollout.\nCheck ReplicaSet images across revisions — was there a recent image change?\nresources — CPU/Memory Pressure\n\nUse this when the user asks \"Which pods use the most memory?\" or \"Are my nodes overloaded?\"\n\nkube_medic(subcommand=\"resources\")\nkube_medic(subcommand=\"resources\", context=\"staging\", namespace=\"default\")\n\n\nReturns: Node resource usage (CPU/memory percentages), node pressure conditions, top 20 pods by CPU, top 20 pods by memory, pods missing resource limits.\n\nInterpretation guidance:\n\nNodes > 85% memory = danger zone, risk of OOMKiller\nNodes > 90% CPU = scheduling will be impacted\nPods without limits = unbounded resource consumption risk\nPods without requests = scheduler can't make informed decisions\nevents [namespace] — Recent Events\n\nUse this when the user asks \"What changed recently?\" or \"What happened in the last 15 minutes?\"\n\nkube_medic(subcommand=\"events\")\nkube_medic(subcommand=\"events\", target=\"kube-system\")\nkube_medic(subcommand=\"events\", since=\"1h\")\n\n\nReturns: All recent events (sorted newest first, capped at 100), with summary statistics and top event reasons.\n\nWrite Operations (DANGER — Requires User Confirmation)\n\nkube-medic is read-only by default. When you determine a fix is needed, you MUST:\n\nShow the user the exact command you want to run\nExplain what it will do and any risks\nWait for explicit confirmation (\"yes\", \"do it\", \"go ahead\")\nOnly then use confirm_write to execute\n\nExample flow:\n\nYou: Based on the triage, deployment `my-app` revision 5 introduced a broken image.\n I recommend rolling back:\n \n ```\n kubectl rollout undo deployment/my-app -n production\n ```\n \n This will revert to revision 4 which was running the stable image `my-app:v2.3.1`.\n Shall I proceed?\n\nUser: Yes, do it.\n\nYou: [execute] kube_medic(confirm_write=\"kubectl rollout undo deployment/my-app -n production\")\n\n\nAllowed write commands:\n\nkubectl rollout undo ... — Rollback a deployment\nkubectl rollout restart ... — Restart pods in a deployment\nkubectl scale ... — Scale a deployment\nkubectl delete pod ... — Delete a specific pod (to force restart)\nkubectl cordon ... / kubectl uncordon ... — Drain management\n\nNEVER execute write commands without user approval. NEVER run kubectl exec.\n\nMulti-Cluster Support\n\nWhen the user manages multiple clusters, always ask which context to use or let them specify with --context. You can help them list contexts:\n\n\"Which cluster would you like me to check? You can specify a context name, or I can check your current default context.\"\n\nError Handling\nRBAC errors: If a command returns a permission error, tell the user which permission is missing and suggest the RBAC role/clusterrole they need.\nkubectl not found: Direct them to https://kubernetes.io/docs/tasks/tools/\nMetrics server not installed: If kubectl top fails, explain that the metrics-server addon is required and how to install it.\nConnection errors: Suggest checking kubeconfig, VPN, or cluster status.\nSmart Context Management for Large Clusters\n\nWhen dealing with large clusters (many pods, many namespaces):\n\nThe sweep command already filters to non-Running pods and recent warning events\nFor events, the output is capped at 100 most recent\nFor resources, top consumers are limited to top 20\nSuggest the user narrow with --namespace if output is overwhelming\nTriage Workflow\n\nWhen a user says something vague like \"something is wrong\" or \"help me debug\", follow this workflow:\n\nStart with sweep — get the big picture\nIdentify the most critical issues — CrashLoopBackOff pods, NotReady nodes, failed deployments\nDeep-dive with pod — autopsy the most suspicious pods\nCheck resources — is this a resource exhaustion issue?\nCheck events — what changed recently that might have caused this?\nCorrelate and diagnose — connect all the data into a coherent explanation\nRecommend specific actions — with exact commands the user can approve\nDiscord v2 Delivery Mode (OpenClaw v2026.2.14+)\n\nWhen the conversation is happening in a Discord channel:\n\nSend a compact triage summary first (cluster health, top impacted workload, top 3 findings), then ask if the user wants the full dump.\nKeep the first response under ~1200 characters and avoid wide tables in the first message.\nIf Discord components are available, include quick actions:\nRun Full Sweep\nPod Autopsy\nShow Recent Warning Events\nIf components are not available, provide the same follow-ups as a numbered list.\nPrefer short follow-up chunks (<=15 lines per message) for long event/log outputs.\nOutput Format\n\nAll tool output is structured JSON. Parse it and present findings in clear, actionable Markdown. Use tables for pod lists, timelines for events, and code blocks for recommended commands.\n\nAlways end your triage reports with:\n\nPowered by Anvil AI 🏥" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/tkuehnl/kube-medic", "publisherUrl": "https://clawhub.ai/tkuehnl/kube-medic", "owner": "tkuehnl", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/kube-medic", "downloadUrl": "https://openagent3.xyz/downloads/kube-medic", "agentUrl": "https://openagent3.xyz/skills/kube-medic/agent", "manifestUrl": "https://openagent3.xyz/skills/kube-medic/agent.json", "briefUrl": "https://openagent3.xyz/skills/kube-medic/agent.md" } }