[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-gke-skill-creator":3,"mdc--hxc8ue-key":34,"related-repo-google-cloud-gke-skill-creator":555,"related-org-google-cloud-gke-skill-creator":653},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":32,"mdContent":33},"gke-skill-creator","generate specialized GKE operational skills","Dynamically generates specialized GKE skills for complex troubleshooting, operational workflows, architectural setup, or performance\u002Fcost optimization. Trigger this skill whenever the user faces a novel or non-obvious GKE challenge, needs custom cluster management workflows, or standard agent capabilities fall short, even if they don't explicitly ask to create a skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20,23],{"name":14,"slug":15,"type":16},"Automation","automation","tag",{"name":18,"slug":19,"type":16},"Engineering","engineering",{"name":21,"slug":22,"type":16},"Kubernetes","kubernetes",{"name":9,"slug":8,"type":16},161,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp","2026-07-12T07:39:32.148618",null,78,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":27},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgke-mcp\u002Ftree\u002FHEAD\u002Fskills\u002Fgke-skill-creator","---\nname: gke-skill-creator\ndescription: >-\n  Dynamically generates specialized GKE skills for complex troubleshooting,\n  operational workflows, architectural setup, or performance\u002Fcost optimization.\n  Trigger this skill whenever the user faces a novel or non-obvious GKE\n  challenge, needs custom cluster management workflows, or standard agent\n  capabilities fall short, even if they don't explicitly ask to create a skill.\n---\n\n# GKE Skill Creator\n\n## Overview\n\nThis meta-skill acts as an interactive assistant to diagnose novel or complex\nGoogle Kubernetes Engine (GKE) issues and dynamically generate a specialized\ntroubleshooting skill tailored to the exact problem discovered.\n\n## Core Mandate: Public-Facing Output\n\nDuring the investigation and research phase, you should leverage official GKE\ndocumentation, public Kubernetes issue trackers, and trusted SRE resources to\ndeeply understand the issue.\n\n**CRITICAL:** The _generated skill_ must be strictly public-facing. It MUST NOT\ncontain any internal codenames, acronyms, or references to internal Google\nsystems. All remediation logic must be expressed in terms of standard, public\ntools like `kubectl` and `gcloud`. This ensures the skill is usable by external\nGKE customers.\n\n## Workflow\n\n### 1. Capture Intent & Investigate\n\n- Ask the user for specific GKE symptoms (e.g., Pods stuck in\n  `CrashLoopBackOff`, Service 503 errors, Node pressure).\n- Use **read-only** tools to pull live context:\n  - `kubectl get \u003Cresource> -o yaml`\n  - `kubectl describe \u003Cresource>`\n  - `kubectl logs \u003Cpod> --tail=100`\n  - `kubectl get events --sort-by='.lastTimestamp'`\n  - `gcloud container clusters describe \u003Ccluster>`\n\n### 2. Perform Deep Research\n\n- Before drafting the skill, perform deep research on the identified topic.\n- Understand default argument values, potential side effects, and best\n  practices for the commands you plan to include.\n- Use trusted public sources to ensure accuracy.\n- Use web search to find specific technical details from official\n  documentation and trusted sources (e.g., Google Cloud, GKE, Kubernetes),\n  such as:\n  - Exact error message matches and their documented causes.\n  - Command references for `kubectl` or `gcloud` to verify syntax and flags.\n  - Known issues, limitations, or version-specific caveats.\n  - Official troubleshooting workflows and decision trees.\n\n### 3. Draft the Skill\n\n- Use the\n  [generated_skill_skeleton.md](references\u002Fgenerated_skill_skeleton.md)\n  template.\n- **Cheat sheet Philosophy**: Write the `SKILL.md` to be terse and opinionated.\n  Focus on \"gotchas\", exact command patterns, and specific pitfalls rather\n  than long explanations.\n- **Progressive Disclosure**: For complex issues, avoid a monolithic\n  `SKILL.md`. Suggest breaking down long lists of commands or log analysis\n  patterns into separate reference artifacts in `references\u002F`.\n- **Make Descriptions Pushy**: Ensure the generated skill's description\n  explicitly states when it should be used, covering variations of the\n  problem.\n- **Fallback Remediation**: If the primary method depends on specific\n  high-level tools (e.g., MCP tools, API integrations) or environment\n  configurations that might fail, include standard CLI fallback alternatives\n  (like raw `kubectl` or `gcloud` commands) to achieve the same result.\n- **Match User Intent**: Instruct executing agents to match the user's intent:\n  explain\u002Finvestigate if requested, or execute remediation if asked to fix the\n  issue.\n- Ensure the draft contains:\n  - Precise Symptoms.\n  - User Intent & Execution Rules.\n  - Step-by-step Diagnosis commands.\n  - Remediation (Fix) commands with impact descriptions.\n  - Verification steps.\n  - Technical Explanation (explaining _why_ the fix works).\n\n### 4. Review & Iterate\n\n- Present the proposed diagnosis and the draft commands to the user.\n- **Human-in-the-loop:** The user must approve the logic before finalization.\n- Incorporate any user feedback or constraints.\n\n### 5. Finalize & Handoff\n\n- Once approved, provide the finalized `SKILL.md` content directly in the\n  chat.\n- **Handoff:** Instruct the user that they can use this diagnosis and\n  remediation logic directly in their current session, or save it to a local\n  file for reference.\n- Clarify that this process is for generating dynamic, session-specific skills\n  and is distinct from adding permanent skills to the GKE-MCP codebase.\n\n## Safety Guardrails\n\n- **Read-Only Discovery:** Never execute modifying commands during the\n  investigation phase.\n- **Destructive Actions:** Generated skills MUST instruct the agent to seek\n  explicit human confirmation before running destructive commands (e.g.,\n  `kubectl delete`, `gcloud container clusters update`).\n- **Impact Description:** Every remediation command must have a clear\n  explanation of what it does.\n\n## References\n\n- [Generated Skill Template](references\u002Fgenerated_skill_skeleton.md)\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,47,54,60,66,71,107,113,120,198,204,264,270,418,424,447,453,483,489,538,544],{"type":40,"tag":41,"props":42,"children":43},"element","h1",{"id":4},[44],{"type":45,"value":46},"text","GKE Skill Creator",{"type":40,"tag":48,"props":49,"children":51},"h2",{"id":50},"overview",[52],{"type":45,"value":53},"Overview",{"type":40,"tag":55,"props":56,"children":57},"p",{},[58],{"type":45,"value":59},"This meta-skill acts as an interactive assistant to diagnose novel or complex\nGoogle Kubernetes Engine (GKE) issues and dynamically generate a specialized\ntroubleshooting skill tailored to the exact problem discovered.",{"type":40,"tag":48,"props":61,"children":63},{"id":62},"core-mandate-public-facing-output",[64],{"type":45,"value":65},"Core Mandate: Public-Facing Output",{"type":40,"tag":55,"props":67,"children":68},{},[69],{"type":45,"value":70},"During the investigation and research phase, you should leverage official GKE\ndocumentation, public Kubernetes issue trackers, and trusted SRE resources to\ndeeply understand the issue.",{"type":40,"tag":55,"props":72,"children":73},{},[74,80,82,88,90,97,99,105],{"type":40,"tag":75,"props":76,"children":77},"strong",{},[78],{"type":45,"value":79},"CRITICAL:",{"type":45,"value":81}," The ",{"type":40,"tag":83,"props":84,"children":85},"em",{},[86],{"type":45,"value":87},"generated skill",{"type":45,"value":89}," must be strictly public-facing. It MUST NOT\ncontain any internal codenames, acronyms, or references to internal Google\nsystems. All remediation logic must be expressed in terms of standard, public\ntools like ",{"type":40,"tag":91,"props":92,"children":94},"code",{"className":93},[],[95],{"type":45,"value":96},"kubectl",{"type":45,"value":98}," and ",{"type":40,"tag":91,"props":100,"children":102},{"className":101},[],[103],{"type":45,"value":104},"gcloud",{"type":45,"value":106},". This ensures the skill is usable by external\nGKE customers.",{"type":40,"tag":48,"props":108,"children":110},{"id":109},"workflow",[111],{"type":45,"value":112},"Workflow",{"type":40,"tag":114,"props":115,"children":117},"h3",{"id":116},"_1-capture-intent-investigate",[118],{"type":45,"value":119},"1. Capture Intent & Investigate",{"type":40,"tag":121,"props":122,"children":123},"ul",{},[124,138],{"type":40,"tag":125,"props":126,"children":127},"li",{},[128,130,136],{"type":45,"value":129},"Ask the user for specific GKE symptoms (e.g., Pods stuck in\n",{"type":40,"tag":91,"props":131,"children":133},{"className":132},[],[134],{"type":45,"value":135},"CrashLoopBackOff",{"type":45,"value":137},", Service 503 errors, Node pressure).",{"type":40,"tag":125,"props":139,"children":140},{},[141,143,148,150],{"type":45,"value":142},"Use ",{"type":40,"tag":75,"props":144,"children":145},{},[146],{"type":45,"value":147},"read-only",{"type":45,"value":149}," tools to pull live context:\n",{"type":40,"tag":121,"props":151,"children":152},{},[153,162,171,180,189],{"type":40,"tag":125,"props":154,"children":155},{},[156],{"type":40,"tag":91,"props":157,"children":159},{"className":158},[],[160],{"type":45,"value":161},"kubectl get \u003Cresource> -o yaml",{"type":40,"tag":125,"props":163,"children":164},{},[165],{"type":40,"tag":91,"props":166,"children":168},{"className":167},[],[169],{"type":45,"value":170},"kubectl describe \u003Cresource>",{"type":40,"tag":125,"props":172,"children":173},{},[174],{"type":40,"tag":91,"props":175,"children":177},{"className":176},[],[178],{"type":45,"value":179},"kubectl logs \u003Cpod> --tail=100",{"type":40,"tag":125,"props":181,"children":182},{},[183],{"type":40,"tag":91,"props":184,"children":186},{"className":185},[],[187],{"type":45,"value":188},"kubectl get events --sort-by='.lastTimestamp'",{"type":40,"tag":125,"props":190,"children":191},{},[192],{"type":40,"tag":91,"props":193,"children":195},{"className":194},[],[196],{"type":45,"value":197},"gcloud container clusters describe \u003Ccluster>",{"type":40,"tag":114,"props":199,"children":201},{"id":200},"_2-perform-deep-research",[202],{"type":45,"value":203},"2. Perform Deep Research",{"type":40,"tag":121,"props":205,"children":206},{},[207,212,217,222],{"type":40,"tag":125,"props":208,"children":209},{},[210],{"type":45,"value":211},"Before drafting the skill, perform deep research on the identified topic.",{"type":40,"tag":125,"props":213,"children":214},{},[215],{"type":45,"value":216},"Understand default argument values, potential side effects, and best\npractices for the commands you plan to include.",{"type":40,"tag":125,"props":218,"children":219},{},[220],{"type":45,"value":221},"Use trusted public sources to ensure accuracy.",{"type":40,"tag":125,"props":223,"children":224},{},[225,227],{"type":45,"value":226},"Use web search to find specific technical details from official\ndocumentation and trusted sources (e.g., Google Cloud, GKE, Kubernetes),\nsuch as:\n",{"type":40,"tag":121,"props":228,"children":229},{},[230,235,254,259],{"type":40,"tag":125,"props":231,"children":232},{},[233],{"type":45,"value":234},"Exact error message matches and their documented causes.",{"type":40,"tag":125,"props":236,"children":237},{},[238,240,245,247,252],{"type":45,"value":239},"Command references for ",{"type":40,"tag":91,"props":241,"children":243},{"className":242},[],[244],{"type":45,"value":96},{"type":45,"value":246}," or ",{"type":40,"tag":91,"props":248,"children":250},{"className":249},[],[251],{"type":45,"value":104},{"type":45,"value":253}," to verify syntax and flags.",{"type":40,"tag":125,"props":255,"children":256},{},[257],{"type":45,"value":258},"Known issues, limitations, or version-specific caveats.",{"type":40,"tag":125,"props":260,"children":261},{},[262],{"type":45,"value":263},"Official troubleshooting workflows and decision trees.",{"type":40,"tag":114,"props":265,"children":267},{"id":266},"_3-draft-the-skill",[268],{"type":45,"value":269},"3. Draft the Skill",{"type":40,"tag":121,"props":271,"children":272},{},[273,287,305,330,340,363,373],{"type":40,"tag":125,"props":274,"children":275},{},[276,278,285],{"type":45,"value":277},"Use the\n",{"type":40,"tag":279,"props":280,"children":282},"a",{"href":281},"references\u002Fgenerated_skill_skeleton.md",[283],{"type":45,"value":284},"generated_skill_skeleton.md",{"type":45,"value":286},"\ntemplate.",{"type":40,"tag":125,"props":288,"children":289},{},[290,295,297,303],{"type":40,"tag":75,"props":291,"children":292},{},[293],{"type":45,"value":294},"Cheat sheet Philosophy",{"type":45,"value":296},": Write the ",{"type":40,"tag":91,"props":298,"children":300},{"className":299},[],[301],{"type":45,"value":302},"SKILL.md",{"type":45,"value":304}," to be terse and opinionated.\nFocus on \"gotchas\", exact command patterns, and specific pitfalls rather\nthan long explanations.",{"type":40,"tag":125,"props":306,"children":307},{},[308,313,315,320,322,328],{"type":40,"tag":75,"props":309,"children":310},{},[311],{"type":45,"value":312},"Progressive Disclosure",{"type":45,"value":314},": For complex issues, avoid a monolithic\n",{"type":40,"tag":91,"props":316,"children":318},{"className":317},[],[319],{"type":45,"value":302},{"type":45,"value":321},". Suggest breaking down long lists of commands or log analysis\npatterns into separate reference artifacts in ",{"type":40,"tag":91,"props":323,"children":325},{"className":324},[],[326],{"type":45,"value":327},"references\u002F",{"type":45,"value":329},".",{"type":40,"tag":125,"props":331,"children":332},{},[333,338],{"type":40,"tag":75,"props":334,"children":335},{},[336],{"type":45,"value":337},"Make Descriptions Pushy",{"type":45,"value":339},": Ensure the generated skill's description\nexplicitly states when it should be used, covering variations of the\nproblem.",{"type":40,"tag":125,"props":341,"children":342},{},[343,348,350,355,356,361],{"type":40,"tag":75,"props":344,"children":345},{},[346],{"type":45,"value":347},"Fallback Remediation",{"type":45,"value":349},": If the primary method depends on specific\nhigh-level tools (e.g., MCP tools, API integrations) or environment\nconfigurations that might fail, include standard CLI fallback alternatives\n(like raw ",{"type":40,"tag":91,"props":351,"children":353},{"className":352},[],[354],{"type":45,"value":96},{"type":45,"value":246},{"type":40,"tag":91,"props":357,"children":359},{"className":358},[],[360],{"type":45,"value":104},{"type":45,"value":362}," commands) to achieve the same result.",{"type":40,"tag":125,"props":364,"children":365},{},[366,371],{"type":40,"tag":75,"props":367,"children":368},{},[369],{"type":45,"value":370},"Match User Intent",{"type":45,"value":372},": Instruct executing agents to match the user's intent:\nexplain\u002Finvestigate if requested, or execute remediation if asked to fix the\nissue.",{"type":40,"tag":125,"props":374,"children":375},{},[376,378],{"type":45,"value":377},"Ensure the draft contains:\n",{"type":40,"tag":121,"props":379,"children":380},{},[381,386,391,396,401,406],{"type":40,"tag":125,"props":382,"children":383},{},[384],{"type":45,"value":385},"Precise Symptoms.",{"type":40,"tag":125,"props":387,"children":388},{},[389],{"type":45,"value":390},"User Intent & Execution Rules.",{"type":40,"tag":125,"props":392,"children":393},{},[394],{"type":45,"value":395},"Step-by-step Diagnosis commands.",{"type":40,"tag":125,"props":397,"children":398},{},[399],{"type":45,"value":400},"Remediation (Fix) commands with impact descriptions.",{"type":40,"tag":125,"props":402,"children":403},{},[404],{"type":45,"value":405},"Verification steps.",{"type":40,"tag":125,"props":407,"children":408},{},[409,411,416],{"type":45,"value":410},"Technical Explanation (explaining ",{"type":40,"tag":83,"props":412,"children":413},{},[414],{"type":45,"value":415},"why",{"type":45,"value":417}," the fix works).",{"type":40,"tag":114,"props":419,"children":421},{"id":420},"_4-review-iterate",[422],{"type":45,"value":423},"4. Review & Iterate",{"type":40,"tag":121,"props":425,"children":426},{},[427,432,442],{"type":40,"tag":125,"props":428,"children":429},{},[430],{"type":45,"value":431},"Present the proposed diagnosis and the draft commands to the user.",{"type":40,"tag":125,"props":433,"children":434},{},[435,440],{"type":40,"tag":75,"props":436,"children":437},{},[438],{"type":45,"value":439},"Human-in-the-loop:",{"type":45,"value":441}," The user must approve the logic before finalization.",{"type":40,"tag":125,"props":443,"children":444},{},[445],{"type":45,"value":446},"Incorporate any user feedback or constraints.",{"type":40,"tag":114,"props":448,"children":450},{"id":449},"_5-finalize-handoff",[451],{"type":45,"value":452},"5. Finalize & Handoff",{"type":40,"tag":121,"props":454,"children":455},{},[456,468,478],{"type":40,"tag":125,"props":457,"children":458},{},[459,461,466],{"type":45,"value":460},"Once approved, provide the finalized ",{"type":40,"tag":91,"props":462,"children":464},{"className":463},[],[465],{"type":45,"value":302},{"type":45,"value":467}," content directly in the\nchat.",{"type":40,"tag":125,"props":469,"children":470},{},[471,476],{"type":40,"tag":75,"props":472,"children":473},{},[474],{"type":45,"value":475},"Handoff:",{"type":45,"value":477}," Instruct the user that they can use this diagnosis and\nremediation logic directly in their current session, or save it to a local\nfile for reference.",{"type":40,"tag":125,"props":479,"children":480},{},[481],{"type":45,"value":482},"Clarify that this process is for generating dynamic, session-specific skills\nand is distinct from adding permanent skills to the GKE-MCP codebase.",{"type":40,"tag":48,"props":484,"children":486},{"id":485},"safety-guardrails",[487],{"type":45,"value":488},"Safety Guardrails",{"type":40,"tag":121,"props":490,"children":491},{},[492,502,528],{"type":40,"tag":125,"props":493,"children":494},{},[495,500],{"type":40,"tag":75,"props":496,"children":497},{},[498],{"type":45,"value":499},"Read-Only Discovery:",{"type":45,"value":501}," Never execute modifying commands during the\ninvestigation phase.",{"type":40,"tag":125,"props":503,"children":504},{},[505,510,512,518,520,526],{"type":40,"tag":75,"props":506,"children":507},{},[508],{"type":45,"value":509},"Destructive Actions:",{"type":45,"value":511}," Generated skills MUST instruct the agent to seek\nexplicit human confirmation before running destructive commands (e.g.,\n",{"type":40,"tag":91,"props":513,"children":515},{"className":514},[],[516],{"type":45,"value":517},"kubectl delete",{"type":45,"value":519},", ",{"type":40,"tag":91,"props":521,"children":523},{"className":522},[],[524],{"type":45,"value":525},"gcloud container clusters update",{"type":45,"value":527},").",{"type":40,"tag":125,"props":529,"children":530},{},[531,536],{"type":40,"tag":75,"props":532,"children":533},{},[534],{"type":45,"value":535},"Impact Description:",{"type":45,"value":537}," Every remediation command must have a clear\nexplanation of what it does.",{"type":40,"tag":48,"props":539,"children":541},{"id":540},"references",[542],{"type":45,"value":543},"References",{"type":40,"tag":121,"props":545,"children":546},{},[547],{"type":40,"tag":125,"props":548,"children":549},{},[550],{"type":40,"tag":279,"props":551,"children":552},{"href":281},[553],{"type":45,"value":554},"Generated Skill Template",{"items":556,"total":652},[557,569,584,597,612,623,639],{"slug":558,"name":558,"fn":559,"description":560,"org":561,"tags":562,"stars":24,"repoUrl":25,"updatedAt":568},"custom-golden-image-discovery","discover golden base images for GKE nodes","Expert at discovering golden base images for GKE custom nodes using technical specs or context clues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[563,566,567],{"name":564,"slug":565,"type":16},"Deployment","deployment",{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},"2026-07-12T07:39:30.888879",{"slug":570,"name":570,"fn":571,"description":572,"org":573,"tags":574,"stars":24,"repoUrl":25,"updatedAt":583},"gke-ai-troubleshooting-handle-disruption-gpu-tpu","diagnose GPU and TPU workload disruptions","Diagnose and predict node disruption during Compute Engine host maintenance for GPU and TPU workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[575,578,579,580],{"name":576,"slug":577,"type":16},"Debugging","debugging",{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":581,"slug":582,"type":16},"Performance","performance","2026-07-28T05:34:18.149515",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":24,"repoUrl":25,"updatedAt":596},"gke-ai-troubleshooting-jobset-interruption","diagnose GKE JobSet interruptions","Systematically diagnose GKE JobSet interruptions, restarts, and preemptions for AI\u002FML training workloads. Identifies preemption events, maintenance interruptions, bad host VMs, unhealthy pods, and coordinator worker failures.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[590,591,592,593],{"name":576,"slug":577,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":594,"slug":595,"type":16},"Observability","observability","2026-07-12T07:40:04.511878",{"slug":598,"name":598,"fn":599,"description":600,"org":601,"tags":602,"stars":24,"repoUrl":25,"updatedAt":611},"gke-ai-troubleshooting-skill-creation-guide","create GKE troubleshooting skill bundles","Expert instructions for building high-quality GKE troubleshooting skills. Codifies Step 0 context rules, zero-hallucination signatures, and explicit LQL\u002FPromQL query requirements.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[603,606,607,608],{"name":604,"slug":605,"type":16},"Documentation","documentation",{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},{"name":609,"slug":610,"type":16},"Technical Writing","technical-writing","2026-07-12T07:39:50.73484",{"slug":613,"name":613,"fn":614,"description":615,"org":616,"tags":617,"stars":24,"repoUrl":25,"updatedAt":622},"gke-ai-troubleshooting-tpu-connection-failure-vbar-oom","diagnose GKE TPU connection failures","Diagnose and prevent `vbar_control_agent` segfaults and OOMs caused by race conditions during TPU device resets and frequent metrics collection (e.g. every 3s). Use when TPU slice initialization fails or `vbar_control_agent` crashes on TPU v6e nodes.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[618,619,620,621],{"name":576,"slug":577,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":581,"slug":582,"type":16},"2026-07-12T07:39:49.482979",{"slug":624,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":24,"repoUrl":25,"updatedAt":638},"gke-app-onboarding","containerize and deploy apps to GKE","Workflows for containerizing and deploying applications to GKE for the first time.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[629,632,633,634,635],{"name":630,"slug":631,"type":16},"Containers","containers",{"name":564,"slug":565,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":636,"slug":637,"type":16},"Onboarding","onboarding","2026-07-12T07:39:41.935837",{"slug":640,"name":640,"fn":641,"description":642,"org":643,"tags":644,"stars":24,"repoUrl":25,"updatedAt":651},"gke-backup-dr","configure GKE backup and disaster recovery","Workflows for configuring Backup for GKE and disaster recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[645,646,647,648],{"name":564,"slug":565,"type":16},{"name":9,"slug":8,"type":16},{"name":21,"slug":22,"type":16},{"name":649,"slug":650,"type":16},"Operations","operations","2026-07-12T07:39:34.806995",25,{"items":654,"total":833},[655,671,687,705,719,728,742,759,776,789,805,815],{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":668,"repoUrl":669,"updatedAt":670},"kb-search","search and extract local knowledge base documents","Allows listing, searching and extracting information from local knowledge base documents for information about tables\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[661,662,665],{"name":604,"slug":605,"type":16},{"name":663,"slug":664,"type":16},"Knowledge Base","knowledge-base",{"name":666,"slug":667,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":672,"name":673,"fn":674,"description":675,"org":676,"tags":677,"stars":668,"repoUrl":669,"updatedAt":686},"knowledgecatalogdiscoveryagent","knowledge_catalog_discovery_agent","search and rank Knowledge Catalog data entries","Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[678,681,682,685],{"name":679,"slug":680,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":683,"slug":684,"type":16},"Knowledge Management","knowledge-management",{"name":666,"slug":667,"type":16},"2026-07-12T07:38:22.196851",{"slug":688,"name":688,"fn":689,"description":690,"org":691,"tags":692,"stars":702,"repoUrl":703,"updatedAt":704},"contributing","contribute to Cloud Foundation Fabric","End-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[693,694,695,698,699],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":696,"slug":697,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":700,"slug":701,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":706,"name":706,"fn":707,"description":708,"org":709,"tags":710,"stars":702,"repoUrl":703,"updatedAt":718},"fabric-builder","generate Terraform code for Google Cloud","Generates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[711,712,715],{"name":9,"slug":8,"type":16},{"name":713,"slug":714,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":716,"slug":717,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":720,"name":720,"fn":721,"description":722,"org":723,"tags":724,"stars":702,"repoUrl":703,"updatedAt":727},"fast-0-org-setup-prereqs","prepare prerequisites for FAST 0-org-setup","Guides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[725,726],{"name":9,"slug":8,"type":16},{"name":649,"slug":650,"type":16},"2026-07-12T07:38:28.127148",{"slug":729,"name":729,"fn":730,"description":731,"org":732,"tags":733,"stars":739,"repoUrl":740,"updatedAt":741},"agent-aware-cli","design agent-aware command-line interfaces","Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user wants to build a CLI, apply CLI best practices, or use Go with Cobra and Viper.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[734,737,738],{"name":735,"slug":736,"type":16},"CLI","cli",{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},1150,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":743,"name":743,"fn":744,"description":745,"org":746,"tags":747,"stars":739,"repoUrl":740,"updatedAt":758},"build-mcp-genmedia","build and configure GenAI MCP servers","Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a container restart, or when \u002Ftmp has been wiped. The prebuilt binaries in \u002Fworkspace\u002F.local\u002Fbin\u002F have no exec bit and live on a noexec mount; this skill compiles fresh executables into \u002Ftmp\u002Fbin\u002F where execution is allowed.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[748,751,752,755],{"name":749,"slug":750,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":753,"slug":754,"type":16},"LLM","llm",{"name":756,"slug":757,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":760,"name":760,"fn":761,"description":762,"org":763,"tags":764,"stars":739,"repoUrl":740,"updatedAt":775},"genmedia-audio-engineer","synthesize and mix audio content","Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[765,768,771,772],{"name":766,"slug":767,"type":16},"Audio","audio",{"name":769,"slug":770,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":773,"slug":774,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":777,"name":777,"fn":778,"description":779,"org":780,"tags":781,"stars":739,"repoUrl":740,"updatedAt":788},"genmedia-image-artist","generate and edit AI images","Expert in AI image generation and editing. Use when the user needs high-quality textures, character-consistent visuals, or image-to-image editing using mcp-nanobanana-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[782,783,784,787],{"name":769,"slug":770,"type":16},{"name":9,"slug":8,"type":16},{"name":785,"slug":786,"type":16},"Image Generation","image-generation",{"name":773,"slug":774,"type":16},"2026-07-12T07:39:15.372822",{"slug":790,"name":790,"fn":791,"description":792,"org":793,"tags":794,"stars":739,"repoUrl":740,"updatedAt":804},"genmedia-producer","produce multi-step media content","Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[795,796,797,798,801],{"name":766,"slug":767,"type":16},{"name":769,"slug":770,"type":16},{"name":9,"slug":8,"type":16},{"name":799,"slug":800,"type":16},"Media","media",{"name":802,"slug":803,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":806,"name":806,"fn":807,"description":808,"org":809,"tags":810,"stars":739,"repoUrl":740,"updatedAt":814},"genmedia-video-editor","edit and compose video content","Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[811,812,813],{"name":769,"slug":770,"type":16},{"name":9,"slug":8,"type":16},{"name":802,"slug":803,"type":16},"2026-07-12T07:39:13.749081",{"slug":816,"name":816,"fn":817,"description":818,"org":819,"tags":820,"stars":739,"repoUrl":740,"updatedAt":832},"genmedia-voice-director","generate expressive text-to-speech with Gemini","Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS. Use this when the user needs virtual voice actor personas, expressive speech generation, or multiple variations of a voiceover (like \"take 3 on the bounce\").",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[821,822,823,826,829],{"name":766,"slug":767,"type":16},{"name":769,"slug":770,"type":16},{"name":824,"slug":825,"type":16},"Gemini","gemini",{"name":827,"slug":828,"type":16},"Speech","speech",{"name":830,"slug":831,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80]