[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FSBFVYF4BQJ40C232C1X8":3,"skill-same:01M71FSBFVYF4BQJ40C232C1X8":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M71FSBFVYF4BQJ40C232C1X8","adk-infra-expert",null,"Use when provisioning Vertex AI ADK infrastructure with Terraform. Trigger with phrases like \"deploy ADK terraform\", \"agent engine infrastructure\", \"provision ADK agent\", \"vertex AI agent terraform\", or \"code execution sandbox terraform\". Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__BbgnsurfTech--adk-infra-expert\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"adk","infra","expert","adk infra expert","engine","when","code execution","controls","trigger","runtime","use","gcloud","Bash","vpc","execution","iam","code","ai agent","memory","sandbox","2026-11-10 10:12:30",false,"---\ndescription: Use when provisioning Vertex AI ADK infrastructure with Terraform. Trigger with phrases like \"deploy ADK terraform\", \"agent engine infrastructure\", \"provision ADK agent\", \"vertex AI agent terraform\", or \"code execution sandbox terraform\". Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.\nallowed-tools:\n- Read\n- Write\n- Edit\n- Grep\n- Glob\n- Bash(terraform:*)\n- Bash(gcloud:*)\nname: adk-infra-expert\nlicense: MIT\nversion: 1.0.0\n---\n\n## Prerequisites\n\nBefore using this skill, ensure:\n- Google Cloud project with billing enabled\n- Terraform 1.0+ installed\n- gcloud CLI authenticated with appropriate permissions\n- Vertex AI API enabled in target project\n- VPC Service Controls access policy created (for enterprise)\n- Understanding of Agent Engine architecture and requirements\n\n## Instructions\n\n1. **Initialize Terraform**: Set up backend for remote state storage\n2. **Configure Variables**: Define project_id, region, agent configuration\n3. **Provision VPC**: Create network infrastructure with Private Service Connect\n4. **Set Up IAM**: Create service accounts with least privilege roles\n5. **Deploy Agent Engine**: Configure runtime with code execution and memory bank\n6. **Enable VPC-SC**: Apply service perimeter for data exfiltration protection\n7. **Configure Monitoring**: Set up Cloud Monitoring dashboards and alerts\n8. **Validate Deployment**: Test agent endpoint and verify all components\n\n## Output\n\n**Agent Engine Deployment:**\n```hcl\n# {baseDir}\u002Fterraform\u002Fmain.tf\nresource \"google_vertex_ai_agent_runtime\" \"adk_agent\" {\n  project  = var.project_id\n  location = var.region\n  display_name = \"adk-production-agent\"\n\n  agent_config {\n    model = \"gemini-2.5-flash\"\n    code_execution {\n      enabled = true\n      state_ttl_days = 14\n      sandbox_type = \"SECURE_ISOLATED\"\n    }\n    memory_bank {\n      enabled = true\n    }\n  }\n\n  vpc_config {\n    vpc_network = google_compute_network.agent_vpc.id\n    private_service_connect {\n      enabled = true\n    }\n  }\n}\n```\n\n**VPC Service Controls:**\n```hcl\nresource \"google_access_context_manager_service_perimeter\" \"adk_perimeter\" {\n  parent = \"accessPolicies\u002F${var.access_policy_id}\"\n  title  = \"ADK Agent Engine Perimeter\"\n\n  status {\n    restricted_services = [\n      \"aiplatform.googleapis.com\",\n      \"run.googleapis.com\"\n    ]\n  }\n}\n```\n\n**IAM Configuration:**\n```hcl\nresource \"google_service_account\" \"adk_agent\" {\n  account_id   = \"adk-agent-sa\"\n  display_name = \"ADK Agent Service Account\"\n}\n\nresource \"google_project_iam_member\" \"agent_identity\" {\n  project = var.project_id\n  role    = \"roles\u002Faiplatform.agentUser\"\n  member  = \"serviceAccount:${google_service_account.adk_agent.email}\"\n}\n```\n\n## Error Handling\n\n**Terraform State Lock**\n- Error: \"Error acquiring the state lock\"\n- Solution: Use `terraform force-unlock \u003Clock-id>` or wait for lock expiry\n\n**API Not Enabled**\n- Error: \"Vertex AI API has not been used\"\n- Solution: Enable with `gcloud services enable aiplatform.googleapis.com`\n\n**VPC-SC Configuration**\n- Error: \"Access denied by VPC Service Controls\"\n- Solution: Add project to service perimeter or adjust ingress\u002Fegress policies\n\n**IAM Permission Denied**\n- Error: \"does not have required permission\"\n- Solution: Grant roles\u002Fowner temporarily to service account running Terraform\n\n**Resource Already Exists**\n- Error: \"Resource already exists\"\n- Solution: Import existing resource or use data source instead\n\n## Resources\n\n- Agent Engine: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fagent-engine\u002Foverview\n- VPC-SC: https:\u002F\u002Fcloud.google.com\u002Fvpc-service-controls\u002Fdocs\n- Terraform Google Provider: https:\u002F\u002Fregistry.terraform.io\u002Fproviders\u002Fhashicorp\u002Fgoogle\u002Flatest\n- ADK Terraform examples in {baseDir}\u002Fexamples\u002F\n","## Prerequisites\n\nBefore using this skill, ensure:\n- Google Cloud project with billing enabled\n- Terraform 1.0+ installed\n- gcloud CLI authenticated with appropriate permissions\n- Vertex AI API enabled in target project\n- VPC Service Controls access policy created (for enterprise)\n- Understanding of Agent Engine architecture and requirements\n\n## Instructions\n\n1. **Initialize Terraform**: Set up backend for remote state storage\n2. **Configure Variables**: Define project_id, region, agent configuration\n3. **Provision VPC**: Create network infrastructure with Private Service Connect\n4. **Set Up IAM**: Create service accounts with least privilege roles\n5. **Deploy Agent Engine**: Configure runtime with code execution and memory bank\n6. **Enable VPC-SC**: Apply service perimeter for data exfiltration protection\n7. **Configure Monitoring**: Set up Cloud Monitoring dashboards and alerts\n8. **Validate Deployment**: Test agent endpoint and verify all components\n\n## Output\n\n**Agent Engine Deployment:**\n```hcl\n# {baseDir}\u002Fterraform\u002Fmain.tf\nresource \"google_vertex_ai_agent_runtime\" \"adk_agent\" {\n  project  = var.project_id\n  location = var.region\n  display_name = \"adk-production-agent\"\n\n  agent_config {\n    model = \"gemini-2.5-flash\"\n    code_execution {\n      enabled = true\n      state_ttl_days = 14\n      sandbox_type = \"SECURE_ISOLATED\"\n    }\n    memory_bank {\n      enabled = true\n    }\n  }\n\n  vpc_config {\n    vpc_network = google_compute_network.agent_vpc.id\n    private_service_connect {\n      enabled = true\n    }\n  }\n}\n```\n\n**VPC Service Controls:**\n```hcl\nresource \"google_access_context_manager_service_perimeter\" \"adk_perimeter\" {\n  parent = \"accessPolicies\u002F${var.access_policy_id}\"\n  title  = \"ADK Agent Engine Perimeter\"\n\n  status {\n    restricted_services = [\n      \"aiplatform.googleapis.com\",\n      \"run.googleapis.com\"\n    ]\n  }\n}\n```\n\n**IAM Configuration:**\n```hcl\nresource \"google_service_account\" \"adk_agent\" {\n  account_id   = \"adk-agent-sa\"\n  display_name = \"ADK Agent Service Account\"\n}\n\nresource \"google_project_iam_member\" \"agent_identity\" {\n  project = var.project_id\n  role    = \"roles\u002Faiplatform.agentUser\"\n  member  = \"serviceAccount:${google_service_account.adk_agent.email}\"\n}\n```\n\n## Error Handling\n\n**Terraform State Lock**\n- Error: \"Error acquiring the state lock\"\n- Solution: Use `terraform force-unlock \u003Clock-id>` or wait for lock expiry\n\n**API Not Enabled**\n- Error: \"Vertex AI API has not been used\"\n- Solution: Enable with `gcloud services enable aiplatform.googleapis.com`\n\n**VPC-SC Configuration**\n- Error: \"Access denied by VPC Service Controls\"\n- Solution: Add project to service perimeter or adjust ingress\u002Fegress policies\n\n**IAM Permission Denied**\n- Error: \"does not have required permission\"\n- Solution: Grant roles\u002Fowner temporarily to service account running Terraform\n\n**Resource Already Exists**\n- Error: \"Resource already exists\"\n- Solution: Import existing resource or use data source instead\n\n## Resources\n\n- Agent Engine: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fagent-engine\u002Foverview\n- VPC-SC: https:\u002F\u002Fcloud.google.com\u002Fvpc-service-controls\u002Fdocs\n- Terraform Google Provider: https:\u002F\u002Fregistry.terraform.io\u002Fproviders\u002Fhashicorp\u002Fgoogle\u002Flatest\n- ADK Terraform examples in {baseDir}\u002Fexamples\u002F\n",{"name":5,"license":14,"version":48,"description":7,"allowed-tools":49},"1.0.0",[50,51,52,53,54,55,56],"Read","Write","Edit","Grep","Glob","Bash(terraform:*)","Bash(gcloud:*)","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__BbgnsurfTech--adk-infra-expert",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add JSGforever\u002Fskillguard --skill adk-infra-expert",{"tool":70,"command":71},"bunx","bunx skills add JSGforever\u002Fskillguard --skill adk-infra-expert",{"tool":73,"command":74},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill adk-infra-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__BbgnsurfTech--adk-infra-expert\u002FSKILL.md",true,[78],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Finit-terraform.sh","SCRIPT","脚本",2106,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__BbgnsurfTech--adk-infra-expert\u002Fscripts\u002Finit-terraform.sh",[85,115,130,155,175,196],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":95,"publishedAt":43},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[96,97,98,99,100,101,102,103,104,105,106,107,28,108,109,110,111,112,113,114],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":126,"publishedAt":43},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[127,128,129],"data","data exfiltrator","files",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":43},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[137,138,139,140,27,141,142,143,144,145,146,147,148,149,150,35,151,152,153,154],"time","real time collaboration engine","real time collaboration","collaboration","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","activate","optimizer","react","streaming",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":164,"publishedAt":43},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[161],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[145,165,152,153,166,167,168,169,25,170,137,171,172,149,35,39,151,154,173,174],"react performance optimizer","react performance","performance optimizer","app","nextjs","re","render","2025","router","strategies",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":43},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[181],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},[183,154,184,185,186,187,145,137,188,189,190,35,151,152,191,153,192,193,194,195],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":207,"publishedAt":43},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[202,205,206],{"categoryNo":203,"categoryName":204,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},[208,209,210,211,212,213,214,143,25,215,216,217,151,174,218,195,219,220,221,222],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]