[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MBZZDF55KGP17K3D5ZQ3B":3,"skill-same:01M75MBZZDF55KGP17K3D5ZQ3B":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M75MBZZDF55KGP17K3D5ZQ3B","aws-compute",null,"Provisions, scales, and operates Amazon EC2 virtual-machine workloads: instance-type selection (Graviton\u002FArm64, burstable T credits, GPU, instance store vs EBS), launch templates, Auto Scaling groups (scaling policies, instance refresh, mixed instances, Spot, warm pools, lifecycle hooks), IMDSv2, placement groups, Elastic IPs, AMI lifecycle, and Systems Manager fleet operations (Session Manager, Run Command, Patch Manager). Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity, CPU-credit\u002Fsurplus charges, IMDSv2 401s, instances stuck in Pending:Wait, ASG not replacing unhealthy instances, status-check failures, SSH refused\u002Ftimed out, or instances missing as SSM managed nodes. For a single secure instance launch, the launching-ec2-instance-with-best-practices skill is more appropriate; for instance profiles, see setting-up-ec2-instance-profiles; for Image Builder, see amazon-ec2-image-builder. Does NOT cover Lambda, ECS\u002FFargate, EKS, VPC\u002FALB\u002FNLB design, or IAM policy authoring.","jkomyno\u002F.dotfiles","jkomyno","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12381818?v=4","01M75MA8EK2FJFP0274GEB1RNB","Alberto Schiabel","01M75MA8FKQN5GTW089WN3838D",5,"MIT","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: aws-compute\ndescription: >-\n  Provisions, scales, and operates Amazon EC2 virtual-machine workloads: instance-type\n  selection (Graviton\u002FArm64, burstable T credits, GPU, instance store vs EBS), launch\n  templates, Auto Scaling groups (scaling policies, instance refresh, mixed instances,\n  Spot, warm pools, lifecycle hooks), IMDSv2, placement groups, Elastic IPs, AMI lifecycle,\n  and Systems Manager fleet operations (Session Manager, Run Command, Patch Manager).\n  Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity, CPU-credit\u002Fsurplus\n  charges, IMDSv2 401s, instances stuck in Pending:Wait, ASG not replacing unhealthy\n  instances, status-check failures, SSH refused\u002Ftimed out, or instances missing as\n  SSM managed nodes. For a single secure instance launch, the launching-ec2-instance-with-best-practices\n  skill is more appropriate; for instance profiles, see setting-up-ec2-instance-profiles;\n  for Image Builder, see amazon-ec2-image-builder. Does NOT cover Lambda, ECS\u002FFargate,\n  EKS, VPC\u002FALB\u002FNLB design, or IAM policy authoring.\nversion: 2\n---\n\n# Amazon EC2 Compute\n\nBest experience with the AWS MCP server; also works with the AWS CLI alone — no hard dependency on either.\n\n## Critical Warnings\n\n**Launch configurations are deprecated** and do not support current EC2 instance types; new accounts cannot create them. Use launch templates for every new Auto Scaling group. See [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**ASGs ignore ELB health checks by default**: An Auto Scaling group only uses EC2 status checks unless you set `--health-check-type ELB`. Without it, instances failing the load balancer's health check stay in service forever. See [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**IMDSv2 hop limit breaks containers**: the default `HttpPutResponseHopLimit` of 1 makes the IMDSv2 token PUT response fail to reach a containerized process (the extra hop exceeds the response TTL), so the token request times out. Set `HttpPutResponseHopLimit=2` for bridge\u002Fawsvpc container workloads. (If IMDSv2 is *required*, a subsequent tokenless GET returns `401`; if optional, it silently falls back to IMDSv1.) See [provisioning.md](references\u002Fprovisioning.md).\n\n**T3\u002FT3a\u002FT4g default to unlimited mode**: Unlike T2 (standard), these burst without throttling but bill surplus CPU credits when 24h-average CPU exceeds baseline — a silent cost leak. See [instance-selection.md](references\u002Finstance-selection.md).\n\n**Instance store is ephemeral**: Data on instance store volumes is lost on stop, hibernate, terminate, instance-type change, and host failure — it survives only a reboot. Put anything durable on EBS\u002FEFS\u002FS3. See [instance-selection.md](references\u002Finstance-selection.md).\n\n## Which do you need?\n\n| If you're deciding... | Guidance |\n|-----------------------|----------|\n| Instance family \u002F size \u002F Graviton \u002F GPU \u002F burstable | [instance-selection.md](references\u002Finstance-selection.md) — start with the workload→family table |\n| How to define instances once and reuse (launch template) | [provisioning.md](references\u002Fprovisioning.md) |\n| How to run many instances that scale automatically | [auto-scaling.md](references\u002Fauto-scaling.md) |\n| How to access\u002Fpatch\u002Fmanage instances without SSH keys | [systems-manager.md](references\u002Fsystems-manager.md) |\n\n## Quick Navigation\n\n| You want to... | Go to |\n|----------------|-------|\n| Pick an instance type, Graviton vs x86, burstable credits, GPU, instance store vs EBS | [instance-selection.md](references\u002Finstance-selection.md) |\n| Create a launch template, user data, key pairs, IMDSv2, placement groups, Elastic IPs | [provisioning.md](references\u002Fprovisioning.md) |\n| Set up or fix an Auto Scaling group, scaling policies, instance refresh, Spot, lifecycle hooks | [auto-scaling.md](references\u002Fauto-scaling.md) |\n| Get SSH-less access, patch a fleet, or fix an instance not showing as a managed node | [systems-manager.md](references\u002Fsystems-manager.md) |\n| Create, share, or retire (deprecate\u002Fdisable\u002Fderegister) an AMI | [ami-management.md](references\u002Fami-management.md) |\n| Fix something broken (can't connect, status-check fail, capacity error, stuck instances) | [troubleshooting.md](references\u002Ftroubleshooting.md) |\n\n## Common Workflows\n\n**\"Stand up an autoscaling web fleet\"** → Create a launch template (AMI, type, IMDSv2), then an ASG referencing it with `--health-check-type ELB` and a target-tracking policy, see [auto-scaling.md](references\u002Fauto-scaling.md). For the public entry point, secure the load balancer (TLS\u002FACM, WAF, security response headers) per the Security Considerations below and the load-balancer notes in [auto-scaling.md](references\u002Fauto-scaling.md) — the load-balancer build itself belongs to `aws-networking`.\n\n**\"Roll out a new AMI to my fleet\"** → New launch template version → instance refresh; pin a numeric launch-template version so rollback works, see [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**\"Connect to a private instance without a bastion\"** → Give the instance SSM permissions (an instance profile with `AmazonSSMManagedInstanceCore`, or account-level DHMC) plus a network path, then use Session Manager, see [systems-manager.md](references\u002Fsystems-manager.md).\n\n**\"Cut EC2 cost\"** → Right-size (burstable vs fixed-performance), Graviton where the app supports Arm64, Spot with `price-capacity-optimized` for fault-tolerant fleets, release idle Elastic IPs, see [instance-selection.md](references\u002Finstance-selection.md).\n\n## Troubleshooting\n\n| Symptom | Likely cause | Quick fix |\n|---------|-------------|-----------|\n| SSH \"Connection timed out\" | Network path (SG\u002FNACL\u002Froute\u002Fno public IP) | Open TCP 22 from your IP; check route to IGW; verify public IP — see [troubleshooting.md](references\u002Ftroubleshooting.md) |\n| SSH \"Connection refused\" | Host: sshd down or still booting | Wait for boot; check sshd\u002Fport via Session Manager or serial console |\n| `InsufficientInstanceCapacity` | AWS lacks capacity of that type in the AZ (NOT a quota) | Try another AZ \u002F instance type \u002F retry; don't request a quota increase |\n| `InstanceLimitExceeded` | vCPU quota reached (this IS a quota) | Request a Service Quotas increase for the instance family |\n| ASG never replaces LB-unhealthy instances | Health check type still EC2 | Set `--health-check-type ELB` |\n| Instances stuck in `Pending:Wait`, terminated after ~1h | Lifecycle hook never completed (heartbeat 3600s, default ABANDON) | Call `complete-lifecycle-action` CONTINUE, or set DefaultResult CONTINUE |\n| System status check failed | AWS host\u002Fhardware | Stop\u002Fstart to migrate to new hardware (reboot won't) |\n| Instance status check failed | Instance OS\u002Fnetwork config | Reboot or fix the OS\u002Fnetwork config |\n\nFull tables and more errors in [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Security Considerations\n\n- **Enforce IMDSv2** (`HttpTokens=required`) on launch templates to block SSRF-based credential theft; set the account-level default per Region (applies to new launches only).\n- **Prefer Session Manager over inbound SSH** — no open port 22, no key management, and a CloudTrail record of session API calls; enable Session Manager session logging to CloudWatch Logs\u002FS3 (off by default) to capture the in-session commands themselves — see [systems-manager.md](references\u002Fsystems-manager.md).\n- **Use instance profiles, never embedded credentials**; scope the role to least privilege.\n- **Encrypt EBS\u002FAMIs**; to share an encrypted AMI cross-account, re-encrypt under a customer-managed KMS key (the default `aws\u002Febs` key can't be shared).\n- **Enable CloudTrail** in all Regions to audit EC2\u002FASG\u002FSSM API activity, and alarm on sensitive actions (security-group changes, `RunInstances`\u002F`TerminateInstances` from unexpected principals) so unauthorized changes surface.\n- **For public-facing web fleets**, encrypt traffic in transit with an ACM certificate on the load balancer's HTTPS listener and add AWS WAF for defense in depth against common web exploits — the load-balancer\u002FWAF setup itself lives in `aws-networking`.\n- For hardening beyond this guidance, see [AWS EC2 security best practices](https:\u002F\u002Fdocs.aws.amazon.com\u002FAWSEC2\u002Flatest\u002FUserGuide\u002Fec2-security.html) and CIS Benchmarks for the guest OS.\n\n## Not Covered By This Skill\n\n- **Launching a single hardened instance with best-practice defaults** → use the `launching-ec2-instance-with-best-practices` skill\n- **Creating IAM roles \u002F instance profiles for EC2** → use the `setting-up-ec2-instance-profiles` skill\n- **Building AMIs with an Image Builder pipeline** → use the `amazon-ec2-image-builder` skill\n- **Lambda \u002F serverless** → `aws-serverless`; **ECS\u002FFargate** → `aws-containers`; **EKS\u002FKubernetes** → `kubernetes`\n- **VPC, subnets, ALB\u002FNLB, endpoints** → `aws-networking` or built-in knowledge\n- **IAM policy logic and CloudWatch dashboards\u002Fagent setup** → `aws-iam`, `aws-observability`\n","# Amazon EC2 Compute\n\nBest experience with the AWS MCP server; also works with the AWS CLI alone — no hard dependency on either.\n\n## Critical Warnings\n\n**Launch configurations are deprecated** and do not support current EC2 instance types; new accounts cannot create them. Use launch templates for every new Auto Scaling group. See [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**ASGs ignore ELB health checks by default**: An Auto Scaling group only uses EC2 status checks unless you set `--health-check-type ELB`. Without it, instances failing the load balancer's health check stay in service forever. See [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**IMDSv2 hop limit breaks containers**: the default `HttpPutResponseHopLimit` of 1 makes the IMDSv2 token PUT response fail to reach a containerized process (the extra hop exceeds the response TTL), so the token request times out. Set `HttpPutResponseHopLimit=2` for bridge\u002Fawsvpc container workloads. (If IMDSv2 is *required*, a subsequent tokenless GET returns `401`; if optional, it silently falls back to IMDSv1.) See [provisioning.md](references\u002Fprovisioning.md).\n\n**T3\u002FT3a\u002FT4g default to unlimited mode**: Unlike T2 (standard), these burst without throttling but bill surplus CPU credits when 24h-average CPU exceeds baseline — a silent cost leak. See [instance-selection.md](references\u002Finstance-selection.md).\n\n**Instance store is ephemeral**: Data on instance store volumes is lost on stop, hibernate, terminate, instance-type change, and host failure — it survives only a reboot. Put anything durable on EBS\u002FEFS\u002FS3. See [instance-selection.md](references\u002Finstance-selection.md).\n\n## Which do you need?\n\n| If you're deciding... | Guidance |\n|-----------------------|----------|\n| Instance family \u002F size \u002F Graviton \u002F GPU \u002F burstable | [instance-selection.md](references\u002Finstance-selection.md) — start with the workload→family table |\n| How to define instances once and reuse (launch template) | [provisioning.md](references\u002Fprovisioning.md) |\n| How to run many instances that scale automatically | [auto-scaling.md](references\u002Fauto-scaling.md) |\n| How to access\u002Fpatch\u002Fmanage instances without SSH keys | [systems-manager.md](references\u002Fsystems-manager.md) |\n\n## Quick Navigation\n\n| You want to... | Go to |\n|----------------|-------|\n| Pick an instance type, Graviton vs x86, burstable credits, GPU, instance store vs EBS | [instance-selection.md](references\u002Finstance-selection.md) |\n| Create a launch template, user data, key pairs, IMDSv2, placement groups, Elastic IPs | [provisioning.md](references\u002Fprovisioning.md) |\n| Set up or fix an Auto Scaling group, scaling policies, instance refresh, Spot, lifecycle hooks | [auto-scaling.md](references\u002Fauto-scaling.md) |\n| Get SSH-less access, patch a fleet, or fix an instance not showing as a managed node | [systems-manager.md](references\u002Fsystems-manager.md) |\n| Create, share, or retire (deprecate\u002Fdisable\u002Fderegister) an AMI | [ami-management.md](references\u002Fami-management.md) |\n| Fix something broken (can't connect, status-check fail, capacity error, stuck instances) | [troubleshooting.md](references\u002Ftroubleshooting.md) |\n\n## Common Workflows\n\n**\"Stand up an autoscaling web fleet\"** → Create a launch template (AMI, type, IMDSv2), then an ASG referencing it with `--health-check-type ELB` and a target-tracking policy, see [auto-scaling.md](references\u002Fauto-scaling.md). For the public entry point, secure the load balancer (TLS\u002FACM, WAF, security response headers) per the Security Considerations below and the load-balancer notes in [auto-scaling.md](references\u002Fauto-scaling.md) — the load-balancer build itself belongs to `aws-networking`.\n\n**\"Roll out a new AMI to my fleet\"** → New launch template version → instance refresh; pin a numeric launch-template version so rollback works, see [auto-scaling.md](references\u002Fauto-scaling.md).\n\n**\"Connect to a private instance without a bastion\"** → Give the instance SSM permissions (an instance profile with `AmazonSSMManagedInstanceCore`, or account-level DHMC) plus a network path, then use Session Manager, see [systems-manager.md](references\u002Fsystems-manager.md).\n\n**\"Cut EC2 cost\"** → Right-size (burstable vs fixed-performance), Graviton where the app supports Arm64, Spot with `price-capacity-optimized` for fault-tolerant fleets, release idle Elastic IPs, see [instance-selection.md](references\u002Finstance-selection.md).\n\n## Troubleshooting\n\n| Symptom | Likely cause | Quick fix |\n|---------|-------------|-----------|\n| SSH \"Connection timed out\" | Network path (SG\u002FNACL\u002Froute\u002Fno public IP) | Open TCP 22 from your IP; check route to IGW; verify public IP — see [troubleshooting.md](references\u002Ftroubleshooting.md) |\n| SSH \"Connection refused\" | Host: sshd down or still booting | Wait for boot; check sshd\u002Fport via Session Manager or serial console |\n| `InsufficientInstanceCapacity` | AWS lacks capacity of that type in the AZ (NOT a quota) | Try another AZ \u002F instance type \u002F retry; don't request a quota increase |\n| `InstanceLimitExceeded` | vCPU quota reached (this IS a quota) | Request a Service Quotas increase for the instance family |\n| ASG never replaces LB-unhealthy instances | Health check type still EC2 | Set `--health-check-type ELB` |\n| Instances stuck in `Pending:Wait`, terminated after ~1h | Lifecycle hook never completed (heartbeat 3600s, default ABANDON) | Call `complete-lifecycle-action` CONTINUE, or set DefaultResult CONTINUE |\n| System status check failed | AWS host\u002Fhardware | Stop\u002Fstart to migrate to new hardware (reboot won't) |\n| Instance status check failed | Instance OS\u002Fnetwork config | Reboot or fix the OS\u002Fnetwork config |\n\nFull tables and more errors in [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Security Considerations\n\n- **Enforce IMDSv2** (`HttpTokens=required`) on launch templates to block SSRF-based credential theft; set the account-level default per Region (applies to new launches only).\n- **Prefer Session Manager over inbound SSH** — no open port 22, no key management, and a CloudTrail record of session API calls; enable Session Manager session logging to CloudWatch Logs\u002FS3 (off by default) to capture the in-session commands themselves — see [systems-manager.md](references\u002Fsystems-manager.md).\n- **Use instance profiles, never embedded credentials**; scope the role to least privilege.\n- **Encrypt EBS\u002FAMIs**; to share an encrypted AMI cross-account, re-encrypt under a customer-managed KMS key (the default `aws\u002Febs` key can't be shared).\n- **Enable CloudTrail** in all Regions to audit EC2\u002FASG\u002FSSM API activity, and alarm on sensitive actions (security-group changes, `RunInstances`\u002F`TerminateInstances` from unexpected principals) so unauthorized changes surface.\n- **For public-facing web fleets**, encrypt traffic in transit with an ACM certificate on the load balancer's HTTPS listener and add AWS WAF for defense in depth against common web exploits — the load-balancer\u002FWAF setup itself lives in `aws-networking`.\n- For hardening beyond this guidance, see [AWS EC2 security best practices](https:\u002F\u002Fdocs.aws.amazon.com\u002FAWSEC2\u002Flatest\u002FUserGuide\u002Fec2-security.html) and CIS Benchmarks for the guest OS.\n\n## Not Covered By This Skill\n\n- **Launching a single hardened instance with best-practice defaults** → use the `launching-ec2-instance-with-best-practices` skill\n- **Creating IAM roles \u002F instance profiles for EC2** → use the `setting-up-ec2-instance-profiles` skill\n- **Building AMIs with an Image Builder pipeline** → use the `amazon-ec2-image-builder` skill\n- **Lambda \u002F serverless** → `aws-serverless`; **ECS\u002FFargate** → `aws-containers`; **EKS\u002FKubernetes** → `kubernetes`\n- **VPC, subnets, ALB\u002FNLB, endpoints** → `aws-networking` or built-in knowledge\n- **IAM policy logic and CloudWatch dashboards\u002Fagent setup** → `aws-iam`, `aws-observability`\n",{"name":5,"version":24,"description":7},2,"main","9e160012bf175f264279507807d206dbe17e9aac","target\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute",3,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles","https:\u002F\u002Fgithub.com\u002Fjkomyno","https:\u002F\u002Fjkomyno.dev","AX engineer working on agentic dev tools. Previously Senior SWE @prisma & mathematical optimisation @cvut. International tech speaker.","2026-11-14 21:45:28",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add jkomyno\u002F.dotfiles --skill aws-compute",{"tool":40,"command":41},"bunx","bunx skills add jkomyno\u002F.dotfiles --skill aws-compute",{"tool":43,"command":44},"pnpm","pnpm dlx skills add jkomyno\u002F.dotfiles --skill aws-compute","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002FSKILL.md",true,[48,54,60,64,68,72,76],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},".aws-skill-metadata","OTHER","其他",18,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002F.aws-skill-metadata",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fami-management.md","REFERENCE","参考文档",6008,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Fami-management.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fauto-scaling.md",10345,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Fauto-scaling.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Finstance-selection.md",5816,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Finstance-selection.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fprovisioning.md",9391,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Fprovisioning.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fsystems-manager.md",7561,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Fsystems-manager.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Ftroubleshooting.md",5797,"https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Faws-compute\u002Freferences\u002Ftroubleshooting.md",[81,89,96,103,110,118],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"01M7DY814SMBRJFBZF4NTY2ZCK","potetomode","Load pstack's poteto-mode workflow for concise responses, deliberate delegation, simple code, and verified work. Use when the user requests potetomode or \u002Fpotetomode.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Fpotetomode\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":88},"01M7DY7YG4V89VKPN5ZQ64EXAV","bro","Restate the last assistant message in plain, concise language using pstack's bro skill. Use when the user requests bro or \u002Fbro.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Fbro\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M75MJWVSC460HY537YJ5W6MX","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M75MJSKK9BZGSTMZ308DM1HA","using-exe-dev","Operate exe.dev virtual machines. Use when the task mentions exe.dev, exe VMs, *.exe.xyz hosts, or exe.dev infrastructure.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Fusing-exe-dev\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M75MJNT911P56SE62DZSQTX8","unlazy","Prove substantial work complete with file-backed gates and runnable checks. Use for exhaustive completion, a Depth Tree, or a completion ledger.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Funlazy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Funlazy\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M75MJHN22B60A6BNT0W4H7NH","sync-skills","Sync vendored third-party skills against their upstream repositories, re-apply local patches, and flag new upstream skills. Invoke explicitly with \u002Fsync-skills.","https:\u002F\u002Fgithub.com\u002Fjkomyno\u002F.dotfiles\u002Fblob\u002Fmain\u002Ftarget\u002Fhome\u002F.agents\u002Fskills\u002Fsync-skills\u002FSKILL.md",[],[]]