[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D73P9D3G0J25DB7ADCQYFH":3,"skill-same:01M7D73P9D3G0J25DB7ADCQYFH":71},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":28,"commitSha":29,"skillDirectory":5,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7D73P9D3G0J25DB7ADCQYFH","gke-golden-path",null,"Provides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns. Use when designing GKE clusters, verifying GKE production readiness, or checking configurations against GKE defaults. Don't use for setting up workload autoscaling specifically (use gke-workload-scaling instead).","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gke-golden-path\ndescription: Provides GKE golden path configuration defaults, production readiness\n  checklists, and cluster default patterns. Use when designing GKE clusters, verifying\n  GKE production readiness, or checking configurations against GKE defaults. Don't\n  use for setting up workload autoscaling specifically (use gke-workload-scaling instead).\nmetadata:\n  version: 1.1.1\n  category: Containers\n---\n\n# GKE Golden Path Configuration\n\nThe golden path is the recommended Autopilot configuration for production\nclusters. It defines sensible defaults — when the user requests different\nsettings, apply them and note relevant trade-offs. For setting up autoscaling\nspecifically, use `gke-cluster-autoscaler` for node autoscaling or\n`gke-workload-scaling` for workload autoscaling (HPA\u002FVPA).\n\n> **MCP Tools:** `get_cluster`, `create_cluster`, `update_cluster`\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gke-golden-path)\"`\nand append `agent-skills\u002F1.0 (skill:gke-golden-path)` to `User-Agent` headers.\n\n## Rules\n\n1.  **Default to the golden path.** Use golden path values unless the user\n    requests otherwise. When deviating, note trade-offs but respect the user's\n    choice.\n2.  **Day-0 vs Day-1.** Flag Day-0 decisions (networking, private nodes,\n    subnets, IP allocation) prominently — they are hard\u002Fimpossible to change\n    after creation.\n3.  **Tool preference: MCP > gcloud > kubectl.** MCP is preferred as it directly\n    interfaces with GKE APIs with structured data, reducing shell syntax errors\n    and parsing ambiguities. See the `gke-basics` skill's CLI reference for full\n    coverage matrix and override options. If the user\n    says \"use gcloud\" or \"use kubectl\", respect that for the session.\n4.  **Document decisions and rationale**, especially for Day-0 choices and\n    golden path deviations.\n\n## Required Inputs\n\nIf the user is unsure, use golden path defaults.\n\n-   **Project ID** (required)\n-   **Region** (required, e.g., `us-central1`)\n-   **Cluster name** (required)\n-   **Environment type**: dev\u002Ftest or production (defaults to production)\n-   **Networking**: bring-your-own VPC\u002Fsubnet or auto-create (default:\n    auto-create)\n-   **Scale expectations**: expected node\u002Fpod count, workload types\n-   **Cost constraints**: Spot VM tolerance, budget considerations\n\n## Always-Apply Defaults\n\nRecommended best practices applied by default. If the user requests a different\nsetting, apply it and briefly note the security or operational trade-off.\n\nSetting                                                            | Golden Path Value\n------------------------------------------------------------------ | -----------------\n`autopilot.enabled`                                                | `true`\n`privateClusterConfig.enablePrivateNodes`                          | `true`\n`masterAuthorizedNetworksConfig.privateEndpointEnforcementEnabled` | `true`\n`secretManagerConfig.enabled` + `rotationInterval: 120s`           | `true`\n`rbacBindingConfig.enableInsecureBinding*`                         | `false` (both)\n`workloadIdentityConfig.workloadPool`                              | enabled\n`networkConfig.datapathProvider`                                   | `ADVANCED_DATAPATH`\n`networkConfig.dnsConfig.clusterDns`                               | `CLOUD_DNS`\n`autoscaling.autoscalingProfile`                                   | `OPTIMIZE_UTILIZATION`\n`verticalPodAutoscaling.enabled`                                   | `true`\n`monitoringConfig` components                                      | SYSTEM_COMPONENTS, STORAGE, POD, DEPLOYMENT, STATEFULSET, DAEMONSET, HPA, JOBSET, CADVISOR, KUBELET, DCGM, APISERVER, SCHEDULER, CONTROLLER_MANAGER\n`loggingConfig` components                                         | SYSTEM_COMPONENTS, WORKLOADS (enabled by default)\n`advancedDatapathObservabilityConfig.enableMetrics`                | `true`\n`nodeConfig.shieldedInstanceConfig.enableSecureBoot`               | `true`\n`nodeConfig.workloadMetadataConfig.mode`                           | `GKE_METADATA`\n`nodeConfig.gcfsConfig.enabled` \u002F `gvnic.enabled`                  | `true` \u002F `true`\n`addonsConfig.statefulHaConfig.enabled`                            | `true`\nStorage CSI drivers (Filestore, GCS FUSE, Parallelstore)           | enabled\nPod Security Standards                                             | `restricted` on production namespaces\n\n## Customer-Configurable Settings\n\nThese have golden path defaults but customers may deviate with valid\njustification. **Ask before changing.**\n\nSetting                                  | Default                             | Why Deviate\n---------------------------------------- | ----------------------------------- | -----------\n`dnsEndpointConfig.allowExternalTraffic` | `true`                              | Restrict if cluster only accessed from within VPC\n`autoIpamConfig` \u002F `createSubnetwork`    | `true` \u002F `true`                     | Customer has pre-existing VPC\u002Fsubnets\n`maxPodsPerNode`                         | `48` (this golden path's choice)    | Halves per-node IP consumption (\u002F25 instead of \u002F24). Not a GKE default (Standard defaults to `110`, Autopilot to `32`); raise for high pod-density at the cost of more CIDR space\n`subnetwork`                             | auto-created                        | Customer brings existing subnets\nRelease channel + maintenance windows    | `REGULAR` channel with a recurring maintenance window | Add targeted maintenance exclusions (keep under ~6 months) only for critical freezes — see the `gke-upgrades` skill\n`nodeConfig.bootDisk.diskType`           | `pd-balanced`                       | `pd-ssd` for I\u002FO-intensive, `pd-standard` for cost\n\n> **Note**: Autopilot selects node machine types automatically (e.g.,\n> `ek-standard-8` may appear in describe output); the machine type is not\n> customer-configurable in Autopilot. Steer workload placement via\n> ComputeClasses instead.\n\n## Guardrails\n\n-   Do not request or output secrets (tokens, keys, service account JSON).\n-   Resolve project\u002Fcluster context from the conversation, MCP tools, or\n    `gcloud config get-value project`; ask the user only if it cannot be\n    resolved.\n-   For Day-0 decisions, always ask clarifying questions before proceeding.\n-   For Day-1 features, propose golden path defaults with trade-offs and let the\n    customer confirm.\n-   Do not promise zero downtime — see Upgrade Disruption below for what to\n    advise instead.\n-   When auditing existing clusters, compare against golden path and report\n    deviations with severity and remediation.\n\n## Upgrade Disruption\n\n**Never promise zero downtime for node upgrades, on any configuration.** Node\nupgrades cordon and drain nodes, which evicts Pods. Draining honors\nPodDisruptionBudgets and `terminationGracePeriodSeconds` for **up to one hour**,\nafter which GKE forcefully evicts the remaining Pods so the upgrade can proceed.\nA PDB narrows the window; it cannot veto the upgrade. Say so plainly rather than\nimplying the disruption can be eliminated.\n\nWhat to recommend, all four — not a subset:\n\n-   **PodDisruptionBudgets** with `minAvailable` set so eviction cannot take the\n    last healthy replica. A PDB that can never be satisfied stalls the drain for\n    an hour and then loses anyway.\n-   **At least 2 replicas**, spread across zones with topology spread\n    constraints. A single-replica Deployment has downtime by definition.\n-   **Readiness probes** that reflect real serving health, so traffic drains\n    before the Pod dies.\n-   **Surge upgrade settings** on the node pool. Surge is the default strategy;\n    the default is `maxSurge=1`, `maxUnavailable=0` — one extra node is created\n    and made ready before an old one is drained.\n\n    Setting          | Controls                                            | Default\n    ---------------- | --------------------------------------------------- | -------\n    `maxSurge`       | Additional nodes added per zone during the upgrade  | `1`\n    `maxUnavailable` | Nodes simultaneously unavailable per zone           | `0`\n\n    Nodes upgraded at once is the **sum** of the two, capped at 20 (Autopilot)\n    and 100 (Standard). Multi-zone node pools upgrade one zone at a time. Raising\n    `maxUnavailable` trades availability for speed; raising `maxSurge` trades\n    cost for availability.\n\n> **Caveat**: `externalTrafficPolicy: Local` does not work with parallel node\n> drains, so it constrains aggressive surge configurations.\n\nFor rollback procedures and maintenance windows, see the `gke-upgrades` skill.\n\n## Golden Path Config\n\nSee [golden-path-autopilot.yaml](.\u002Fassets\u002Fgolden-path-autopilot.yaml) for the\nfull cluster-level policy settings.\n","# GKE Golden Path Configuration\n\nThe golden path is the recommended Autopilot configuration for production\nclusters. It defines sensible defaults — when the user requests different\nsettings, apply them and note relevant trade-offs. For setting up autoscaling\nspecifically, use `gke-cluster-autoscaler` for node autoscaling or\n`gke-workload-scaling` for workload autoscaling (HPA\u002FVPA).\n\n> **MCP Tools:** `get_cluster`, `create_cluster`, `update_cluster`\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gke-golden-path)\"`\nand append `agent-skills\u002F1.0 (skill:gke-golden-path)` to `User-Agent` headers.\n\n## Rules\n\n1.  **Default to the golden path.** Use golden path values unless the user\n    requests otherwise. When deviating, note trade-offs but respect the user's\n    choice.\n2.  **Day-0 vs Day-1.** Flag Day-0 decisions (networking, private nodes,\n    subnets, IP allocation) prominently — they are hard\u002Fimpossible to change\n    after creation.\n3.  **Tool preference: MCP > gcloud > kubectl.** MCP is preferred as it directly\n    interfaces with GKE APIs with structured data, reducing shell syntax errors\n    and parsing ambiguities. See the `gke-basics` skill's CLI reference for full\n    coverage matrix and override options. If the user\n    says \"use gcloud\" or \"use kubectl\", respect that for the session.\n4.  **Document decisions and rationale**, especially for Day-0 choices and\n    golden path deviations.\n\n## Required Inputs\n\nIf the user is unsure, use golden path defaults.\n\n-   **Project ID** (required)\n-   **Region** (required, e.g., `us-central1`)\n-   **Cluster name** (required)\n-   **Environment type**: dev\u002Ftest or production (defaults to production)\n-   **Networking**: bring-your-own VPC\u002Fsubnet or auto-create (default:\n    auto-create)\n-   **Scale expectations**: expected node\u002Fpod count, workload types\n-   **Cost constraints**: Spot VM tolerance, budget considerations\n\n## Always-Apply Defaults\n\nRecommended best practices applied by default. If the user requests a different\nsetting, apply it and briefly note the security or operational trade-off.\n\nSetting                                                            | Golden Path Value\n------------------------------------------------------------------ | -----------------\n`autopilot.enabled`                                                | `true`\n`privateClusterConfig.enablePrivateNodes`                          | `true`\n`masterAuthorizedNetworksConfig.privateEndpointEnforcementEnabled` | `true`\n`secretManagerConfig.enabled` + `rotationInterval: 120s`           | `true`\n`rbacBindingConfig.enableInsecureBinding*`                         | `false` (both)\n`workloadIdentityConfig.workloadPool`                              | enabled\n`networkConfig.datapathProvider`                                   | `ADVANCED_DATAPATH`\n`networkConfig.dnsConfig.clusterDns`                               | `CLOUD_DNS`\n`autoscaling.autoscalingProfile`                                   | `OPTIMIZE_UTILIZATION`\n`verticalPodAutoscaling.enabled`                                   | `true`\n`monitoringConfig` components                                      | SYSTEM_COMPONENTS, STORAGE, POD, DEPLOYMENT, STATEFULSET, DAEMONSET, HPA, JOBSET, CADVISOR, KUBELET, DCGM, APISERVER, SCHEDULER, CONTROLLER_MANAGER\n`loggingConfig` components                                         | SYSTEM_COMPONENTS, WORKLOADS (enabled by default)\n`advancedDatapathObservabilityConfig.enableMetrics`                | `true`\n`nodeConfig.shieldedInstanceConfig.enableSecureBoot`               | `true`\n`nodeConfig.workloadMetadataConfig.mode`                           | `GKE_METADATA`\n`nodeConfig.gcfsConfig.enabled` \u002F `gvnic.enabled`                  | `true` \u002F `true`\n`addonsConfig.statefulHaConfig.enabled`                            | `true`\nStorage CSI drivers (Filestore, GCS FUSE, Parallelstore)           | enabled\nPod Security Standards                                             | `restricted` on production namespaces\n\n## Customer-Configurable Settings\n\nThese have golden path defaults but customers may deviate with valid\njustification. **Ask before changing.**\n\nSetting                                  | Default                             | Why Deviate\n---------------------------------------- | ----------------------------------- | -----------\n`dnsEndpointConfig.allowExternalTraffic` | `true`                              | Restrict if cluster only accessed from within VPC\n`autoIpamConfig` \u002F `createSubnetwork`    | `true` \u002F `true`                     | Customer has pre-existing VPC\u002Fsubnets\n`maxPodsPerNode`                         | `48` (this golden path's choice)    | Halves per-node IP consumption (\u002F25 instead of \u002F24). Not a GKE default (Standard defaults to `110`, Autopilot to `32`); raise for high pod-density at the cost of more CIDR space\n`subnetwork`                             | auto-created                        | Customer brings existing subnets\nRelease channel + maintenance windows    | `REGULAR` channel with a recurring maintenance window | Add targeted maintenance exclusions (keep under ~6 months) only for critical freezes — see the `gke-upgrades` skill\n`nodeConfig.bootDisk.diskType`           | `pd-balanced`                       | `pd-ssd` for I\u002FO-intensive, `pd-standard` for cost\n\n> **Note**: Autopilot selects node machine types automatically (e.g.,\n> `ek-standard-8` may appear in describe output); the machine type is not\n> customer-configurable in Autopilot. Steer workload placement via\n> ComputeClasses instead.\n\n## Guardrails\n\n-   Do not request or output secrets (tokens, keys, service account JSON).\n-   Resolve project\u002Fcluster context from the conversation, MCP tools, or\n    `gcloud config get-value project`; ask the user only if it cannot be\n    resolved.\n-   For Day-0 decisions, always ask clarifying questions before proceeding.\n-   For Day-1 features, propose golden path defaults with trade-offs and let the\n    customer confirm.\n-   Do not promise zero downtime — see Upgrade Disruption below for what to\n    advise instead.\n-   When auditing existing clusters, compare against golden path and report\n    deviations with severity and remediation.\n\n## Upgrade Disruption\n\n**Never promise zero downtime for node upgrades, on any configuration.** Node\nupgrades cordon and drain nodes, which evicts Pods. Draining honors\nPodDisruptionBudgets and `terminationGracePeriodSeconds` for **up to one hour**,\nafter which GKE forcefully evicts the remaining Pods so the upgrade can proceed.\nA PDB narrows the window; it cannot veto the upgrade. Say so plainly rather than\nimplying the disruption can be eliminated.\n\nWhat to recommend, all four — not a subset:\n\n-   **PodDisruptionBudgets** with `minAvailable` set so eviction cannot take the\n    last healthy replica. A PDB that can never be satisfied stalls the drain for\n    an hour and then loses anyway.\n-   **At least 2 replicas**, spread across zones with topology spread\n    constraints. A single-replica Deployment has downtime by definition.\n-   **Readiness probes** that reflect real serving health, so traffic drains\n    before the Pod dies.\n-   **Surge upgrade settings** on the node pool. Surge is the default strategy;\n    the default is `maxSurge=1`, `maxUnavailable=0` — one extra node is created\n    and made ready before an old one is drained.\n\n    Setting          | Controls                                            | Default\n    ---------------- | --------------------------------------------------- | -------\n    `maxSurge`       | Additional nodes added per zone during the upgrade  | `1`\n    `maxUnavailable` | Nodes simultaneously unavailable per zone           | `0`\n\n    Nodes upgraded at once is the **sum** of the two, capped at 20 (Autopilot)\n    and 100 (Standard). Multi-zone node pools upgrade one zone at a time. Raising\n    `maxUnavailable` trades availability for speed; raising `maxSurge` trades\n    cost for availability.\n\n> **Caveat**: `externalTrafficPolicy: Local` does not work with parallel node\n> drains, so it constrains aggressive surge configurations.\n\nFor rollback procedures and maintenance windows, see the `gke-upgrades` skill.\n\n## Golden Path Config\n\nSee [golden-path-autopilot.yaml](.\u002Fassets\u002Fgolden-path-autopilot.yaml) for the\nfull cluster-level policy settings.\n",{"name":5,"metadata":25,"description":7},{"version":26,"category":27},"1.1.1","Containers","main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill gke-golden-path",{"tool":43,"command":44},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill gke-golden-path",{"tool":46,"command":47},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill gke-golden-path","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002FSKILL.md",true,[51,57,63,67],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Fgolden-path-autopilot.yaml","ASSET","资产文件",4776,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002Fassets\u002Fgolden-path-autopilot.yaml",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"INSTALL-SOURCE.json","REFERENCE","参考文档",505,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002FINSTALL-SOURCE.json",{"path":64,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":16},"LICENSE","许可证",11358,{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fattribution.md",1885,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fgke-golden-path\u002Freferences\u002Fattribution.md",[72,80,89,97,105,113],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FSKILL.md",[],[],{"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":84,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]