[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XD47N29B4W4JA8CB1EGDAN":3,"skill-same:01M6XD47N29B4W4JA8CB1EGDAN":123},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6XD47N29B4W4JA8CB1EGDAN","kubernetes-specialist",null,"Deep-dive Kubernetes troubleshooting, workload design, and cluster health review. Use when you need a structured investigation of a cluster issue, a design review of Kubernetes manifests, or a health audit of a namespace or workload. Triggers on: \"debug kubernetes\", \"why is my pod\", \"review my manifests\", \"cluster health\", \"kubernetes design review\", \"k8s audit\".","kaiohenricunha\u002Fdotbabel","kaiohenricunha","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69804490?v=4","01M6XCZD37W0KPCDGEA40Y610V","Kaio Cunha","01M6XCZD7SX714D114H3ZPNW09",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"kubernetes","specialist","kubernetes specialist","deep","when","manifests","my","you","cluster","problem","k8s","design","issue","context","read","Bash","why","audit","workload","review","2026-11-10 10:12:30",false,"---\n# dotbabel:generated projection=sha256:fb142e51962e06aff81c35b99b1eae2a8346efc07f919fafa1dedee1fb52dcfc source=skills\u002Fkubernetes-specialist\u002FSKILL.md — do not edit directly\nallowed-tools: Read Grep Glob Bash\nargument-hint: \u003Ccluster context, namespace, or problem description>\ndescription: |\n  Deep-dive Kubernetes troubleshooting, workload design, and cluster health review. Use when you need a structured investigation of a cluster issue, a design review of Kubernetes manifests, or a health audit of a namespace or workload. Triggers on: \"debug kubernetes\", \"why is my pod\", \"review my manifests\", \"cluster health\", \"kubernetes design review\", \"k8s audit\".\nname: kubernetes-specialist\n---\n\n# Kubernetes Specialist\n\nStructured investigation for Kubernetes workloads. Five phases: gather context, diagnose,\nroot-cause, recommend, verify.\n\n## Arguments\n\n- `$0` — cluster context, namespace, problem description, or manifest path. Required.\n\n---\n\n## Phase 1: Context Gathering\n\nEstablish what you are working with before touching any cluster.\n\n1. Glob for YAML\u002FHelm templates in the working directory: `**\u002F*.yaml`, `**\u002Ftemplates\u002F**\u002F*.yaml`.\n2. Read `kustomization.yaml` or `Chart.yaml` if present to understand the structure.\n3. If a cluster context is available, run:\n   ```bash\n   kubectl config current-context\n   kubectl get nodes -o wide\n   kubectl get namespaces\n   ```\n4. Note the namespace(s) in scope. Scope all subsequent commands to `--namespace \u003Cns>` to\n   avoid reading unrelated resources.\n\n---\n\n## Phase 2: Diagnosis\n\nGather the signals that describe the current state.\n\n**For pod or workload issues:**\n\n```bash\nkubectl get pods -n \u003Cns> -o wide\nkubectl describe pod \u003Cpod> -n \u003Cns>\nkubectl get events -n \u003Cns> --sort-by=.lastTimestamp | tail -30\nkubectl logs \u003Cpod> -n \u003Cns> --previous --tail=100   # if CrashLoopBackOff\n```\n\n**For networking issues:**\n\n```bash\nkubectl get services -n \u003Cns>\nkubectl get ingress -n \u003Cns>\nkubectl get networkpolicies -n \u003Cns>\n```\n\n**For resource pressure:**\n\n```bash\nkubectl top nodes\nkubectl top pods -n \u003Cns>\nkubectl describe node \u003Cnode>   # check Conditions and Allocatable vs Requests\n```\n\n**For RBAC issues:**\n\n```bash\nkubectl auth can-i --list --as=system:serviceaccount:\u003Cns>:\u003Csa>\nkubectl get rolebindings,clusterrolebindings -n \u003Cns> -o wide\n```\n\n---\n\n## Phase 3: Root-Cause Analysis\n\nFor each signal found in Phase 2, trace to its cause:\n\n| Symptom             | Common Causes                                                    | Check                               |\n| ------------------- | ---------------------------------------------------------------- | ----------------------------------- |\n| `Pending` pod       | Insufficient resources, node selector, taint\u002Ftoleration mismatch | `kubectl describe pod` → Events     |\n| `CrashLoopBackOff`  | App crash, misconfigured probe, missing env\u002Fsecret               | `kubectl logs --previous`           |\n| `ImagePullBackOff`  | Bad tag, registry auth, network policy blocking egress           | `kubectl describe pod` → Events     |\n| `OOMKilled`         | Memory limit too low, memory leak                                | `kubectl describe pod` → Last State |\n| Service not routing | Selector mismatch, port mismatch, NetworkPolicy blocking         | `kubectl get endpoints`             |\n| 5xx from Ingress    | Upstream pod not ready, probe too aggressive, readiness failing  | Ingress controller logs             |\n\nCite `resource\u002Fname` or `file:line` for every finding.\n\n---\n\n## Phase 4: Recommendations\n\nPresent findings as a prioritized list:\n\n```\n[CRITICAL] \u003Ctitle>\nResource: \u003Ckind\u002Fname> or \u003Cfile:line>\nIssue: \u003Cone sentence>\nEvidence: \u003Ccommand output or manifest snippet>\nFix: \u003Cspecific change>\n\n[WARNING] \u003Ctitle>\n...\n\n[INFO] \u003Ctitle>\n...\n```\n\n- Order: CRITICAL → WARNING → INFO.\n- For each fix, explain the trade-off if there is a meaningful alternative.\n- Reference relevant docs in `references\u002F` where applicable.\n\n---\n\n## Phase 5: Verification\n\nAfter fixes are applied:\n\n1. Confirm pods reach `Running` and pass readiness:\n   ```bash\n   kubectl rollout status deployment\u002F\u003Cname> -n \u003Cns>\n   kubectl get pods -n \u003Cns> -w   # watch for 30 s\n   ```\n2. Check events are clean:\n   ```bash\n   kubectl get events -n \u003Cns> --sort-by=.lastTimestamp | tail -10\n   ```\n3. Validate probes are passing — no `Liveness probe failed` in events.\n4. For networking changes, confirm endpoints are populated:\n   ```bash\n   kubectl get endpoints \u003Cservice> -n \u003Cns>\n   ```\n5. For RBAC changes, re-run `kubectl auth can-i` to confirm access is as expected.\n\n---\n\n## Reference Docs\n\nConsult `references\u002F` for decision guides:\n\n| File                       | When to use                                            |\n| -------------------------- | ------------------------------------------------------ |\n| `workload-types.md`        | Choosing Deployment vs StatefulSet vs DaemonSet vs Job |\n| `resource-sizing.md`       | Setting requests\u002Flimits, VPA vs HPA                    |\n| `networking.md`            | Service types, Ingress, NetworkPolicy, DNS             |\n| `rbac.md`                  | Role design, ServiceAccount least-privilege            |\n| `storage.md`               | PV\u002FPVC, StorageClass, stateful workloads               |\n| `observability.md`         | Probes, metrics, logging patterns                      |\n| `security-hardening.md`    | Pod security, admission control, image signing         |\n| `helm-patterns.md`         | Chart structure, values, hook ordering                 |\n| `ci-cd-integration.md`     | GitOps, manifest generation in pipelines               |\n| `troubleshooting.md`       | Failure modes and diagnostic commands                  |\n| `deployment-strategies.md` | Rolling, blue\u002Fgreen, canary trade-offs                 |\n","# Kubernetes Specialist\n\nStructured investigation for Kubernetes workloads. Five phases: gather context, diagnose,\nroot-cause, recommend, verify.\n\n## Arguments\n\n- `$0` — cluster context, namespace, problem description, or manifest path. Required.\n\n---\n\n## Phase 1: Context Gathering\n\nEstablish what you are working with before touching any cluster.\n\n1. Glob for YAML\u002FHelm templates in the working directory: `**\u002F*.yaml`, `**\u002Ftemplates\u002F**\u002F*.yaml`.\n2. Read `kustomization.yaml` or `Chart.yaml` if present to understand the structure.\n3. If a cluster context is available, run:\n   ```bash\n   kubectl config current-context\n   kubectl get nodes -o wide\n   kubectl get namespaces\n   ```\n4. Note the namespace(s) in scope. Scope all subsequent commands to `--namespace \u003Cns>` to\n   avoid reading unrelated resources.\n\n---\n\n## Phase 2: Diagnosis\n\nGather the signals that describe the current state.\n\n**For pod or workload issues:**\n\n```bash\nkubectl get pods -n \u003Cns> -o wide\nkubectl describe pod \u003Cpod> -n \u003Cns>\nkubectl get events -n \u003Cns> --sort-by=.lastTimestamp | tail -30\nkubectl logs \u003Cpod> -n \u003Cns> --previous --tail=100   # if CrashLoopBackOff\n```\n\n**For networking issues:**\n\n```bash\nkubectl get services -n \u003Cns>\nkubectl get ingress -n \u003Cns>\nkubectl get networkpolicies -n \u003Cns>\n```\n\n**For resource pressure:**\n\n```bash\nkubectl top nodes\nkubectl top pods -n \u003Cns>\nkubectl describe node \u003Cnode>   # check Conditions and Allocatable vs Requests\n```\n\n**For RBAC issues:**\n\n```bash\nkubectl auth can-i --list --as=system:serviceaccount:\u003Cns>:\u003Csa>\nkubectl get rolebindings,clusterrolebindings -n \u003Cns> -o wide\n```\n\n---\n\n## Phase 3: Root-Cause Analysis\n\nFor each signal found in Phase 2, trace to its cause:\n\n| Symptom             | Common Causes                                                    | Check                               |\n| ------------------- | ---------------------------------------------------------------- | ----------------------------------- |\n| `Pending` pod       | Insufficient resources, node selector, taint\u002Ftoleration mismatch | `kubectl describe pod` → Events     |\n| `CrashLoopBackOff`  | App crash, misconfigured probe, missing env\u002Fsecret               | `kubectl logs --previous`           |\n| `ImagePullBackOff`  | Bad tag, registry auth, network policy blocking egress           | `kubectl describe pod` → Events     |\n| `OOMKilled`         | Memory limit too low, memory leak                                | `kubectl describe pod` → Last State |\n| Service not routing | Selector mismatch, port mismatch, NetworkPolicy blocking         | `kubectl get endpoints`             |\n| 5xx from Ingress    | Upstream pod not ready, probe too aggressive, readiness failing  | Ingress controller logs             |\n\nCite `resource\u002Fname` or `file:line` for every finding.\n\n---\n\n## Phase 4: Recommendations\n\nPresent findings as a prioritized list:\n\n```\n[CRITICAL] \u003Ctitle>\nResource: \u003Ckind\u002Fname> or \u003Cfile:line>\nIssue: \u003Cone sentence>\nEvidence: \u003Ccommand output or manifest snippet>\nFix: \u003Cspecific change>\n\n[WARNING] \u003Ctitle>\n...\n\n[INFO] \u003Ctitle>\n...\n```\n\n- Order: CRITICAL → WARNING → INFO.\n- For each fix, explain the trade-off if there is a meaningful alternative.\n- Reference relevant docs in `references\u002F` where applicable.\n\n---\n\n## Phase 5: Verification\n\nAfter fixes are applied:\n\n1. Confirm pods reach `Running` and pass readiness:\n   ```bash\n   kubectl rollout status deployment\u002F\u003Cname> -n \u003Cns>\n   kubectl get pods -n \u003Cns> -w   # watch for 30 s\n   ```\n2. Check events are clean:\n   ```bash\n   kubectl get events -n \u003Cns> --sort-by=.lastTimestamp | tail -10\n   ```\n3. Validate probes are passing — no `Liveness probe failed` in events.\n4. For networking changes, confirm endpoints are populated:\n   ```bash\n   kubectl get endpoints \u003Cservice> -n \u003Cns>\n   ```\n5. For RBAC changes, re-run `kubectl auth can-i` to confirm access is as expected.\n\n---\n\n## Reference Docs\n\nConsult `references\u002F` for decision guides:\n\n| File                       | When to use                                            |\n| -------------------------- | ------------------------------------------------------ |\n| `workload-types.md`        | Choosing Deployment vs StatefulSet vs DaemonSet vs Job |\n| `resource-sizing.md`       | Setting requests\u002Flimits, VPA vs HPA                    |\n| `networking.md`            | Service types, Ingress, NetworkPolicy, DNS             |\n| `rbac.md`                  | Role design, ServiceAccount least-privilege            |\n| `storage.md`               | PV\u002FPVC, StorageClass, stateful workloads               |\n| `observability.md`         | Probes, metrics, logging patterns                      |\n| `security-hardening.md`    | Pod security, admission control, image signing         |\n| `helm-patterns.md`         | Chart structure, values, hook ordering                 |\n| `ci-cd-integration.md`     | GitOps, manifest generation in pipelines               |\n| `troubleshooting.md`       | Failure modes and diagnostic commands                  |\n| `deployment-strategies.md` | Rolling, blue\u002Fgreen, canary trade-offs                 |\n",{"name":5,"description":54,"allowed-tools":55,"argument-hint":56},"Deep-dive Kubernetes troubleshooting, workload design, and cluster health review. Use when you need a structured investigation of a cluster issue, a design review of Kubernetes manifests, or a health audit of a namespace or workload. Triggers on: \"debug kubernetes\", \"why is my pod\", \"review my manifests\", \"cluster health\", \"kubernetes design review\", \"k8s audit\".\n","Read Grep Glob Bash","\u003Ccluster context, namespace, or problem description>","main","91c337164997b99943fbcc64e8e362577b67bc81","examples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha","I'm a Platform\u002FInfra engineer who happens to work in cybersec and write Go code.","2026-10-26 14:12:51",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill kubernetes-specialist",{"tool":70,"command":71},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill kubernetes-specialist",{"tool":73,"command":74},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill kubernetes-specialist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002FSKILL.md",true,[78,84,88,92,96,100,104,107,111,115,119],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fci-cd-integration.md","REFERENCE","参考文档",2301,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fci-cd-integration.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fdeployment-strategies.md",2632,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fdeployment-strategies.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fhelm-patterns.md",2226,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fhelm-patterns.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fnetworking.md",2310,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fnetworking.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fobservability.md",2324,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fobservability.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Frbac.md",2380,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Frbac.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":106},"references\u002Fresource-sizing.md","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fresource-sizing.md",{"path":108,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fsecurity-hardening.md",2599,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fsecurity-hardening.md",{"path":112,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fstorage.md",2069,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fstorage.md",{"path":116,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Ftroubleshooting.md",2387,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Ftroubleshooting.md",{"path":120,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Fworkload-types.md",1857,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fkubernetes-specialist\u002Freferences\u002Fworkload-types.md",[124,151,179,200,218,239],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":49},"01M6XDQ7QMASPFZ355MYKCD06T","yolo","Start temporary autonomy for the current task or an explicit scope with a required --for expiry. Codex permits scoped pushes, merges, deploys, and releases after strict testing and validation; Full access is a separate runtime setting. Claude Code uses a session permission hook with a protected-action denylist.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fyolo\u002FSKILL.md",[130],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[126,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150],"testing","merge","code","start","access","session","ops","autonomy","releases","permission","full","runtime","scope","devex","hook","true","action","for","scoped",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":163,"publishedAt":49},"01M6XDQ1N21VE4KH98JWGZ7GN9","veracity-audit","Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time. All source paths are supplied via flags — no defaults, no project assumptions. Subcommands: audit (full pipeline walk), score-check (scoring math only), gate-check (gate coverage only), source-trace \u003Clabel> (single source end-to-end). Invoke when: \"audit pipeline\", \"veracity check\", \"scoring math correct?\", \"check gates\", \"trace source\", \"verify quality gates\", \"formula correct?\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fveracity-audit\u002FSKILL.md",[157,160],{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":161,"categoryName":162,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务",[46,164,132,48,165,166,44,167,168,169,170,171,172,173,174,175,176,177,178,33],"veracity audit","data pipeline","pipeline","math","coverage","only","engineer","formula","scoring","time","project","worker","end","at","invoke",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":49},"01M6XDPVDKBR376C06CEK9BC5S","validate-spec","Audit an already-implemented spec against the codebase. Walks each constraint (ARCH-N, PERF-N, KD-N, etc.) and acceptance criterion, grounds findings in file:line evidence, runs the spec.json acceptance_commands, and writes a single audit doc to docs\u002Faudits\u002F. Use whenever the user asks to \"validate a spec\", \"audit a spec\", \"check if spec is implemented\", \"verify the spec is done\", \"is this spec really done\", or otherwise wants closure on spec-driven work. Read-only against the spec — produces an audit, never modifies the spec itself.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-spec\u002FSKILL.md",[],[186,187,188,132,48,189,190,46,44,191,43,192,169,193,194,195,196,197,198,199],"spec","validate","validate spec","run","acceptance","work","never","max","done","arch","line","2025","spec-driven","closure",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":49},"01M6XDPMMECH82RAW553Y94HDS","terragrunt-specialist","Deep-dive Terragrunt hierarchy review, DRY pattern audits, and run-all orchestration analysis. Use for structured investigations of multi-environment Terragrunt layouts, dependency graphs, remote state config, and hook correctness. Triggers on: \"Terragrunt audit\", \"run-all review\", \"dependency block\", \"DRY pattern review\", \"env hierarchy audit\", \"mock_outputs\", \"terragrunt hooks\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterragrunt-specialist\u002FSKILL.md",[206],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[208,30,209,48,210,211,189,46,212,44,43,213,214,193,32,215,197,216,177,217],"terragrunt","terragrunt specialist","orchestration","debugging","analysis","dependency","hooks","dry","remote","hierarchy",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":231,"publishedAt":49},"01M6XDPFJS2HGSE13RXF1HV8S7","terraform-specialist","Deep-dive Terraform architecture review, module design, state management, and migration. Use for structured investigations of Terraform workspaces, provider configuration, module coupling, import workflows, and test coverage. Triggers on: \"Terraform audit\", \"module review\", \"state management\", \"Terraform import\", \"workspace design\", \"provider config review\", \"Terraform testing\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-specialist\u002FSKILL.md",[224,227,228],{"categoryNo":225,"categoryName":226,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":229,"categoryName":230,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[232,233,30,132,40,48,234,235,236,211,46,44,43,168,237,238,32,38,197,177],"terraform","terraform specialist","workflows","architecture","architecture review","test coverage","workspaces",{"skillNo":240,"name":186,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":248,"publishedAt":49},"01M6XDP7V6H8WYPSXVEKYE6HJ6","Create structured engineering specs through interactive pairing. Use when the user wants to create a spec, design doc, technical specification, architecture document, RFC, or engineering plan. Triggers on \"let's spec this out\", \"create a spec\", \"design doc\", \"write a technical plan\", \"plan the architecture\". Works for greenfield and brownfield projects. Outputs to docs\u002Fspecs\u002F.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[244,245],{"categoryNo":229,"categoryName":230,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":246,"categoryName":247,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[186,40,249,235,250,251,252,253,254,255,256,257,258,259,260,149,261,262,263,264],"component","create","plan","projects","write","interactive","use","document","specification","triggers","opus","technical specification","trade-offs","technical plan","outputs","frontier"]