Loading...
Loading...
Found 10 Skills
Validate and auto-repair YAML frontmatter on brain pages. Catches malformed pages before they enter the brain (missing closing
Diagnose and resolve cluster-wide GKE TPU node pool creation or scale-up failures caused by Compute Engine reservation stockouts (GCE_STOCKOUT, ZONE_RESOURCE_POOL_EXHAUSTED) when existing unhealthy or NotReady TPU node pools in the cluster have node auto-repair disabled and hold reserved TPU capacity. Use when TPU node pool creation or scale-up fails with GCE_STOCKOUT, ZONE_RESOURCE_POOL_EXHAUSTED, or ZONE_RESOURCE_POOL_EXHAUSTED_WITH_DETAILS despite having a specific Compute Engine TPU reservation. Don't use for general pod scheduling without a TPU reservation or workload-level container crashes.
Runtime per-test healing with evidence: multi-attribute selector healing, environment-aware diagnosis, flake classification, quarantine management, and confidence-scored auto-repair. Goes beyond simple locator fallbacks to cover action-level healing, data healing, and observable repair workflows. Use when: "flaky test," "test stability," "self-healing locator," "broken locator recovery," "unreliable test," "quarantine flaky test." Not for: bulk regenerating selectors after a planned UI refactor — use selector-drift-recovery (this skill heals ONE test at runtime; that one rewrites many tests offline). Not for: classifying/clustering CI failures into bug reports — use ai-bug-triage. Related: playwright-automation, selector-drift-recovery, ci-cd-integration, qa-metrics, ai-bug-triage.
Generate complete automated TDD development pipelines from a todolist.md file. Creates a self-contained directory with autodev.sh, system_prompt.md, gate_check.sh, and task cards that drive Claude Code through spec-anchored, gate-guarded, card-by-card development — fully automated with no human in the loop. Features: TDD 5-step closure, 3-level AI decision protocol, independent acceptance verification, auto-repair on test failure, Bug Hunt phase for post-development P0/P1/P2 bug scanning and fixing. Use when user says "帮我生成 autodev", "create autodev for", "generate autodev pipeline", or needs to turn a todolist.md into an automated gated TDD development pipeline.
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for healthy nodes, pod-only application crashes, or routine GKE upgrades.
Use when the user operates Alibaba Cloud Container Service for Kubernetes (ACK). Covers cluster lifecycle (create / modify / delete / upgrade), node pools & nodes (create, modify, delete, repair, fix CVE), addons (install / upgrade / uninstall), KubeConfig & RBAC (issue for RAM user, grant / revoke), security & policy (CVE scan/fix, policy governance, KMS, delete protection), logging / audit / alerting, intelligent O&M (check / inspect / diagnosis / auto-repair), async tasks (track / pause / resume / cancel), templates, autoscaling, tags & quotas. Triggers: create / upgrade / delete ACK cluster, migrate to Pro, scale nodepool, fix node CVE, install / remove addon, get / revoke kubeconfig, grant RBAC, enable audit log, run inspection, diagnose cluster, track task_id, debug cs error, Forbidden.RAM, kubectl cannot connect. Terms: ACK, container service, k8s cluster, nodepool, addon, AutoMode, Terway, Flannel, ForRegion, kubeconfig, RBAC, CVE.
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure via OPENCLI_DIAGNOSTIC, patching the adapter, and retrying. Works with any AI agent.
Run health checks on the Ruflo installation and fix common issues
Use when skills fail to activate, produce errors, need structural validation, or the library needs a health audit. Diagnose YAML frontmatter, XML sections, config.json schema, file structure, and cross-skill dependencies.
Diagnose GKE TPU VM instances stuck in Compute Engine repair (REPAIRING state) after host errors, maintenance events, or faulty host reports in single-host, multi-host, dynamic slicing, and TPU All Capacity mode node pools. Use when TPU instances in a slice node pool remain in REPAIRING, host error events appear in audit logs, or TPU slices are unschedulable due to a VM in repair. Don't use for nodes reporting Ready: Unknown when no VM is in REPAIRING (use gke-ai-troubleshooting-node-unresponsive-timeout), other NotReady nodes when no VM is in REPAIRING (use gke-node-notready), Pending Pods when all nodes are Ready (use gke-workload-troubleshooting), JobSet preemption events (use gke-ai-troubleshooting-jobset-interruption), or Slice custom resource lifecycle failures (use gke-ai-troubleshooting-tpu-dynamic-slices-monitoring).