All authors
Claude Skills by go-steer
github.com/go-steer40 skills0 installs94 views
- Autonomous SetupWalk a user through configuring an unattended core-agent — single-agent monitor or multi-agent team. Use when the user asks to "set up an autonomous agent", "run core-agent unattended", "configure a monitor", "build a multi-agent team", "deploy core-agent to production", "set up a long-running agent", asks how to bound budgets, asks about crash-resume, or describes a goal that obviously needs unattended execution (e.g., "watch the deploy", "monitor SLO breaches", "scan the fleet every hour").Votes: 0GitHub stars: 7
- Cli SetupWalk a user through configuring core-agent for interactive (TUI / REPL) use against their project. Use when the user asks to "set up core-agent", "configure core-agent for my repo", "help me get started with core-agent", "what should my AGENTS.md look like", "what permissions should I use", "how do I add a skill", or asks any question implying they're customizing core-agent for the first time or expanding an existing configuration.Votes: 0GitHub stars: 7
- Library EmbeddingWalk a Go developer through embedding core-agent in their own binary. Use when the user asks "how do I embed core-agent", "use core-agent as a library", "build my own agent on core-agent", "agent.New", "custom prompter", "custom tools", "custom provider", "HTTP-served agent", "integrate core-agent into [Go project]", or asks any question implying they want to use the Go API rather than the bundled CLI.Votes: 0GitHub stars: 7
- Gke TriageRunbook for triaging a GKE workload whose pods will not start.Votes: 0GitHub stars: 7
- Gke ObservabilityAudit whether a GKE cluster and its workloads are observable — logging, metrics, managed Prometheus, control-plane metrics, tracing. Read-only; produces findings, the evidence for them, and proposed changes the parent applies.Votes: 0GitHub stars: 7
- Gke ReliabilityAssess the availability posture of a GKE workload — disruption budgets, health probes, zone spreading, graceful shutdown, maintenance windows. Read-only; produces findings, the evidence for them, and proposed manifest changes the parent applies.Votes: 0GitHub stars: 7
- Gke StorageDiagnose GKE storage problems — unbound PVCs, mount failures, exhausted volumes, wrong access modes or disk types. Read-only; produces a root cause, the evidence for it, and a proposed manifest change the parent applies.Votes: 0GitHub stars: 7
- Gke Workload ScalingDiagnose scaling behavior of a GKE workload — replica counts, HPA and VPA configuration, resource requests, cluster autoscaler headroom. Read-only; produces a finding, the evidence for it, and a proposed scaling change the parent applies.Votes: 0GitHub stars: 7
- Gke Workload SecurityAudit the security posture of a GKE cluster and its workloads — Workload Identity, network policy, node hardening, Pod Security Standards, secret handling. Read-only; produces findings, the evidence for them, and proposed hardening the parent applies.Votes: 0GitHub stars: 7
- Gke Workload TroubleshootingDiagnose a GKE workload failure you were delegated — image pull failures, crash loops, OOMKills, scheduling failures, mount errors, connectivity timeouts. Read-only; produces a root cause, the evidence for it, and a proposed manifest patch.Votes: 0GitHub stars: 7
- K8s TriageHandle a Kubernetes event inject shaped like {"kind": "k8s-event", "reason": "<Reason>", "namespace": "...", ...}. Loads the reason-specific reference and drives the diagnose → verify → propose loop for any k8s failure mode. Falls back to a generic playbook (references/_fallback.md) for unknown reasons.Votes: 0GitHub stars: 7
- Gke ObservabilityWorkflows for setting up and auditing observability (logging, monitoring, tracing) on GKE.Votes: 0GitHub stars: 7
- Gke ReliabilityWorkflows for ensuring high availability and reliability of GKE workloads.Votes: 0GitHub stars: 7
- Gke StorageGuidance on managing storage in Google Kubernetes Engine (GKE) clusters.Votes: 0GitHub stars: 7
- Gke Workload ScalingSpecific workflows for scaling GKE workloads using HPA and VPA, as well as best practices for autoscaling configuration.Votes: 0GitHub stars: 7
- Gke Workload SecurityWorkflows for auditing and hardening the security of GKE workloads.Votes: 0GitHub stars: 7
- Gke Workload TroubleshootingSystematic Standard Operating Procedure (SOP) for diagnosing GKE workload failures, crash loops, resource OOMs, mounting errors, and connectivity timeouts.Votes: 0GitHub stars: 7
- Cluster Agent LifecycleCreate, delegate to, and tear down per-cluster Cluster Agent Hermes profiles. Use whenever a GKE cluster is onboarded or deleted, or whenever a single-cluster runtime debugging/operations task should be delegated to that cluster's Cluster Agent.Votes: 0GitHub stars: 7
- Fleet AuditPublish the findings of an autonomous fleet audit as one continuously-rewritten GitHub issue per audit stream, and propose fixes as narrow remediation pull requests.Votes: 0GitHub stars: 7
- Github Issue Resolver> [!CAUTION] **INVIOLABLE SAFETY RED LINE:** NEVER inspect, comment on, edit, > close, or modify any issue labeled `status:escalation-needed`, `agent:ignore`, > or `agent:audit`. Issues labeled `status:escalation-needed` are locked for > human intervention and must NEVER be modified or closed autonomously. Issues > labeled `agent:audit` are `fleet-audit` ledgers, rewritten in place by that > skill on every run — touching one corrupts a report the audit owns. This skill delegates all determini...Votes: 0GitHub stars: 7
- Gke App OnboardingWorkflows for containerizing and deploying applications to GKE for the first time.Votes: 0GitHub stars: 7
- Gke Backup DrWorkflows for configuring Backup for GKE and disaster recovery.Votes: 0GitHub stars: 7
- Gke Cluster CreatorGuides the user through creating GKE clusters using pre-defined templates (Standard, Autopilot, GPU/AI).Votes: 0GitHub stars: 7
- Gke Cluster LifecycleGuidance on managing the lifecycle and upgrades of Google Kubernetes Engine (GKE) clusters.Votes: 0GitHub stars: 7
- Gke Compute ClassesConfigures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.Votes: 0GitHub stars: 7
- Gke Cost AnalysisAnswer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.Votes: 0GitHub stars: 7
- Gke Inference QuickstartDeploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ). Covers model discovery, manifest generation, and deployment using native MCP tools and CLI.Votes: 0GitHub stars: 7
- Gke Manifest GenerationStandard Operating Procedure (SOP) for generating and updating secure, compliant, and cost-effective GKE manifests.Votes: 0GitHub stars: 7
- Gke Multi TenancyGuidance on implementing multi-tenancy and governance in Google Kubernetes Engine (GKE) clusters.Votes: 0GitHub stars: 7
- Gke Networking EdgeWorkflows for configuring edge networking, ingress, and security on GKE.Votes: 0GitHub stars: 7
- Gke ProductionizeAssists in preparing applications and clusters on GKE for production.Votes: 0GitHub stars: 7
- Kube Agents ObservabilityAudit, monitor, and debug the logging, tracing, metrics, and API/dashboard observability of the Platform Agent.Votes: 0GitHub stars: 7
- Manage ClusterBring an existing GKE cluster under management on user request (e.g. "manage my cluster <name> in <location>") by creating its Cluster Agent profile. Use whenever a user asks to manage/onboard/watch a specific existing cluster.Votes: 0GitHub stars: 7
- Submit SuggestionPropose declarative configuration updates securely by committing file changes and submitting GitHub Pull Requests (PRs) for SRE review.Votes: 0GitHub stars: 7
- Workload RebalancingOrchestrate cross-cluster workload rebalancing using the kanban board with the validation-then-declare pattern. Use when fleet utilization shows one cluster overutilized and another with headroom and a workload should move.Votes: 0GitHub stars: 7
- Adversarial Review GateRun the mandatory skeptic review over a staged diff and record it in the PR body. Use before `gh pr create` on any change touching Go code in core-agent. Covers what to delegate, what the reviewer needs to be told, how to disposition findings, and the `## Adversarial review` section the required CI check looks for.Votes: 0GitHub stars: 7
- Changelog BulletWrite the CHANGELOG entry for a core-agent PR. Use whenever a change is user-visible — a feature, bug fix, published-doc or contributor-rule change, breaking change or cleanup. Covers which subsection, citing the issue rather than the PR, what a bullet has to contain, and the stacked-release-branch hazard that silently files a bullet under a shipped version.Votes: 0GitHub stars: 7
- Prefix Failure VerificationProve a new regression test actually fails on the pre-fix code, without reverting files or checking out the parent commit. Use for any bug-fix PR in core-agent before opening it. Covers the patch-the-behaviour-back method, why the obvious methods do not work, predicting the failure list, and restoring cleanly.Votes: 0GitHub stars: 7
- Presubmit SweepRun the local presubmit scripts before pushing to core-agent. Use when a change is ready to push, before `git push` or `gh pr create`, or when CI has gone red and you want to reproduce it locally. Covers which scripts to run, which are slow, and why a green local run is the same run as CI.Votes: 0GitHub stars: 7
- Stacked Pr OrderLand a stack of dependent PRs in core-agent without closing the downstream ones. Use when a branch is based on another feature branch rather than main, or when merging a parent whose children are still open. Covers the retarget-before-merge order, rebasing after each parent lands, recovery, and reading merge state correctly.Votes: 0GitHub stars: 7