菜单
Kubernetes cluster access via loctl (kubectl, helm, stern). Use when checking pod health, inspecting resources, or streaming logs from pods.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Coordinate full-strength Claude and Codex teammates in detached tmux sessions with external stall monitoring, durable file channels, completion markers, and resumable conversations. Use when work can be divided into independent tasks, when the user asks for teammates or subagents, or when delegating research, implementation, frontend, review, or long-running work across model accounts.
Coordinate full-strength Claude and Codex teammates in detached tmux sessions with external stall monitoring, durable file channels, completion markers, and resumable conversations. Use when work can be divided into independent tasks, when the user asks for teammates or subagents, or when delegating research, implementation, frontend, review, or long-running work across model accounts.
Drive the kautopilot binary as a thin in-session controller: ticket/free-form request → merge-ready PRs across one or more repos, as ONE flat session. The binary owns all state, prompts, and next-step decisions; this skill just runs what `kautopilot next` yields. Use when running /kautopilot.
Drive the kautopilot binary as a thin in-session controller: ticket/free-form request → merge-ready PRs across one or more repos, as ONE flat session. The binary owns all state, prompts, and next-step decisions; this skill just runs what `kautopilot next` yields. Use when running /kautopilot.
Iteratively review-and-resolve the current changes using parallel subagent reviewers across multiple lenses (bugs, quality, completion), looping until every reviewer is satisfied. Use when running /floop, or when asked to deeply review and harden a diff until all critiques are addressed.
Give the user a fast, ADHD/dyslexia-friendly recap of the current work or conversation — the outcome first, then what (if anything) you need from them. Use when running /summary, or when asked to "summarize", "recap", "where are we", "catch me up", or "what do you need from me".
| name | liftoff-kubernetes |
| description | Kubernetes cluster access via loctl (kubectl, helm, stern). Use when checking pod health, inspecting resources, or streaming logs from pods. |
The qa environment maps to QA clusters. The ops environment maps to all non-QA clusters: production, staging, data platform, dashboard, and operations.
loctl qa)| Context | Purpose |
|---|---|
eks-qa-us-east-1b | QA |
loctl ops)| Context | Purpose |
|---|---|
eks-prod-us-east-1b | Production (US East) |
eks-prod-us-east-1c | Production (US East) |
eks-prod-us-east-1d | Production (US East) |
eks-prod-us-east-1f | Production (US East) |
eks-prod-ap-northeast-1a | Production (APNE) |
eks-stage-us-east-1a | Staging |
eks-ops-us-east-1c | Operations (Mimir, Grafana, monitoring) |
eks-ops-ap-northeast-1a | Operations (APNE) |
eks-data-1a | Data platform |
eks-dashboard-us-east-1a | Dashboards |
KUBECONFIG set to agent-config (EngineeringRole)AWS_PROFILE forced to EngineeringRoleqa or ops prefix is required -- no default--context -- there is no defaultloctl qa list contextsRead-only verbs: get, describe, logs, top, explain, api-resources, api-versions, version, config, auth, cluster-info, debug, exec, port-forward, wait, diff
loctl qa kubectl --context eks-qa-us-east-1b get nodes
loctl ops kubectl --context eks-prod-us-east-1b get pods -n api
loctl ops kubectl --context eks-ops-us-east-1c get pods -n grafana
loctl ops kubectl --context eks-ops-us-east-1c get events -n grafana --sort-by=.lastTimestamp
loctl qa kubectl --context eks-qa-us-east-1b top pods -n grafana --sort-by=cpu
Read-only commands: get, history, list, ls, show, status, template, version, search, repo, env, diff
Note: uses --kube-context (not --context). EngineeringRole may lack RBAC for helm list/status in some namespaces.
loctl qa helm --kube-context eks-qa-us-east-1b show values argocd
loctl ops helm --kube-context eks-ops-us-east-1c show values mimir
loctl qa stern --context eks-qa-us-east-1b my-app -n default --tail=10
loctl ops stern --context eks-prod-us-east-1b my-app -n api --tail=10