一键导入
k8s-tool
LOAD THIS SKILL when: working with Kubernetes pods, logs, deployments, resource usage, or running kubectl commands. Contains all k8s-tool commands.
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。
菜单
LOAD THIS SKILL when: working with Kubernetes pods, logs, deployments, resource usage, or running kubectl commands. Contains all k8s-tool commands.
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
Automates the full PR lifecycle — create or update a pull request, then aggressively monitor CI checks and review feedback in a continuous loop, fixing failures and addressing comments until the PR is fully green. Also covers push, branch creation, and branch sync workflows.
LOAD THIS SKILL when: working with Azure DevOps pipelines, builds, repos, or checking build logs and failures. Contains all az-tool commands.
LOAD THIS SKILL when: running SQL queries, inspecting database schema, listing tables or columns, or working with database environments. Contains all db-tool commands.
LOAD THIS SKILL when: working with GitHub PRs, issues, workflows, CI checks, reviews, merging, or branch management. Contains all gh-tool commands for PR management, workflow monitoring, issue tracking, and branch operations.
LOAD THIS SKILL when: reading application logs, listing log files, or accessing remote pod logs. Contains all logs-tool commands.
LOAD THIS SKILL when: investigating Grafana-backed LGTM telemetry, especially Tempo traces, Loki log correlation, and Prometheus metrics through observability-tool. Contains all observability-tool commands and usage patterns.
| name | k8s-tool |
| description | LOAD THIS SKILL when: working with Kubernetes pods, logs, deployments, resource usage, or running kubectl commands. Contains all k8s-tool commands. |
Kubernetes tool — kubectl wrapper with config-driven context resolution and structured commands. Part of @blogic-cz/agent-tools.
Run via bun k8s-tool (requires @blogic-cz/agent-tools as a dev dependency).
NEVER run bare kubectl — the credential guard will block it.
Auth: existing kubectl context (kubeconfig). Cluster ID from config resolves context automatically.
bun k8s-tool kubectl --env test --cmd "get pods -n test-ns"
bun k8s-tool kubectl --env prod --cmd "logs <pod> --tail=100"
bun k8s-tool kubectl --env test --cmd "describe pod <pod>"
bun k8s-tool pods --env test # List pods (structured)
bun k8s-tool logs --pod <pod> --env test --tail 50 # Fetch logs
bun k8s-tool describe --resource pod --name <pod> --env test
bun k8s-tool exec --pod <pod> --exec-cmd "ls -la" --env test
bun k8s-tool top --env test # Show resource usage
Environment is any string (e.g. test, prod). Set defaultEnvironment in agent-tools.json5 to skip --env on every call. Implicit production access is blocked for safety.
bun k8s-tool commands for the full machine-readable command/flag tree; --help for one subcommand.--format json only when you'll machine-parse the result.hint, nextCommand, and retryable fields — always check them on failure.