← 返回 Skills 市场
9295
总下载
6
收藏
0
当前安装
11
版本数
在 OpenClaw 中安装
/install kubernetes
功能描述
Kubernetes & OpenShift Platform Agent Swarm — A coordinated multi-agent system for cluster operations. Includes Orchestrator (Jarvis), Cluster Ops (Atlas), G...
安全使用建议
Install only if you intend to give an agent live Kubernetes/OpenShift authority and possibly cloud, registry, GitOps, and incident-response access. Before use, require explicit human approval for production changes, deletes, secret reads/writes, alert silences, PagerDuty/Slack/Teams messages, git commits, pushes, and PRs; scope credentials to least privilege and replace broad `git add -A` and action logging with path-limited, redacted records.
功能分析
Type: OpenClaw Skill
Name: kubernetes
Version: 2.1.0
The 'kubernetes' skill bundle is a comprehensive multi-agent orchestration system designed for Kubernetes and OpenShift platform operations. It defines seven specialized agent roles (e.g., Jarvis for orchestration, Shield for security) and provides detailed instructions for cluster management, GitOps, and security auditing. While the agents are granted high-privilege capabilities—including RBAC management, secret rotation, and cluster upgrades—the bundle incorporates extensive safety guardrails, such as mandatory human-in-the-loop approvals for destructive actions, environment-aware constraints (e.g., 'NEVER' delete in production), and a rigorous audit logging protocol (LOGS.md). No evidence of malicious intent, unauthorized data exfiltration, or obfuscation was found across the SKILL.md or AGENTS.md files.
能力评估
Purpose & Capability
The broad Kubernetes/OpenShift swarm purpose coherently covers cluster ops, GitOps, security, observability, artifacts, and developer support, but several subskills also authorize high-impact actions such as secret-store administration, alert silencing, rollback/scale/traffic containment guidance, and repository PR creation beyond some stated role boundaries.
Instruction Scope
Multiple agent instructions require session-start repository reads and session-end `git add -A` commits, and the orchestrator heartbeat is instructed to create branches, push commits, and open PRs; this is broader than necessary for routine cluster operations and can affect unrelated workspace files.
Install Mechanism
The package is markdown/instruction-only with no executable scripts or install-time binary payloads; installation is documented through `clawhub install kubernetes`.
Credentials
KUBECONFIG, kubectl, optional cloud credentials, registry credentials, and secrets tooling are proportionate for this purpose, but Slack/Teams/PagerDuty outbound workflows and routing keys are not fully declared in the root metadata and can transmit operational details externally.
Persistence & Privilege
The skill intentionally persists memory, logs, incidents, and working state, but broad mandatory commits and logging every action without strong redaction rules could persist unrelated files, secrets, tokens, kubeconfig-derived details, or sensitive operational context.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install kubernetes - 安装完成后，直接呼叫该 Skill 的名称或使用
/kubernetes触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v2.1.0
v2.1.0: Declare all credentials/binaries in metadata, add human-approval warnings for destructive operations
v2.0.1
v2.0.1: Replace all shell variable placeholders with literal values to address security scan
v2.0.0
v2.0.0: Converted to instruction-only skill. Removed all executable scripts. Pure markdown instructions.
v1.0.7
- Added OPERATIONAL_RISKS.md to document operational risks, inconsistencies, and mitigations.
- SKILL.md updated to reference the new OPERATIONAL_RISKS.md and SECURITY.md for additional documentation.
- Enhanced install instructions and security warnings in SKILL.md, emphasizing pinning to specific commit hashes and supply chain risk awareness.
v1.0.6
- Added SECURITY.md for improved transparency on security practices.
- Introduced shared/library scripts: preflight.sh and verify-binary.sh.
- Removed SKILL.md from skills/qmd directory (was likely deprecated or redundant).
- No major functional changes to skill logic or documented platform requirements.
v1.0.5
- Reduced required environment variables and binaries to only those essential for basic Kubernetes/OpenShift operations.
- Made cloud and integration credentials optional, clarifying that they should be provided only if specific features are used.
- Simplified and modularized credential requirements, highlighting "enable only what you need" for cloud and integrations.
- Updated documentation to streamline security warnings and remove redundant sections.
- Installation and security instructions are more concise, with clearer guidance on auditing and sandboxing before production use.
v1.0.4
No code or documentation changes were detected for version 1.0.4.
- No file changes since the previous release.
v1.0.3
**Security and safety warnings added for all users installing the skill.**
- Added comprehensive security and risk considerations, including source verification, install mechanism warnings, and requirements for least-privilege credentials.
- Detailed instructions on validating the GitHub source, auditing scripts before use, and running in a sandbox/non-production environment prior to production use.
- Explicit warnings that procedural controls (like human approval) are not technical controls; users must enforce their own safeguards for production.
- Listed supply chain risks and recommendations for limiting download sources and toolchain exposure.
- No functional or agent capability changes; documentation and metadata only.
v1.0.2
- Added explicit runtime, credential, and integration requirements for all supported cloud providers and external services.
- Included a new section detailing necessary environment variables (KUBECONFIG, cloud credentials, etc.) for Kubernetes/OpenShift and cloud operations.
- Introduced a new "Session Setup" section and setup-session.sh script to standardize agent environment setup.
- Extended metadata to declare credentials and integrations required for key agent features.
- Added instructions for new skill "qmd" (hybrid markdown search) and updated installation options accordingly.
- Enhanced security and usage documentation—emphasized human approval for production actions and improved guidance on credential handling.
v1.0.1
**Major update: Skill transformed from a general Kubernetes guide to a modular, multi-agent system (Cluster Agent Swarm) for platform operations.**
- Introduces a coordinated agent architecture, splitting functions into specialized agents: Orchestrator, Cluster Ops, GitOps, Security, Observability, Artifacts, and Developer Experience.
- Adds documentation for all agents, detailed capability breakdowns, roles, communication protocols, heartbeats, and escalation flows.
- New install instructions for both full swarm and individual agents.
- Source reorganized: scripts and docs for platform tasks now distributed into agent-based folders by domain.
- Expands supported platforms and tools (AKS, EKS, GKE, OpenShift, ROSA, ARO).
- Previous monolithic scripts removed; replaced by modular, agent-scoped assets and documentation.
v1.0.0
Kubernetes Skill 1.0.0 — Initial Release
- Covers Kubernetes and OpenShift cluster management including operations, troubleshooting, manifest generation, security, and GitOps workflows.
- Includes common commands, templates, and bundled scripts for tasks such as node management, upgrades, backup/restore, and health checks.
- Provides ready-to-use manifest templates for Deployments, Services, Ingress, NetworkPolicy, and OpenShift Routes.
- Offers security guidance (RBAC, PodSecurity, audits) and outlines GitOps tools (ArgoCD, Flux, Helm, Kustomize).
- Supports multi-cloud cluster operations for AKS, EKS, GKE, ARO, and ROSA.
- Documents tool and platform versions as of January 2026.
元数据
常见问题
Kubernetes Agent Swarm 是什么？
Kubernetes & OpenShift Platform Agent Swarm — A coordinated multi-agent system for cluster operations. Includes Orchestrator (Jarvis), Cluster Ops (Atlas), G... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 9295 次。
如何安装 Kubernetes Agent Swarm？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kubernetes」即可一键安装，无需额外配置。
Kubernetes Agent Swarm 是免费的吗？
是的，Kubernetes Agent Swarm 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Kubernetes Agent Swarm 支持哪些平台？
Kubernetes Agent Swarm 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Kubernetes Agent Swarm？
由 Chin K（@kcns008）开发并维护，当前版本 v2.1.0。
推荐 Skills