菜单
Use an installed devopsctl CLI to operate an enterprise DevOps platform. Trigger when the user asks an agent to inspect or manage business spaces, apps, services, deployments, Jenkins publish/build history, login/auth status, or supported DevOps backend API calls.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/clcc2019/dsflow --skill devopsctl命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Calculate incident impact, detection and recovery durations, classify incidents as L0-L3 from service criticality and impact inputs, compute weighted SLA impact and derived availability, and generate post-incident Markdown reports. Use for SLA calculations, incident severity assessment, outage-duration review, availability summaries, postmortems, incident reports, and remediation tracking.
云原生 SRE 值班助理和巡检编排技能。用于基础设施早检、Kubernetes 集群健康检查、Ceph 存储巡检、计算集群巡检、网关故障初筛、异常证据汇总和值班日报生成。触发场景：用户要求早检、巡检、检查集群是否正常、检查 Ceph、检查计算集群、排查网关错误或生成基础设施健康报告。
Create, review, tune, and validate production-grade Prometheus alerting rules and Kubernetes PrometheusRule resources. Use when writing or repairing alert rule YAML, designing PromQL alert expressions, recommending defensible thresholds and for durations, building SLO/error-budget burn-rate alerts, reducing alert noise, standardizing severity/labels/annotations, adding promtool tests, or reviewing an existing Prometheus rule catalog. 用户要求创建、评审或优化 Prometheus 告警规则、PromQL、告警阈值、告警降噪时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | devopsctl |
| description | Use an installed devopsctl CLI to operate an enterprise DevOps platform. Trigger when the user asks an agent to inspect or manage business spaces, apps, services, deployments, Jenkins publish/build history, login/auth status, or supported DevOps backend API calls. |
Use this skill whenever a task can be handled through the configured DevOps backend instead of manually browsing the UI or reconstructing API calls.
Resolve an installed executable. This sanitized skill does not bundle an organization-specific binary.
DEVOPSCTL="${DEVOPSCTL:-$(command -v devopsctl)}"
test -n "$DEVOPSCTL" || { echo "devopsctl is not installed" >&2; exit 1; }
"$DEVOPSCTL" --help
Configure the backend through the CLI config, DEVOPS_BASE_URL, or --base-url. Never infer an internal endpoint.
devopsctl from PATH or DEVOPSCTL."$DEVOPSCTL" auth status --pretty."$DEVOPSCTL" login --username <email> and let the user enter the password when prompted. Prefer this over asking for cookies.--json --pretty when the next step needs structured data.--business-space-id to app list."$DEVOPSCTL" health --pretty for backend health checks and "$DEVOPSCTL" routes --json --pretty to discover supported backend routes."$DEVOPSCTL" call METHOD PATH.Read references/cli-usage.md when you need exact flags, backend endpoints, JSON/query field names, or examples.
Treat create, update, delete, write, Jenkins build, rebuild, cancel, deploy, restart, rollout, and any non-GET raw API call as mutating operations.
Before running any mutating operation, get a second confirmation from the user in the current conversation, even when the user already requested the operation. Present the exact command or API method/path, target resource identifiers, and expected effect, then wait for an explicit affirmative reply. Do not treat prior intent, tool approval, or successful authentication as confirmation.