菜单
Use when operating the dce generated CLI. Discover commands, inspect parameters, check auth state, and execute API operations safely.
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
Generate a Chinese daily GPU operations snapshot for system resource utilization, idle headroom, and the trade-off between higher utilization and elastic buffer. Use for requests containing 今日系统运维摘要, 系统资源利用率, 空闲余量, GPU利用率, 资源利用效率, or 弹性缓冲. Query only the Crane API endpoint /apis/crane.io/v1alpha1/singlepage/gpu-resource-status through its DCE command.
Query Crane for model cost and revenue over the most recent N complete calendar days and produce a chart-first operations summary. Use for model cost, model revenue, model gross profit, and recent-N-day model finance requests. Default N is 3. Chinese trigger keywords: 模型成本、模型收入、模型毛利、最近N天模型经营数据. Use only Crane-backed business-cockpit queries; never call other DCE modules.
Query recent Token costs for users or tenants through Crane, rank the top M entries by cost, and produce an operational report with a chart. Trigger this skill for requests containing Chinese keywords such as “Token 费用排名”, “费用 Top 用户”, or “最近几天费用最高用户”. N defaults to 3 and M defaults to 5. This skill only ranks costs; it does not split results by model or perform write operations.
Generate a concise leadership-facing AI operations daily summary and business-value analysis from DaoCloud Enterprise DCE / LLM Studio / Hydra data. Use when the user asks for today's AI operations summary, AI usage report, LLM Studio operating metrics, boss/leadership AI daily report, token/API key/model service overview, business value, operating value, risk identification, or wants available DCE CLI data turned into the most important conclusions, especially in table form.
Diagnose OpenClaw request failures or slow requests with DCE Insight tracing, alerts, logs, and pod status. Use when the user asks for OpenClaw request root-cause analysis, R.E.D analysis, error-chain details, or mitigation advice.
Use when a user asks why a self-hosted LLM's ROI is dropping, why its inference cost is rising, whether a model's serving template / resource pool is right-sized, or whether the deployment mix across several self-hosted models should change (scale down / scale up / reprice / shift traffic). Covers single-model cost-decline attribution and portfolio-level deployment-mix ROI. Also use for Chinese requests like 自部署模型 ROI 为什么下降、成本为什么涨、 当前副本/资源池配置是否合理、要不要缩容/扩容/调价、deepseek-v4-pro 和 GLM-5.1 的 部署比例要不要调整、模型组合整体 ROI 怎么样、哪些模型该承接流量. Triggers on model names like DeepSeek, GLM, Qwen, MiniMax, Kimi and terms gross margin, GPU utilization, 毛利率, 利用率, 单位成本, 缩容护栏.
| name | dce |
| description | Use when operating the dce generated CLI. Discover commands, inspect parameters, check auth state, and execute API operations safely. |
Use this skill when a user asks you to operate dce, inspect its API commands, or find the right generated command for an API task.
dce search "<intent>" --json; use --limit when needed. Search is only candidate discovery.dce commands show <path...> --json before executing an unfamiliar command.auth.required=true, run dce auth status --hostname <host> before execution. Use http.default_hostname when present unless the user provides --hostname or $DCE_HOST.commands show.dce commands --json: full generated command catalog.dce commands --include-hidden --json: include hidden generated commands.dce commands show <path...> --json: source of truth for one command.dce commands schema --json: catalog schema version for parser compatibility.dce search "<intent>" --json: ranked candidate commands.dce --version or dce -v: print CLI build version.references/catalog.md for the command discovery protocol and catalog field meanings.references/modules/ai-lab.md for the ai-lab module command index.references/modules/billing-center.md for the billing-center module command index.references/modules/business-cockpit.md for the business-cockpit module command index.references/modules/container-management.md for the container-management module command index.references/modules/elasticsearch.md for the elasticsearch module command index.references/modules/global-management.md for the global-management module command index.references/modules/insight.md for the insight module command index.references/modules/kafka.md for the kafka module command index.references/modules/llm-studio.md for the llm-studio module command index.references/modules/microservice-engine.md for the microservice-engine module command index.references/modules/minio.md for the minio module command index.references/modules/mongodb.md for the mongodb module command index.references/modules/mysql.md for the mysql module command index.references/modules/operations-management.md for the operations-management module command index.references/modules/postgresql.md for the postgresql module command index.references/modules/rabbitmq.md for the rabbitmq module command index.references/modules/redis.md for the redis module command index.references/modules/rocketmq.md for the rocketmq module command index.references/modules/seaweedfs.md for the seaweedfs module command index.references/modules/virtual-machines.md for the virtual-machines module command index.references/modules/workbench.md for the workbench module command index.commands show first.-o json for machine-readable command output unless the user asks for human-readable output.--file, --set, or --set-str for JSON request bodies according to commands show body requirements.flags[].input_modes: --<flag>-env, --<flag>-file, or --<flag>-stdin.The catalog (dce commands / dce search) lists every module dce was built with, regardless of which modules are actually installed on the target host. A command appearing in the catalog does not guarantee its module is deployed.
A 404 / route-not-found at the module path level (the API route itself does not exist, not a specific object) is ambiguous: the module may not be installed, or the path/version may be wrong. On such a 404, actively confirm before concluding by running dce global-management about list-g-product-versions -o json (global-management is the always-present base module, so this is always available). Then:
404 is not a missing module. Re-check the exact path and params with dce commands show <path...> --json (likely a wrong path/version or a resource-level not-found); do not report the module as missing.404 (a specific ID/name on an otherwise-working module) means that object doesn't exist, not that the module is missing — handle that normally.