Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add QianWen-AI/qianwenai-deploy --skill operategit clone --depth 1 https://github.com/QianWen-AI/qianwenai-deployWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qianwen-ai/qianwenai-deploy/operate)<a href="https://agentmods.dev/skills/qianwen-ai/qianwenai-deploy/operate"><img src="https://agentmods.dev/badge/skills/qianwen-ai/qianwenai-deploy/operate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qianwen-ai/qianwenai-deploy/operate"><img src="https://agentmods.dev/badge/skills/qianwen-ai/qianwenai-deploy/operate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00198 | $0.01820 |
| Opus 5.5 | $0.00079 | $0.00728 |
| Sonnet 5.5 | $0.00040 | $0.00364 |
| Haiku 4.5 | $0.00020 | $0.00182 |
Grade A, and why
qianwenai-operate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
千问 AI 运维
对由 qianwenai-deploy 部署在阿里云国内站的应用做故障诊断与确认式恢复。诊断只读、无需确认；任何
改变云资源或应用运行状态的动作都必须经过明确确认。
交互流程
识别应用和资源
→ 最小诊断（只读）
→ 给出原因、证据、建议动作
→ 展示影响并请求确认
→ 执行一个恢复动作
→ 验证应用、ECS、RDS
→ 返回结果和审计信息
→ 提议经 qianwenai-observe 重新评分（恢复前 → 恢复后）
交互形态
- 只读信息（诊断、原因、证据、验证结果）：纯文本，每条判断后附一行证据（指标、状态、RequestId）。
- 改状态动作（启停 ECS、重启应用、重载 Nginx 等任何写调用）：先用 AskUserQuestion，提问答清 做什么 · 影响（停机/不可逆） · 怎么验证，确认前不执行；一次只提议一个恢复动作。
- 主动纪律：恢复后如结果正常则安静收尾；仅在仍有风险或未恢复时主动给下一步，让用户选。
范围
| 范围内 | 范围外 |
|---|---|
由 qianwenai-deploy 部署的应用（存在状态文件） |
无 .qianwenai-deploy 状态文件的应用 |
| 单 ECS，或 ECS + RDS MySQL 8.0 | 其他拓扑 / 自建服务器 |
| 诊断 + 确认式恢复（启动 ECS、重启应用、重载 Nginx） | 数据破坏性操作、扩缩容、配置重构 |
| 定位到应用层报错（哪一层坏了、报了什么错） | 源码审查、找 bug/漏洞、判断哪行代码写错、改代码 |
| 阿里云国内站 | 国际站 → 用 qwencloud-operate |
代码问题不在能力范围内
本 skill 处理基础设施与运行时故障，不做源码审查、缺陷定位或代码修改。诊断可定位到「应用层报错、报了 什么错」，帮用户缩小范围，但不判断具体哪行代码有问题，也不改代码。
涉及代码时，明确告知用户：修改代码属于本 skill 能力之外，需由用户自行决定并执行，相应后果由用户 自行承担。不要在恢复动作里夹带任何代码改动。
前置条件
Aliyun CLI：
aliyun version（需 3.x）。所有命令用驼峰原生形态直连 OpenAPI， 不依赖插件。凭证仅用aliyun configure list查看状态。绝不读取、回显、打印或索要 AK/SK/Token。 无有效配置集 → 停止并请用户在本会话之外配置凭证。见references/cli_installation_guide.md。
怎么做
- 识别应用 — 从
.qianwenai-deploy识别应用。见 workflow。 - 诊断（只读，无需确认）— 找出坏在哪一层、可能的原因、证据，以及该怎么处理。见 diagnose。
- 一次只恢复一件事，且先确认。 选中与诊断匹配的动作，向用户展示影响并取得同意，再执行且仅执行
那一件事：
- 启动已停止的服务器 → recover-ecs
- 重启卡死的服务器 → recover-reboot
- 重启应用服务 → recover-app
nginx -t通过后重载 Nginx → recover-nginx- EIP 解绑后重新绑定 → recover-eip
- 放行安全组 80 / 443 入方向 → recover-securitygroup
- 数据库相关问题 → recover-rds
- 根分区将满 / 清理后仍不足需扩容 → recover-disk
- 验证应用是否恢复，再记录做了什么。见 workflow。
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/api_gotchas.md 1.1 KB
- references/cli_installation_guide.md 1.1 KB
- references/diagnose.md 4.3 KB
- references/ram_policies.md 1.9 KB
- references/recover_app.md 1.1 KB
- references/recover_disk.md 2.7 KB
- references/recover_ecs.md 907 B
- references/recover_eip.md 1.1 KB
- references/recover_nginx.md 1.3 KB
- references/recover_rds.md 938 B
- references/recover_reboot.md 1021 B
- references/recover_securitygroup.md 1.4 KB
- references/workflow.md 4.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 115 lines · 198 tokens per session scan A b235f235f532
qianwenai-operate is a skill published in the GitHub repository QianWen-AI/qianwenai-deploy (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 198 tokens to every session and 1,820 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.
Other skills, from other repositories
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-mxla-hang
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/).…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-node-unresponsive-timeout
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for…
gke-ai-troubleshooting-tpu-performance-degradation
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (gcloud alpha mldiagnostics monitored-events / hypercomputecluster.googleapis.com/v1alpha) and 1-minute Cloud Monitoring system metrics (kubernetes.io/node/accelerator/).…