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 agentmods add skills/volcengine/volcengine-skills/volcengine-troubleshootingnpx skills add volcengine/volcengine-skills --skill volcengine-troubleshootinggit clone --depth 1 https://github.com/volcengine/volcengine-skillsWrote 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/volcengine/volcengine-skills/volcengine-troubleshooting)<a href="https://agentmods.dev/skills/volcengine/volcengine-skills/volcengine-troubleshooting"><img src="https://agentmods.dev/badge/skills/volcengine/volcengine-skills/volcengine-troubleshooting.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01359 |
| Opus 5 | $0.00027 | $0.00679 |
| Sonnet 5 | $0.00011 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
volcengine-troubleshooting 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VolcEngine Troubleshooting
本 skill 面向用户本地环境使用,目标是在不修改云上资源的前提下,帮助定位 VolcEngine 产品、OpenAPI、Python SDK、ve/tosutil CLI 和控制台操作失败的原因。主入口只保留必要的启动规则、场景路由和安全边界;本地工具检查与完整领域索引放在 references/getting-started.md,OpenAPI 报错、签名、鉴权、参数、限流以及 ve/tosutil/Python SDK 调用链路的快速检查放在 references/openapi-quick-check.md,具体产品域手册放在 references/domain-guides/。
先把 SKILL_ROOT 解析为包含本 SKILL.md 的绝对目录。所有脚本和 reference 都从
${SKILL_ROOT} 解析,不依赖仓库布局或当前工作目录。
开始前
-
先读取
references/getting-started.md,确认本地工具、环境变量、场景依赖和领域路由。 -
如用户允许执行本地体检,运行通用检查:
bash "${SKILL_ROOT}/scripts/common_check.sh" -
优先用
ve sts GetCallerIdentity验证当前身份链路,只报告是否可用和必要的身份摘要,不输出 SecretKey、SessionToken、完整 AccessKeyId、完整手机号、账单明细或对象内容。 -
不要运行
ve configure、登录/SSO 初始化、安装依赖、写入配置文件或修改云资源,除非用户明确要求并确认影响。 -
若不确定归属,按
references/getting-started.md中的“场景路由”定位领域;遇到 OpenAPI 报错、签名/鉴权失败、参数校验、限流、服务端错误,或由ve/tosutil/Python SDK 暴露出的 OpenAPI 调用失败,先读references/openapi-quick-check.md收敛 RequestId、Action、Region、错误码和最小复现上下文。 -
根据下方路由打开对应
references/domain-guides/<domain>/README.md,再按领域手册的“先读这些”读取query-cli-catalog.md、章节 README、api-coverage-matrix.md和脚本 README。
场景路由
先从用户报错中提取 RequestId、ErrorCode、Action、Service、Region、资源 ID、发生时间和调用方式。如果缺失,先问最少必要问题。
领域判断优先读 references/getting-started.md。确定领域后,再进入对应 references/domain-guides/<domain>/README.md:
openapi-sdk-cli:OpenAPI、veCLI、Python SDK、签名、API 网关。account-permission:账号、AK/SK、STS、IAM、角色、权限不足。billing-quota:账单、余额、欠费、订单、配额、资源包。compute-container-network:ECS、VKE、CLB/ALB、VPC、NAT、EIP、路由、安全组。storage-database:TOS、EBS、文件存储、云备份、RDS、Redis、数据库连接。domain-cdn-ingress:DNS、域名、证书、CDN/DCDN、入口回源。communication-media:SMS、RTC、VOD、Live、CV/OCR、veImageX。llm-ecosystem:Ark、豆包、VikingDB、AgentKit、ArkClaw、Coze、机器学习平台。security-kms-encryption:KMS、Secret、云加密机、WAF、DDoS、Cloud Firewall、安全中心。
仍无法分类时,完成 scripts/common_check.sh 后,按报错中的服务名查 ve SERVICE --help 和 ve SERVICE ACTION --help。
核心原则
- 只读优先:默认只执行 Describe/List/Get/Query/Lookup/Check 类命令。Create/Update/Delete/Attach/Detach/Put/Set/Start/Stop/Run/Invoke/Pay/Renew/Refresh/Preload 等写操作必须先解释影响并等待用户确认。
- CLI 优先,SDK 辅助:只支持
ve和tosutil两类 CLI。只有分页聚合、跨资源拓扑、日志归并或 CLI 未覆盖时,才建议volc-sdk-python或volcengine-python-sdk脚本。 - 凭证安全:只从环境变量读取 AK/SK/Token;不要要求用户把凭证写入文件;不要打印 SecretKey、SessionToken 或完整 AccessKeyId;展示 AK 时至少遮蔽中间部分。
- 最小上下文:每次排障只收集当前问题所需的服务、地域、资源和时间窗口。不要批量枚举无关账号资源。
- 解释判据:每个检查都说明为什么查、期望看到什么、异常意味着什么,以及下一步该收集哪一项证据。
What ships with it
60 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/domain-guides/account-permission/README.md 7.9 KB
- references/domain-guides/account-permission/references/01-overview-routing/README.md 1.4 KB
- references/domain-guides/account-permission/references/02-account-verification-risk/README.md 1.1 KB
- references/domain-guides/account-permission/references/03-iam-user-policy/README.md 1.7 KB
- references/domain-guides/account-permission/references/04-role-sts/README.md 1.3 KB
- references/domain-guides/account-permission/references/05-product-resource-access/README.md 980 B
- references/domain-guides/account-permission/references/06-access-key/README.md 1.6 KB
- references/domain-guides/account-permission/references/07-playbooks/README.md 893 B
- references/domain-guides/account-permission/references/api-coverage-matrix.md 35 KB
- references/domain-guides/account-permission/references/python-sdk-script-patterns.md 495 B
- references/domain-guides/account-permission/references/query-cli-catalog.md 1.2 KB
- references/domain-guides/account-permission/scripts/README.md 459 B
- references/domain-guides/billing-quota/README.md 14 KB
- references/domain-guides/billing-quota/references/01-overview-routing/README.md 2.5 KB
- references/domain-guides/billing-quota/references/02-balance-arrears-precharge/README.md 3.2 KB
- references/domain-guides/billing-quota/references/03-subscription-package/README.md 2.9 KB
- references/domain-guides/billing-quota/references/04-usage-quota-limit/README.md 3.1 KB
- references/domain-guides/billing-quota/references/05-order-purchase-activation/README.md 2.3 KB
- references/domain-guides/billing-quota/references/06-bill-cost-detail/README.md 4.6 KB
- references/domain-guides/billing-quota/references/07-playbooks/README.md 2.5 KB
- references/domain-guides/billing-quota/references/api-coverage-matrix.md 11 KB
- references/domain-guides/billing-quota/references/provider-code-aliases.md 1.8 KB
- references/domain-guides/billing-quota/references/python-sdk-script-patterns.md 2.1 KB
- references/domain-guides/billing-quota/references/query-cli-catalog.md 2.8 KB
- references/domain-guides/billing-quota/scripts/collect_billing_context.py 19 KB runs code
- references/domain-guides/billing-quota/scripts/README.md 3.3 KB
- references/domain-guides/communication-media/README.md 7.8 KB
- references/domain-guides/communication-media/references/01-overview-routing/README.md 1.4 KB
- references/domain-guides/communication-media/references/02-sms-service/README.md 1.4 KB
- references/domain-guides/communication-media/references/03-rtc-webrtc/README.md 1.1 KB
- references/domain-guides/communication-media/references/04-vod-playback-media/README.md 1.4 KB
- references/domain-guides/communication-media/references/05-live-streaming/README.md 1.6 KB
- references/domain-guides/communication-media/references/06-cv-ocr-media-processing/README.md 1.1 KB
- references/domain-guides/communication-media/references/07-playbooks/README.md 1.1 KB
- references/domain-guides/communication-media/references/api-coverage-matrix.md 48 KB
- references/domain-guides/communication-media/references/python-sdk-script-patterns.md 1000 B
- references/domain-guides/communication-media/references/query-cli-catalog.md 2.0 KB
- references/domain-guides/communication-media/scripts/README.md 500 B
- references/domain-guides/compute-container-network/README.md 13 KB
- references/domain-guides/compute-container-network/references/01-overview-routing/README.md 2.9 KB
- references/domain-guides/compute-container-network/references/02-ecs-lifecycle-state/README.md 3.3 KB
- references/domain-guides/compute-container-network/references/03-login-os-access/README.md 3.2 KB
- references/domain-guides/compute-container-network/references/04-public-private-connectivity/README.md 3.8 KB
- references/domain-guides/compute-container-network/references/05-security-policy-port/README.md 2.4 KB
- references/domain-guides/compute-container-network/references/06-eip-nat-route-gateway/README.md 3.5 KB
- references/domain-guides/compute-container-network/references/07-vke-container-runtime/README.md 3.4 KB
- references/domain-guides/compute-container-network/references/08-image-init-cloudassistant/README.md 1.9 KB
- references/domain-guides/compute-container-network/references/09-playbooks/README.md 3.3 KB
- references/domain-guides/compute-container-network/references/api-coverage-matrix.md 63 KB
- references/domain-guides/compute-container-network/references/python-sdk-script-patterns.md 5.2 KB
- references/domain-guides/compute-container-network/references/query-cli-catalog.md 3.0 KB
- references/domain-guides/compute-container-network/scripts/collect_clb_backend_context.py 9.8 KB runs code
- references/domain-guides/compute-container-network/scripts/collect_ecs_network_context.py 6.6 KB runs code
- references/domain-guides/compute-container-network/scripts/collect_vke_pod_context.py 6.1 KB runs code
- references/domain-guides/compute-container-network/scripts/README.md 3.7 KB
- references/domain-guides/domain-cdn-ingress/README.md 9.3 KB
- references/domain-guides/domain-cdn-ingress/references/01-overview-routing/README.md 1.7 KB
- references/domain-guides/domain-cdn-ingress/references/02-dns-domain-resolution/README.md 1.5 KB
- references/domain-guides/domain-cdn-ingress/references/03-ssl-https-certificate/README.md 1.8 KB
- references/domain-guides/domain-cdn-ingress/references/04-cdn-dcdn-cache-origin/README.md 2.6 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.
- 4d ago First seen · 68 lines · 54 tokens per session scan A e837df14afd9
volcengine-troubleshooting is a skill published in the GitHub repository volcengine/volcengine-skills (19 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,359 once invoked, about $0.0003 per session on Opus 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 2026-09-01.
Other skills, from other repositories
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
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-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-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.