>
npx skills add https://github.com/aliyun/alibabacloud-ecs-troubleshoot-skills --skill alibabacloud-ecs-linux-troubleshooting
本技能仅适用于阿里云 ECS 上的 Linux GuestOS,针对用户指定的阿里云 ECS Linux 实例(目标机)进行异常问题排查。Agent 运行在目标机或他机上,通过 aliyun CLI 工具对目标 ECS 实例进行远程诊断与数据采集。
references/ 中的命令、路径等按实例内环境编写。references/utils/guestos-pe-prep.md 中步骤外其他步骤只能使用references/aliyun-cli-cheatsheet.md中列出的子命令,不得调用未列出的子命令。references/<slug>.md 排查文档中描述运行排查所需命令,不要盲目自行猜测命令。必须按序执行
在打开任何域文档前,如果用户问题描述较模糊时先通过多轮对话细化问题,并通过 aliyun CLI 和 向用户询问 尽量补齐异常问题发生的证据和相关的环境信息,通常会涉及以下信息:
| 维度 | 要补齐的内容 | 获取方式 |
| --- | --- | --- |
| 实例基本信息、状态、规格 | 实例状态 | 按需调用 aliyun CLI |
| 范围 | 是否必现;起止时间;异常问题发生时是否存在变更、重启、扩缩容 | 向用户询问 |
| 通道 | VNC 是否可用;SSH/Workbench/云助手是否可用 | 向用户询问 |
| 网络方向 | 外部→实例业务端口、实例→外部网络、仅 VPC 内互通等 | 向用户询问 |
| 表现 | 报错原文、截图 | 向用户询问 |
references/symptom-to-domain.md,按用户澄清后的异常问题描述选现象域大类和现象域。references/<slug>.md。同时要求用户确认现象域是否准确,准确后才进入「阶段 3」。如用户告知不准确,将将排除第 2 步中现象域后 TOP 3 的次现象域展示给用户,让用户确认是否属于这些次现象域。如用户告知不属于任何一个次现象域,则终止后续所有流程,并建议用户提交阿里云工单。打开选定的 references/<slug>.md 后,按顺序完成文档开头的「确定是否属于 GuestOS 问题」章节中的步骤,要求:
在进入域内细节排查之前,先根据现象域推荐的诊断工具进行快速排查。
references/phenomenon-domain.md 中当前现象域对应的「推荐的诊断集合」列,确定需要调用的诊断集合列表。若推荐列为「—」(无推荐的诊断集合),则跳过本阶段,直接进入「阶段 5」。references/create-diagnostic-report.md 中的步骤创建资源诊断报告执行诊断。如果用户不同意,则略过此阶段。注意:阅读 references/<slug>.md 的 GuestOS 内 部分:
references/utils/<component-slug>.md时,打开对应引用文档按顺序进行组件排查。要求通过 aliyun CLI 工具采集数据(需要采集当前现象域的 GuestOS 内数据时可调用 aliyun.ecs.RunCommand)。并且命令要尽可能详细,要尽量一次性收集本现象域所有所需数据,以减少 RunCommand 执行次数。最后,根据以下两种情况给出总结与建议:
references/diagnosis-report-template.md生成诊断报告。flowchart TD
A[阶段1 收集事实 + aliyun CLI采集元数据] --> B[阶段2 确定现象域(symptom-to-domain + phenomenon-domain)]
B --> C[选定 references/slug.md]
C --> D[阶段3 确认问题边界: GuestOS / 管控 / 客户端]
D -->|非 GuestOS 主因| E[先处理/网络/平台侧]
D -->|GuestOS| D2[阶段4 快速排查:资源诊断报告排查]
D2 -->|有推荐诊断集合| D3[调用 aliyun.ecs.CreateDiagnosticReport]
D2 -->|无推荐诊断集合| F[阶段5 域内排查: 组件排查 + 定位步骤]
D3 --> F
F --> G{需 utils / 更多数据?}
G -->|是| H[打开对应引用文档按顺序进行组件排查]
G -->|否| I[阶段6 总结与建议]
H --> I
E --> I
| 路径 | 用途 |
| --- | --- |
| symptom-to-domain.md | 自然语言 → 现象域路由 |
| phenomenon-domain.md | 权威表:唯一标识、概念、典型现象、slug、推荐的诊断工具 |
| aliyun-cli-cheatsheet.md | aliyun CLI 工具速查(白名单子命令) |
| create-diagnostic-report.md | 资源诊断报告创建与解读 |
| references/<slug>.md | 各现象域完整排查流程 |
| references/utils/<component-slug>.md | GuestOS 组件级排查 |
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take aliyun/alibabacloud-ecs-linux-troubleshooting from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.