aliyun

Operate Alibaba Cloud AgentLoop Dataset resources with aliyun CLI and the AgentLoop API version 2026-05-20. Use when requests concern AgentLoop datasets, data rows, Dataset schemas, embedding fields, semantic search, ExecuteQuery, AgentSpace data, 数据集, 数据写入, 数据查询, 语义检索, or ask to create/list/get/update AgentLoop datasets, append structured rows, run read-only SQL or SearchExpr queries, inspect query results, or debug aliyun agentloop Dataset commands.

Proactively use AgentLoop Recall to retrieve prior Alibaba Cloud AgentLoop experience through the bundled SearchContext CLI whenever the user asks or implies that prior work may help. Trigger for requests to check, search, recall, retrieve, look up, review, consult, reference, or compare prior experience, historical troubleshooting cases, past fixes, comparable incidents, lessons learned, old runbooks, previous remediations, or successful workflows before or during work. Also trigger for Chinese requests such as 先查历史经验、回忆类似案例、召回过往排障记录、看看之前有没有处理过类似问题、 参考以前怎么处理、找找之前的踩坑记录、翻一下历史排障、有没有类似经验、先看看过去的案例.

AgentLoop APM接入 / AI可观测接入 / 应用监控接入 / 自研探针 / 探针安装. Use for Python aliyun-bootstrap (aliyun-instrument), Java AliyunJavaAgent, Golang instgo, Node.js cms_node_sdk, PHP/.NET OpenTelemetry, ack-onepilot, LicenseKey, AgentLoop workspace agentloop-*. Also for LangChain, Dify, DashScope, LLM monitoring, AI tracing. Synonyms: onboard APM, install agent, probe setup, OpenTelemetry onboarding, application monitoring onboarding. Trigger even if the prompt starts with aliyun cms2 --update-beta when the goal is AgentLoop APM/AI onboarding. Do NOT use for CMS alerts, RUM, Prometheus rules, billing, or default-cms-* workspaces.

Diagnose Alibaba Cloud ECS public network access problems and VPC cloud service public network access problems. Covers ECS public network access, ECS public IP reachability, and ECS security group blocking (automatically handling the NAT-gateway egress path for instances without a public IP); and VPC cloud service public network access with NAT gateway, SNAT, route and EIP checks for DataWorks, SAE, ACK and other services. Use this when troubleshooting public network connectivity failures for ECS instances or VPC cloud services.

Alibaba Cloud PolarDB Database AI Assistant. For PolarDB MySQL/PostgreSQL cluster management, instance inspection, performance diagnostics, parameter explanation and change assessment, SQL/log analysis, backup, security audit, HA/DR, event analysis, and other PolarDB O&M operations. Use when user questions involve PolarDB, cluster IDs starting with pc-, PolarDB kernel/proxy versions, parameters, primary-standby switchover, IMCI columnar storage, or PolarDB console operations. This Skill is PolarDB-only.

PAI-EAS service diagnosis and troubleshooting. Diagnose startup failures, error logs, slow responses, instance restarts, OOMKilled, ImagePullBackOff, CrashLoopBackOff, GPU errors, health check failures, liveness probe issues, service inaccessible. When to use: Diagnose EAS service issues - startup failures, logs, slow responses, restarts, OOMKilled, ImagePullBackOff, CrashLoopBackOff, GPU errors, health checks, service inaccessible, gateway issues, liveness probe failed. Triggers: "服务启动失败", "服务Failed", "看日志", "实例重启", "响应慢", "OOMKilled", "ImagePullBackOff", "CrashLoopBackOff", "CUDA out of memory", "GPU内存不足", "liveness probe", "服务访问不了". Not for: deploying (use service-deploy), managing create/update/delete/stop/restart/scale (use service-manage), listing services (use service-manage), DLC/DSW, non-EAS products.

Deploy AI models as PAI-EAS inference services. Supports LLMs (Qwen, Llama), image gen (SD, SDXL), speech synthesis, and more. When to use: deploy models, create inference services, EAS deployment, model serving, deploy vLLM/SGLang/ComfyUI.

Perform batch inspection on Alibaba Cloud MSE Nacos instances, checking configuration count usage, connection count usage, QPS usage, and TPS usage. Supports two modes: inspecting a specified list of instance IDs, or inspecting all Nacos instances in a region by region. Triggers when the user needs to perform health inspection, capacity assessment, or usage check on MSE Registration & Configuration Center instances, or when the user mentions "inspect nacos", "check nacos instance usage", "nacos capacity inspection", "MSE registry inspection", "nacos inspection", "check nacos config count", "nacos connection count over limit", "nacos QPS/TPS usage", "inspect all nacos in a region", "inspect nacos instances in cn-hangzhou", "check nacos usage across all regions"

理赔核赔全案复审与决策专家。整合全案复审、流程合规检查能力。核查材料齐全性、立案合理性、医审核定准确性、理算计算正确性及作业规范性，综合输出核赔决策（准赔/减赔/拒赔/挂起）。当核赔专员需要对已完成医审和理算的案件进行终审决策、发现疑点需复核时触发。适用于核赔岗全案审核、赔付决策、案件质检场景。触发词：全案复审、怎么判、审核结论汇总。

理赔理算校验与调度专家。对进入理算环节的案件进行准入审查和数据完整性校验，确认理算前置条件满足后，通过MCP调用理算引擎完成实际金额计算，输出标准化理算书。当案件完成医审和责任认定后进入理算环节、需要计算应赔金额、生成理算书时触发。适用于理赔理算前置校验、理算参数校验、理算书生成场景。触发词：赔多少、理算、赔付金额。

"理赔报案受理与案件登记专家。整合报案信息结构化提取、保单状态核验、重复报案检测能力，提取出险时间、事故经过、伤亡情况、保单信息等关键要素，生成标准化报案记录并分配案件编号。当客户拨打报案电话、提交报案申请或上传报案材料时触发。适用于理赔受理岗报案登记、报案信息结构化录入、案件初始档案建立场景。触发词："报案登记"、"案件登记"、"报案受理"、"录入案件"。 触发词：理赔报案、案件录入、重复报案。"

"保险理赔材料智能分析工具。整合材料分类、OCR提取、完整性检查、单证审核、一致性校验、发票交叉验证、病程时间线梳理能力。采用前置解析+按需复用架构，基于多模态大模型对理赔图片文档进行全链路分析，输出标准化目录结构、病程摘要和审计报告。当用户需要对理赔材料、保险单证、医疗票据进行分类整理，或提及理赔材料分类、保险文档归档、医疗发票识别、材料审核、病程时间线时使用。触发词："理赔材料分类"、"材料完整性检查"、"材料一致性校验"、"理赔交叉验证"、"材料全量审核"、"病程时间线"。 触发词：理赔材料、材料齐不齐、病程时间线。"

对理赔案件进行多维度欺诈风险检测，综合分析材料一致性、行为模式、历史记录等信息，计算欺诈风险评分，识别虚假理赔、骗保欺诈等可疑信号。当需要评估理赔案件欺诈风险、识别可疑骗保行为、对高风险案件进行预警时触发。适用于理赔欺诈筛查、可疑案件调查决策、反欺诈合规管理场景。触发词：欺诈风险、骗保嫌疑、欺诈评分。

理赔结案通知与客户沟通专家。生成标准化的理赔通知书（赔付/拒赔/补件），并配套口头沟通话术与情绪安抚指导，确保书面函件合规、口头沟通专业。当需要出具理赔结果通知、生成拒赔说明书、通知客户补充材料、告知赔付金额，或需要与客户进行拒赔解释、情绪安抚时触发。适用于理赔结案通知生成、拒赔函件起草、补件通知书制作、客户沟通话术辅助场景。触发词：结案通知、通知客户、理赔通知书。

"理赔责任认定专家。整合免责条款审核、保单责任认定、费用责任匹配能力。通过OCR提取理赔材料内容，与保单免责条款逐条比对，识别可能触发的免责事项，评估拒赔风险等级，输出责任认定结论。当需要检查理赔材料中的免责条款适用性、判断是否存在拒赔事由、认定保险责任范围时触发。适用于理赔合规审核、责任认定、拒赔风险评估场景。触发词："免责"、"责免"、"拒赔"、"免责条款"、"责任认定"。 触发词：理赔责任、能不能赔、免责问题。"

对理赔费用清单中所有费用项（含检查、手术、耗材、护理、药品、床位费等）进行逐项合理性审核，识别不符合诊断的费用、超标准收费、重复收费；同时审查处方药品与诊断匹配性，识别超适应症用药、剂量异常、配伍禁忌，结合医保目录与临床指南输出核减建议，生成医学审查报告。当用户要求审核理赔费用明细、核定住院费用合理性、识别超标准或重复收费、审核药品合理性时触发。适用于医疗险理赔费用核定、住院费用审查、费用核减决策、理赔用药审核场景。触发词：住院费用、用药合理性、过度收费。

Pre-execution cost estimation for Alibaba Cloud CLI operations. Use this skill whenever a user asks "how much will this cost", before executing any chargeable operation (create / resize / renew / bandwidth change), or when planning a multi-step workflow whose total cost should be known up front. Covers the --estimate-cost flag (quote without executing), --estimate-cost-context (usage assumptions and future-state overrides for multi-step workflows), reading the quote JSON correctly (pricingMode, pricingUnit, delta amounts), and reconciling quotes against actual bills.

Shared reference for using Alibaba Cloud OpenAPI MCP Server Core effectively. Covers tool usage patterns, API exploration workflow, CLI command generation, scripted execution, async task polling, Infrastructure as Code (RunIaC), cross-account access, and safety policy configuration. Referenced by other alibabacloud-core skills as the canonical guide for MCP Core interactions.

Use this skill when users want to search, discover, browse, or find Alibaba Cloud (阿里云) agent skills. Triggers include: "find a skill for X", "search alicloud skills", "阿里云有什么 skill","阿里云", "搜索阿里云技能", "有没有管理 ECS/RDS/OSS 的 skill", "阿里云 skills 有哪些类目", "帮我找一个 skill", "browse alicloud skills", "list alicloud skill categories", "is there an alicloud skill that can...", "what alicloud skills are available", "XX Skill 的内容是什么", "我想了解阿里云 XX Skill 具体做什么","帮我安装阿里云 Skill","使用阿里云相关的skill", "阿里云 agent skill 市场", "搜一下阿里云的 skill", "建一个数据分析项目有没有相关 skill".

Generate Alibaba Cloud MCP Core RunScript-compatible Python scripts from natural-language cloud operation requests. Use when the user explicitly asks for RunScript scripts, MCP Core scripts, or sandbox-compatible cloud automation code. For standard SDK Python code with imports and credentials, use `alibabacloud-sdk-usage` instead.

This skill should be used when the user asks to "导入阿里云资源到 Terraform", "terraform import 阿里云", "将现有云资源纳入 Terraform 管理", "阿里云资源迁移 Terraform", "生成 terraform state", "import alicloud resources", "阿里云 IaC 迁移", "阿里云 Terraform 导入", or needs to manage existing Alibaba Cloud resources with Terraform. Guides users step-by-step through environment check, authentication, resource discovery, HCL generation, state import, validation, and dependency graph. Supports both one-time migration and incremental sync.

Suggest Alibaba Cloud `aliyun` CLI command strings from natural-language cloud operation requests, ready to pass as the `command` argument of the MCP `CallCLI` tool. Use when the user asks for the CLI command to do something, wants to manage cloud resources via aliyun, or asks "how do I do X with the aliyun CLI". Use `unifiedCli` from GenerateCLICommand (fallback to `cli` when empty) verbatim as the CallCLI command — no manual rewriting. Passes check_cli.py static validation. Suggest only — do not execute unless asked.

Use when the user wants Terraform HCL for Alibaba Cloud (Alicloud) infrastructure — new project or extending an existing one. Covers VPC, ECS, ApsaraDB RDS, OSS, SLB / ALB, Function Compute v3, ACK, and any other `alicloud_*` resource via the provider documentation and IaCService metadata. IaCService API calls should use the CallCLI-compatible tool exposed by the alibabacloud-core MCP server. For AWS → Alicloud migration, importing existing resources into state, or remote plan/apply execution, use a different skill. Triggers: "write terraform for alicloud", "generate alibaba cloud terraform", "alicloud HCL", "create alibaba cloud vpc/ecs/rds", "生成阿里云 Terraform", "阿里云 HCL", "用 Terraform 部署阿里云", "alicloud provider", "aliyun/alicloud", "terraform-provider-alicloud".

Install Alibaba Cloud Agent Toolkit end-to-end: verify and set up prerequisites (uv, Alibaba Cloud CLI, authentication, CLI plugins, MCP Server Core, bearer token exchange), then install the toolkit via openplugin. Use when: alibabacloud agent toolkit install, environment check, prerequisite check, setup alibabacloud, plugin install, toolkit setup, mcp core setup, aliyun CLI setup.

AI-agent-friendly Hologres CLI with safety guardrails and structured JSON output. Use for database operations, schema inspection, SQL execution, data import/export, Dynamic Table lifecycle management (V3.1+ syntax), and GUC parameter management. Triggers: "hologres cli", "hologres command", "hologres database", "dynamic table", "hologres查询", "hologres guc", "GUC parameter"

Hologres 运维诊断日报生成技能。生成一份"诊断结论 + 根因解释 + 行动建议"的每日巡检报告， 覆盖实例健康、可用性、计算资源、SQL 性能、成本治理、容量预测六大维度。 触发词：日报、每日巡检、daily report、运维日报、诊断日报、实例巡检报告、每日健康报告。 实例 / 计算组 / SQL 数据通过 `hologres instance-manage get` / `hologres warehouse` / `hologres sql run` 获取；云监控数据通过 `hologres metric query` 获取。

Hologres 实例 CPU 使用率异常诊断技能。当用户提到 CPU 打满、CPU 持续高位、Worker CPU 不均、负载诊断、CPU 归因分析、后台 Compaction 干扰等场景时使用。 以 instance_id + 时间窗口为输入，自动完成 CPU 状态分级（持续打满 / 持续高位 / 安全平稳）、四象限归因诊断（宏观定性 / 分布定位 / 查询归因 / 后台任务干扰），并输出结构化的 Markdown 诊断报告与治理行动清单。 云监控数据通过 `hologres metric query` / `hologres metric latest` 获取；元仓与 PG 系统表数据通过 `hologres sql run` 获取，全程享有 hologres-cli 的安全护栏、JSON 结构化输出与自动错误重试能力。

Hologres 实例内存使用率异常诊断技能。当用户提到内存打满、OOM、内存持续高位、Worker 内存不均、内存泄漏、内存倾斜、内存归因分析等场景时使用。 以 instance_id + 时间窗口为输入，自动完成内存水位形态判定（全局高 / 局部倾斜 / 持续不回落）、业务指标对齐、内存分类初筛（Query vs System/Cache）， 并沿 Query 主线、倾斜主线、Write/后台主线、System/元数据主线四大归因维度自动下钻，输出结构化的 Markdown 诊断报告与治理行动清单。 云监控数据通过 `hologres metric query` / `hologres metric latest` 获取；元仓与 PG 系统表数据通过 `hologres sql run` 获取；OOM/Jeprof/Coredump 通过 `holo oncall common` 获取。

Hologres Query Execution Plan Analyzer and Optimizer. Use for analyzing SQL performance issues, understanding EXPLAIN/EXPLAIN ANALYZE output, interpreting query operators, and providing optimization recommendations for Hologres queries. Users may provide a query_id, raw SQL query, or pasted EXPLAIN ANALYZE result text. SQL execution / 慢日志查询通过 `hologres sql run` / `hologres sql explain`；GUC 通过 `hologres guc` 操作。 Triggers: "hologres explain", "query plan", "execution plan", "sql optimization", "query performance", "hologres performance", "slow query", "query optimizer", "explain analyze", "query_id"

Hologres slow query log analysis and diagnosis skill. Use for analyzing slow queries, failed queries, query performance diagnosis, and log management in Alibaba Cloud Hologres. All SQL is executed via `hologres sql run` (`hologres sql run --no-limit-check`). Triggers: "hologres slow query", "hg_query_log", "query diagnosis", "慢Query分析", "Hologres性能诊断"

通过 Hologres AI Function 生成广告素材并模拟投放效果分析。适用于广告视频生成、素材转视频、虚拟投放模拟及 ROI 分析场景。

Hologres Knowledge Base Management: Build search & RAG knowledge bases on Hologres using full-text inverted index (Tantivy + BM25), HGraph vector index, and holo-search-sdk. Covers create knowledge base → ingest documents (with embeddings) → vector / full-text / hybrid search → Q&A with LLM. Triggers: "知识库", "knowledge base", "RAG", "向量检索", "vector search", "全文检索", "fulltext search", "倒排索引", "BM25", "HGraph", "holo-search-sdk", "embedding", "混合检索", "hybrid search", "Hologres 搜索", "Hologres search", "tantivy", "jieba", "ik 分词", "向量索引"

阿里云 ROS 模板部署技能，负责可用性查询、执行部署与失败恢复

使用 InfraGuard 审查 ROS 模板；有发现时直接修复并验证，初始扫描干净时直接输出模板

阿里云 Alibaba Cloud Policy as Code / InfraGuard 合规策略生成、校验与策略库查询

使用专用 ROS 模板询价工具预估 ROS 模板的月度部署费用，支持按需修复和校验模板问题

阿里云 ROS 模板生成——将架构方案转化为可部署的 ROS YAML 模板

阿里云 Alibaba Cloud ROS/Terraform IaC 模板生成、解释、完善、校验、询价与部署

判断用户输入是否为基础设施需求，并从中提取结构化的 IntentSpec

根据用户意图生成差异化候选架构方案，简单需求直接给出唯一方案

Use when the user wants to file an upstream bug / issue / feature request against the maxcompute-semantic skill itself ("report a bug", "file an issue", "提 issue", "file this upstream"). Routes to the internal Aone workitem tracker when the `a1` CLI is present, otherwise to GitHub Issues.

Use when answering MaxCompute data questions, writing SQL, inspecting schema for a query, using cold-start live metadata, reviewing SQL, cost-gating, executing SQL, or recording verified/failed query memory.

Use when creating, linking, editing, importing/exporting, diagnosing, or version-recovering MaxCompute semantic profiles.

Use when the user explicitly asks to build, refresh, onboard, or maintain a MaxCompute semantic package.

Review and apply semantic-package proposals generated from build evidence. Use when maintaining package semantics through an agent rather than writing direct annotations.

Use when recording, recalling, listing, showing, removing, clearing, or running reindex for verified/failed SQL and domain notes.

Use when listing, showing, searching, creating, testing, or removing MaxCompute UDFs and UDF resources.

Use when the user wants to run SQL against Alibaba Cloud MaxCompute (ODPS), inspect MaxCompute schemas, build or maintain a semantic package, enrich package semantics, manage MaxCompute UDFs, or record verified/failed SQL memory through the `mcs` CLI.

Generate or refine agent-usable CLIs for existing software/codebases using the CLI-Anything methodology. Use when the user wants to turn a GUI app, desktop tool, repository, SDK, or web/API surface into a structured CLI for agents; when adapting CLI-Anything into OpenClaw workflows; or when packaging a generated harness as an OpenClaw-compatible skill.

Data visualization, report generation, SQL queries, and spreadsheet automation. Transform your AI agent into a data-savvy analyst that turns raw data into actionable insights.

DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

通过阿里云 RDS OpenAPI 与只读 SQL 工具管理 RDS 实例。在用户需要查询/管理阿里云 RDS、执行只读 SQL、查看实例/监控/慢日志/参数时使用。需先配置环境变量 ALIBABA_CLOUD_ACCESS_KEY_ID、ALIBABA_CLOUD_ACCESS_KEY_SECRET，再通过命令行工具 alibabacloud-rds-instances-manage 列出并执行工具。

使用阿里云 RDS Copilot API,帮助用户完成 RDS 相关的智能问答、SQL 优化、实例运维和故障排查, 可直接调用 uv run ./scripts/call_rds_ai.py 脚本获取实时结果。

AgentBay CLI 双语 CHANGELOG 与 GitHub Release 发版 SOP。Use when preparing a release, updating bilingual CHANGELOG, translating release notes, creating tags, refreshing GitHub Release notes, or running make release-prep/backfill-release-notes.

将前端 API 能力封装成 agentbay-cli 命令的标准化流程

AgentBay CLI 命令文档同步流程（docs/、README、CHANGELOG readiness）

AgentBay CLI 需求开发全流程规范(分支管理、推送、提交、PR),不含具体需求内容

将当前本地分支推送到 aliyun 远程的同名分支（禁止推送到 master/main）

将当前本地分支推送到 origin 远程的同名分支（禁止推送到 master/main）

Automated acceptance workflow for Terraform Provider resource releases. Supports two modes - Aone-driven (from workitem link) and local-branch (already on feature branch). Covers code review, acceptance testing, fixing failures, and CI checks.

Code review SOP for Terraform Provider resource changes. Covers delete implementation, code-doc consistency, conditional logic documentation, doc quality, test quality, and common bug patterns. Used standalone or referenced by provider-resource-acceptance.

Fix documentation issues in Terraform Provider resources. Covers attribute value corrections, description updates, example fixes, and documentation consistency checks.

Extract requirement details from a URL (Aone workitem, GitLab Code Review, etc.) using MCP tools. Use when the user provides a link to a requirement or review system.

Add new attributes to an existing Terraform Provider resource. Covers the full workflow from code changes (Schema/Create/Read/Update), testing, documentation, to submitting a PR.

AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复，五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。

分析当前分支的全部变更，自动生成或更新 PR 标题和正文。聚焦内容质量：解释 why、归纳 what、标注测试方式，遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述，或已有 PR 需要更新描述。

编辑代码文件后自动运行对应格式化工具，保持代码风格一致。适用于任何 AI coding agent。

对当前分支的变更执行 AgentSight 专属代码审查。覆盖 6 个维度：硬性规则合规、eBPF 安全、FFI 边界、Footprint Ladder、流水线测试覆盖、文档同步。输出编号的 findings 列表，每条包含文件路径和行号。

Troubleshoot an Alibaba Cloud ECS Linux instance. Use when user needs to troubleshoot a problem on the specified ECS Linux instance, such as: boot stuck, SSH/VNC/Workbench, network, disk/FS, performance, crash/hang, clock, config, etc.

Linux 服务器安全入侵检测与取证工具，专为 AI Agent 设计。自动判断服务器是否被入侵， 提供完整证据链和可执行修复建议。50+ 安全分析器，10 个数据采集器，103+ MITRE ATT&CK 技术映射，支持 3 种部署模式。 当用户询问服务器安全、入侵检测、系统审计、恶意软件检测、安全事件响应时使用。 每当需要判断服务器是否被入侵、检查后门木马、分析安全事件时，优先使用此技能。 务必在发现安全异常时主动调用此技能，即使用户没有明确要求安全检查。

Linux 内核 CVE 漏洞检测与 PoC 验证工具。88 个内核漏洞检测器，CTF 挑战模式验证。需要 root 权限（sudo）运行。 务必在检测内核漏洞时使用此技能。每当需要验证 CVE 或执行 PoC 验证时，优先调用此技能。 当用户提到内核安全、CVE 检测、漏洞利用验证时，主动触发。

Use this skill whenever the user reports a problem with a Windows system, Windows Server, or Windows ECS instance, or asks to check, diagnose, inspect, or troubleshoot anything Windows-related. Covers network issues (ping, DNS, DHCP, firewall, SMB), RDP/remote desktop (connection failures, authentication, black screen, lag), storage/disk, system activation, Windows Update, performance slowdowns, user accounts/permissions, drivers, app crashes, security/certificate/TLS, scheduled tasks, or vague requests like 'check the system' or 'something is wrong.' Load this skill even if the user does not explicitly mention Windows but the context implies a Windows environment.

ADB MySQL 语义层交互 skill。支持 AI Agent 通过 SQL（主方式）或 OpenAPI / aliyun CLI（语义方式）搜索语义视图、执行语义 SQL、管理语义视图 DDL，以及通过 Python 脚本探索物理表元数据。两种方式均需 ADB SQL 连接来执行最终查询。当用户提出针对 ADB MySQL 的数据分析问题时使用。

OpenClaw conversation log collection and deep insight analysis Skill. Collects OpenClaw session logs (JSONL format) in real time and pushes them to Alibaba Cloud AnalyticDB MySQL (ADB) for storage. Provides a three-layer insight analysis architecture: L1 Operational Efficiency (Token efficiency, session depth, tool chain analysis, high-cost attribution, anomaly detection), L2 User Behavior (intent classification, task complexity, success rate, prompt quality, topic clustering, retry detection, thinking depth, user maturity), and L3 Organizational Cognition (tech stack heatmap, knowledge gap discovery, best practice extraction, skill candidate discovery, narrative report generation). Powered by SQL + Python + LLM. Use this Skill when you need to monitor OpenClaw usage, analyze costs, understand user behavior patterns, or generate organizational intelligence reports.

阿里云 AnalyticDB for MySQL 运维诊断助手。支持集群信息查询、性能监控、慢查询诊断、运行中SQL分析、表级优化建议等。当用户提到 ADB MySQL、AnalyticDB、慢查询、SQL 诊断、集群性能、查询RT、BadSQL、数据库优化、表分析、分区诊断、数据倾斜等话题时，应该使用该 Skill。即使用户没有明确说"使用 Skill"，只要涉及 ADB MySQL 相关的运维、诊断或监控问题，也应主动使用。