datus-ai
- 90 skills
- 0 followers
- 6 hours ago last updated
- ▌ Datus Blog · datus-ai bundleResearch, write, wire in, preview and PR one SEO blog post for datus.ai (the Datus-website repo) end to end, then record it so no topic is ever written twice. Use when the operator asks for a blog post — 写一篇 blog、从 /glossary 挑一个方向写文章、写一篇 SEO 博客、新增 blog post、write a blog post, add a post to /blog, publish an article on datus.ai — or asks to iterate on an existing blog PR's review feedback.
- ▌ DB Dws SQL · datus-aiGenerate, review, and understand Huawei Cloud GaussDB(DWS) SQL. Use for DWS queries, DDL, DML, table design, and SQL rewrites where PostgreSQL 9.2 compatibility, ORA/TD/MySQL compatibility-mode semantics, row/column storage, data distribution, partitioning, or materialized-view version limits matter.
- ▌ DB Tidb SQL · datus-aiGenerate, review, and understand TiDB SQL. Use for TiDB queries and DDL where MySQL compatibility, unsupported constructs, silently-ignored clauses, or write-hotspot avoidance can affect correctness or performance.
- ▌ DB Doris SQL · datus-aiGenerate, review, and understand Apache Doris SQL. Use when the target engine is Apache Doris (not StarRocks or MySQL) for queries, OLAP DDL with the Duplicate/Unique/Aggregate key models, bucketing and partitioning, synchronous and asynchronous materialized views, multi-catalog addressing, and loading through Stream Load, Routine Load, or INSERT INTO SELECT over a TVF or catalog.
- ▌ DB Oracle SQL · datus-aiGenerate, review, and understand Oracle Database 19c SQL and PL/SQL. Use for Oracle queries, DDL, DML, stored procedures, functions, packages, anonymous blocks, profiling, transfers, and SQL rewrites where namespace, identifier, pagination, data type, alias, procedural, or write syntax differs from other dialects.
- ▌ DB Gaussdb SQL · datus-aiGenerate, review, and understand GaussDB / openGauss SQL. Use for GaussDB queries, DDL, DML, table design, and SQL rewrites where PostgreSQL compatibility, A/B/PG database compatibility modes, distributed deployments, or version-specific syntax matter.
- ▌ DB Bigquery SQL · datus-aiGenerate or review Google BigQuery Standard SQL, especially when project.dataset qualification, nested data, time semantics, partition pruning, or BigQuery-specific DDL affect correctness or cost.
- ▌ DB Hologres SQL · datus-aiGenerate, review, and understand Alibaba Cloud Hologres SQL. Use for Hologres queries, DDL, DML, table design, foreign tables, data movement, and SQL rewrites where PostgreSQL compatibility, namespaces, storage properties, constraints, transactions, or version-specific syntax matter.
- ▌ DB Snowflake SQL · datus-aiGenerate, review, and understand Snowflake SQL. Use for Snowflake queries, DDL, DML, MERGE, semi-structured data, stages, COPY operations, materialized views, profiling, transfers, and rewrites where identifiers, namespaces, data types, functions, constraints, or loading syntax differ from other dialects.
- ▌ DB Starrocks SQL · datus-aiGenerate, review, and understand StarRocks SQL. Use for StarRocks queries, OLAP table DDL, DML, materialized views, catalogs, S3/GCS imports with FILES() or Broker Load, Stream Load, Routine Load, and rewrites where MySQL compatibility, table types, distribution, functions, or loading semantics can affect correctness.
- ▌ DB Maxcompute SQL · datus-aiGenerate and review Alibaba Cloud MaxCompute or ODPS SQL. Use when namespace mode, partition scanning, data type editions, write semantics, or transactional-table restrictions affect SQL correctness or cost.
- ▌ Table Validation · datus-aiValidate the column contract of a newly written table — column set, types, and nullability match expectations. Object existence and row counts are handled by the builtin layer and are out of scope. Data-content assertions belong to project-level validator skills.
- ▌ Extract Knowledge · datus-aiMine shortest atomic facts from (question + gold_sql) pairs into ./knowledge/*.md; either by simulating SQL drafting (lite) or by driving the gen_sql subagent in blind iteration (deep)
- ▌ Grafana Dashboard · datus-aiCreate, view, and manage Grafana dashboards with panels and datasources
- ▌ Session Summarize · datus-aiReview the current chat session and persist its valuable takeaways — business facts/rules, validated SQL, metric/model definitions, durable preferences, project conventions, reusable workflows — by classifying each via storage-classify and routing it to the right store. Present a Summary Manifest and STOP for confirmation before any heavy generation. Use at the end of a working session or when the user asks to capture what was learned.
- ▌
- ▌ Dashboard Bootstrap · datus-aiBootstrap project reference SQL and metrics from a BI dashboard through an installed plugin. Use when the user asks to initialize, import, extract, or build context, reference SQL, semantic models, or metrics from a dashboard or requests dashboard bootstrap.
- ▌ Memory Organization · datus-aiAudit and reorganize every persistent store — semantic_models, metrics, reference_sql, knowledge, memory, AGENTS.md, skills — verifying each item sits in the correct store per storage-classify, and surfacing duplicates, misclassifications, conflicts, and stale/erroneous entries. Produce a Remediation Plan, STOP for confirmation, then execute. Use ask_user only for genuine decisions during analysis. If nothing needs fixing, report it and stop.
- ▌ Scheduler Validation · datus-aiScheduler validator driven by ValidationHook — read-only static verification of scheduled jobs (schedule correctness, configuration, runtime context already collected by deterministic hook). Does not trigger test runs.
- ▌ Osi Metrics Authoring · datus-aiOSI core schema metric authoring specification — metric expression shape, Datus extension hints, window/period-over-period semantics, and skip gates
- ▌ Dosi Semantic Authoring · datus-aiDosi native OSI dataset, relationship, and metric authoring guidance
- ▌ Transfer Reconciliation · datus-aiLightweight post-transfer reconciliation example — verify tool-reported row count parity and run a small target-side sanity check without re-scanning the source.
- ▌ Metricflow Semantic Authoring · datus-aiMetricFlow semantic model authoring specification — YAML structure, field classification, validation, and Knowledge Base publishing
- ▌ Init · datus-aiLightweight project initialization — optionally scoped to specific files / tables / datasources / domains. Infer the project goal and in-scope datasources, scan the in-scope file tree and database metadata (db/table/desc/sample), classify into business domains, then write an AGENTS.md inventory skeleton plus the cheap file-based stores (atomic facts to ./knowledge/*.md via lite extract-knowledge, durable preferences to memory). Stops short of the expensive vector-indexed stores (semantic_models / metrics / reference_sql). Single confirmation-free pass, low token cost.
- ▌
- ▌
- ▌ Build Kb · datus-aiBuild the project's vector-indexed knowledge base from files plus database metadata — optionally scoped to specific files / tables / datasources / domains. Scan the in-scope material, classify it into business domains, explore each domain's tables and docs in parallel with explore subagents (the validated-query SQL corpus is enumerated directly, no explore needed), then (after the user confirms a generation manifest — or directly, in the same turn, when the user has waived confirmation) route every artifact to its store via storage-classify, generating semantic_models / metrics / reference_sql (and mining any extra knowledge), and refresh AGENTS.md's KB index. The lightweight /init handles the AGENTS.md inventory plus file-based knowledge/memory; this skill owns the heavy vector-store generation.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Create Skill · datus-ai bundleCreate new Datus skills from scratch. Use when users want to build a new skill, scaffold a skill directory, or capture a workflow as a reusable skill. Trigger phrases include "create a skill", "make a skill for", "turn this into a skill", "new skill".
- ▌ Bi Validation · datus-aiBI validator driven by ValidationHook — inspects every dashboard, chart, and dataset delivered in the run, verifies config quality (chart type, metrics, dimensions, dataset wiring) and data presence via get_chart_data when supported
- ▌ Data Migration · datus-aiActivate when the gen_job agent detects that the source and target databases differ. Covers cross-database transfer lifecycle - type mapping via adapter Mixin hints, DDL generation, data transfer via transfer_query_result, and lightweight reconciliation.
- ▌ Optimize Skill · datus-aiOptimize and improve existing Datus skills. Use when users want to edit a skill, improve its instructions, optimize its description for better triggering, or analyze skill performance based on usage sessions. Trigger phrases include "optimize skill", "improve skill", "edit skill", "fix skill", "skill not triggering".
- ▌ Create Subagent · datus-aiCreate or update custom Datus subagents by editing the loaded agent.yml. Use when a workflow needs persistent agentic_nodes scoped to already-built tables, metrics, or reference SQL.
- ▌ Airflow Workflow · datus-aiExecution guide for Airflow scheduled jobs — troubleshooting, updating, conn_id conventions, and cron references
- ▌ Storage Classify · datus-aiDecide where a produced artifact must be persisted before writing it, then route semantic_models and metrics through semantic_modeling, reference_sql through gen_sql_summary, knowledge through extract-knowledge (lite), memory through add_memory, skills through create-skill, and AGENTS.md edits directly. Load before persisting any business fact, validated SQL, metric/model definition, session preference, project convention, or reusable workflow.
- ▌ Optimize Datus Plugin · datus-ai bundleAnalyze Datus plugin E2E run artifacts and iteratively improve the current plugin until deterministic correctness and process-efficiency gates pass. Use when a datus-agent session failed or was slow/wasteful, when reviewing generated files and session/tool traces, when automating a plugin development optimization loop, or when comparing repeated workflow runs. Invoke directly from Claude Code or Codex; no separate optimization CLI is required.
- ▌ Build Datus Plugin E2e · datus-ai bundleBuild and run deterministic, LLM-driven end-to-end workflows for Datus plugins using the repository's pytest harness. Use when creating plugin E2E coverage, testing a plugin through a pinned datus-agent branch, provisioning isolated minikube/MinIO/Flink fixtures, defining programmatic pass/fail oracles, or diagnosing an E2E harness run. Invoke directly from Claude Code or Codex; do not create a standalone test CLI.
- ▌ Datus Plugin Development · datus-ai bundleWrap a user-provided SDK / REST API / documentation into an installable Datus plugin. Produces a design draft FIRST (config schema, CLI command list with doc citations + permission rules, bundled-skill plan), then STOPS for user confirmation before writing any code. Fully self-contained — the entire datus-plugin.yml manifest contract is inlined below.
- ▌
- ▌ K8S Setup · datus-aiConfigure a managed-cloud or kubeconfig-backed environment for the `datus k8s` plugin
- ▌ Flink SQL · datus-aiPrepare and run Apache Flink SQL scripts as Application Mode jobs. Use when packaging or deploying a .sql task, choosing the SQL job entry point, deciding whether a Flink 1.x application needs a version-matched runner JAR or a Flink 2.x application can use the built-in SqlDriver without jarURI, supplying connector/catalog/filesystem dependencies, or handing a validated SQL job to the Flink Kubernetes Operator.
- ▌ Airflow · datus-aiOperate a remote Apache Airflow 2.x or 3.x deployment (list/trigger/monitor DAGs, tasks, variables, connections, pools, backfills) and deploy DAG files to S3 or a dags folder via the `datus airflow` CLI
- ▌ Grafana · datus-aiOperate Grafana dashboards, panels, datasources, queries, annotations, library panels, playlists, correlations, and unified alerting through `datus grafana`
- ▌ Statsig · datus-aiRead Statsig metrics & experiment results, author warehouse-native metric SQL, and drive ETL ingestion via the `datus statsig` CLI (Console API)
- ▌ K8S Jvm Classpath · datus-aiDiagnose classpath, ServiceLoader/SPI, and classloader failures in a JVM service running on Kubernetes — NoClassDefFoundError, ClassNotFoundException, "could not find a file io implementation for scheme", UnsupportedSchemeException, missing connector/catalog/FileIO/FileSystem factory, plugin JAR present but not discovered, or a version that does not match the deployed image. Use for Flink, Paimon, Iceberg, Hive, Spark, Trino, StarRocks, and other JVM data services; probes read-only through `datus k8s exec`.
- ▌ S3 · datus-aiBrowse and move S3 data (ls/stat/cat/head/cp/sync/mv/rm/presign) and run S3 Select SQL over CSV/JSON/Parquet objects via the `datus s3` CLI
- ▌ Superset · datus-aiOperate Apache Superset dashboards, charts, datasets, SQL Lab, reports, tags, annotations, RLS, cache, and migration through `datus superset`
- ▌ Flink Local Dev · datus-aiRun and validate an Apache Flink SQL job on the current machine, in an in-process MiniCluster driven by the Flink SQL Client, before promoting it to production. Use for local Flink SQL development, debugging a SQL script, bounded replay of development Kafka/JDBC/CDC sources, shadowing every sink with print/blackhole/local filesystem, EXPLAIN plan checks, output assertions, and the parity checklist that precedes handing the job to `flink-k8s-operator`. A local run never writes to a production sink, consumer group, or checkpoint path.
- ▌ Airflow Setup · datus-aiConfigure an environment profile for the `datus airflow` plugin (API endpoint, credentials, optional S3/dags-folder deployment target)
- ▌ Ecs · datus-aiRun and monitor tasks on existing Amazon ECS/Fargate clusters, scale services, inspect task definitions, and read task logs via the `datus ecs` CLI
- ▌ Eks · datus-aiInspect Amazon EKS clusters, node groups, add-ons, access entries, Fargate profiles, updates, upgrade insights, and caller identity
- ▌ Emr · datus-aiSubmit and monitor steps on existing Amazon EMR (on EC2) clusters, inspect clusters/instances, and read step logs from S3 via the `datus emr` CLI
- ▌ Iam · datus-aiInspect AWS IAM read-only — roles, users, managed policies, policy documents, and simulate whether a principal can perform an action (the AccessDenied diagnostic) via the `datus iam` CLI
- ▌ Gcs · datus-aiBrowse, inspect, preview, upload, download, copy, sync, move, delete, and sign Google Cloud Storage objects, and inspect buckets or replace lifecycle rules with datus gcs. Use for gs:// data movement, artifact publishing, signed URLs, or GCS lifecycle management.
- ▌ Gke · datus-aiInspect Google Kubernetes Engine clusters, node pools, operations, server versions, and authentication, and hand GKE credentials to the datus k8s plugin. Use for GKE inventory, health, upgrade diagnostics, or Kubernetes access through a GKE provider profile.
- ▌
- ▌ Statsig Setup · datus-aiConfigure an environment profile for the `datus statsig` plugin (Console API base URL, API key, version)
- ▌ Flink K8S Operator · datus-aiBuild, deploy, operate, upgrade, snapshot, and troubleshoot Apache Flink jobs running on the Flink Kubernetes Operator. Use for FlinkDeployment application clusters, session clusters, FlinkSessionJob, FlinkStateSnapshot, Java/Scala Maven or Gradle projects, PyFlink projects, minikube image loading, remote registry publishing, job status, logs, events, suspend/resume, restart, stateful upgrades, recovery, or deletion. Delegate every Kubernetes workload operation to `datus k8s`.
- ▌ Aks · datus-aiInspect Azure Kubernetes Service clusters, node pools, maintenance configurations, upgrades, and authentication, and hand Microsoft Entra credentials to datus k8s. Use for AKS inventory, health, upgrade planning, or Kubernetes access through an AKS provider profile.
- ▌ Ack · datus-aiInspect Alibaba Cloud ACK clusters, node pools, add-ons, tasks, and authentication, and hand temporary ACK credentials to datus k8s. Use for ACK inventory, health, change diagnostics, add-on status, or Kubernetes access through an ACK provider profile.
- ▌ Glue · datus-aiBrowse the AWS Glue Data Catalog (databases/tables/schema/partitions) and run/monitor Glue crawlers and ETL jobs (with logs) via the `datus glue` CLI
- ▌ Mwaa · datus-aiInspect Amazon MWAA (Managed Airflow) environments, mint web-login/CLI tokens, and run the Airflow CLI over the MWAA REST endpoint via the `datus mwaa` CLI
- ▌ S3 Setup · datus-aiConfigure an environment profile for the `datus s3` plugin (AWS region + credentials, optional default bucket and SSE-KMS key)
- ▌ Superset Setup · datus-aiConfigure an Apache Superset environment profile for the `datus superset` plugin
- ▌ Adls · datus-aiBrowse, inspect, preview, upload, download, copy, sync, move, delete, and sign Azure Blob or ADLS Gen2 paths, and inspect filesystems or manage ACLs with datus adls. Use for abfss:// data movement, artifacts, SAS URLs, or hierarchical namespace ACL operations.
- ▌ Ecs Setup · datus-aiConfigure an environment profile for the `datus ecs` plugin (AWS region + credentials, optional default cluster and CloudWatch log group)
- ▌
- ▌ Emr Setup · datus-aiConfigure an environment profile for the `datus emr` plugin (AWS region + credentials, optional default cluster and S3 log_uri)
- ▌ Iam Setup · datus-aiConfigure an environment profile for the `datus iam` plugin (AWS credentials for read-only IAM inspection)
- ▌ Gcs Setup · datus-aiConfigure or troubleshoot a Google Cloud Storage profile for datus gcs, including ADC, credential files, service-account impersonation, default bucket, scopes, custom endpoints, retries, permissions, and verification.
- ▌ Gke Setup · datus-aiConfigure or troubleshoot a Google Kubernetes Engine profile and its paired datus k8s provider profile, including ADC, service-account impersonation, endpoint selection, scopes, retries, and verification.
- ▌ Grafana Query Export · datus-aiExport every Grafana dashboard target—SQL, PromQL, LogQL, TraceQL, Flux, InfluxQL, Graphite, expressions, and unknown JSON—into project context files
- ▌ Aks Setup · datus-aiConfigure or troubleshoot an Azure Kubernetes Service profile and its paired datus k8s provider profile, including Azure cloud, DefaultAzureCredential, service principals, managed identity, private endpoints, and verification.
- ▌ Ack Setup · datus-aiConfigure or troubleshoot an Alibaba Cloud ACK profile and its paired datus k8s provider profile, including the default credential chain, access keys or STS, RAM roles, RRSA/external credentials, endpoint selection, and verification.
- ▌ Glue Setup · datus-aiConfigure an environment profile for the `datus glue` plugin (AWS region + credentials, optional cross-account catalog_id)
- ▌ Mwaa Setup · datus-aiConfigure an environment profile for the `datus mwaa` plugin (AWS region + credentials, optional default MWAA environment name)
- ▌ Superset Query Export · datus-aiExport the compiled SQL behind every Superset dashboard chart into project-local reference files and a manifest for project context
- ▌ Adls Setup · datus-aiConfigure or troubleshoot an Azure Blob or ADLS Gen2 profile for datus adls, including Entra DefaultAzureCredential, service principals, managed identity, account key or SAS, sovereign clouds, HNS behavior, permissions, and verification.
- ▌ Grafana Dashboard Authoring · datus-aiAuthor and safely revise Grafana dashboards and panels, including datasource resolution and panel query verification
- ▌ Superset Dashboard Authoring · datus-aiAuthor and safely revise Superset datasets, charts, and dashboards through the official REST API CLI
- ▌ Cloudwatch · datus-aiQuery AWS CloudWatch logs (groups/streams/tail/Logs Insights), metrics, alarms and dashboards through the `datus cloudwatch` CLI
- ▌ Quicksight · datus-aiManage Amazon QuickSight end-to-end — datasets/datasources/dashboards/analyses/templates/themes/folders lifecycle, users/groups/namespaces, SPICE refresh (with --wait) and schedules, embed URLs, asset-bundle export/import, and account info — via the `datus quicksight` CLI
- ▌ Cloudwatch Setup · datus-aiConfigure an environment profile for the `datus cloudwatch` plugin (AWS region + credentials)
- ▌ Quicksight Setup · datus-aiConfigure an environment profile for the `datus quicksight` plugin (AWS region + credentials and the required aws_account_id)
- ▌ Emr Serverless · datus-aiOperate AWS EMR Serverless applications and run/monitor Spark job runs (with the live Spark UI) via the `datus emr-serverless` CLI
- ▌ Emr Serverless Setup · datus-aiConfigure an environment profile for the `datus emr-serverless` plugin (AWS region + credentials, default application id and execution role)