Datus-ai/Datus-agent

gen-table

Create database tables from SQL (CTAS) or natural language descriptions

원문 언어: 영어

gen-datasource

Generate a realistic synthetic data warehouse (single DuckDB database) from a business description and a row budget, then load it into the active datasource. The output is meant to be queried - by an AI agent answering data questions, by a business report, or…

원문 언어: 영어

init

Lightweight initialization of a project's core scope, optionally limited to files, tables or domains. Reads SQL and persisted lineage, human docs and live schema without querying table data. Writes confirmed knowledge to AGENTS.md and knowledge/*.md;…

원문 언어: 영어

dashboard-bootstrap

Bootstrap reference SQL, semantic models and metrics from BI dashboards, and rebuild selected dashboards as Datus visual dashboards through installed plugins. Use for dashboard context initialization, import, migration or reconstruction, including requests to…

원문 언어: 영어

superset-dashboard

Create, view, and manage Superset dashboards with charts and datasets

원문 언어: 영어

dosi-semantic-authoring

Dosi native OSI dataset, relationship, and metric authoring guidance

원문 언어: 영어

create-skill

Datus skill file format and packaging reference. Consult when creating or revising a skill requires optional frontmatter fields, directory layout, or agent.yml integration details.

원문 언어: 영어

storage-classify

Decide 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…

원문 언어: 영어

create-subagent

Create 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.

원문 언어: 영어

build-kb

Build 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…

원문 언어: 영어

extract-knowledge

Mine 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)

원문 언어: 영어

memory-organization

Audit 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…

원문 언어: 영어

session-summarize

Review 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…

원문 언어: 영어

data-migration

Activate 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.

원문 언어: 영어

table-validation

Validate 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…

원문 언어: 영어

transfer-reconciliation

Lightweight post-transfer reconciliation example — verify tool-reported row count parity and run a small target-side sanity check without re-scanning the source.

원문 언어: 영어

data-profiler

Profile data quality and distributions

원문 언어: 영어

report-generator

Generate formatted data reports from SQL query results

원문 언어: 영어

airflow-workflow

Execution guide for Airflow scheduled jobs — troubleshooting, updating, conn_id conventions, and cron references

원문 언어: 영어

scheduler-validation

Scheduler 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.

원문 언어: 영어

grafana-dashboard

Create, view, and manage Grafana dashboards with panels and datasources

원문 언어: 영어

bi-validation

BI 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

원문 언어: 영어

admin-tools

Administrative database tools (restricted access)

원문 언어: 영어

sql-analysis

Guided workflow for SQL data analysis using db_tools

원문 언어: 영어

sql-optimization

SQL query optimization techniques and best practices

원문 언어: 영어