Datus-ai/Datus-agent

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.

原文语言：英语

dashboard-bootstrap

Bootstrap 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.

原文语言：英语

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…

原文语言：英语

gen-table

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

原文语言：英语

init

Lightweight 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…

原文语言：英语

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…

原文语言：英语

semantic-sql-history-profiler

Optional semantic-model profiling workflow that mines historical SQL and bounded column distributions before YAML authoring

原文语言：英语

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…

原文语言：英语

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…

原文语言：英语

dosi-semantic-authoring

Dosi native OSI dataset, relationship, metric, and structured-window authoring contract

原文语言：英语

gen-metrics

Generate MetricFlow metrics from natural language business descriptions

原文语言：英语

metricflow-semantic-authoring

MetricFlow semantic model authoring specification — YAML structure, field classification, validation, and Knowledge Base publishing

原文语言：英语

osi-metrics-authoring

OSI core schema metric authoring specification — metric expression shape, Datus extension hints, window/period-over-period semantics, and skip gates

原文语言：英语

osi-semantic-authoring

OSI core schema semantic model authoring specification — field roles, structural keys, Datus extension hints, relationships, and validation

原文语言：英语

create-skill

Create 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".

原文语言：英语

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.

原文语言：英语

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)

原文语言：英语

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…

原文语言：英语

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.

原文语言：英语

data-profiler

Profile data quality and distributions

原文语言：英语

report-generator

Generate formatted data reports from SQL query results

原文语言：英语

airflow-workflow

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

原文语言：英语

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.

原文语言：英语

grafana-dashboard

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

原文语言：英语

superset-dashboard

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

原文语言：英语

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

原文语言：英语

optimize-skill

Optimize 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…

原文语言：英语

admin-tools

Administrative database tools (restricted access)

原文语言：英语

sql-analysis

Guided workflow for SQL data analysis using db_tools

原文语言：英语

sql-optimization

SQL query optimization techniques and best practices

原文语言：英语