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