Menu
SkillsMP a collecté 30 skills depuis Datus-ai/Datus-agent. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 30 skills collectés sur 30.
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Create database tables from SQL (CTAS) or natural language descriptions
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Optional semantic-model profiling workflow that mines historical SQL and bounded column distributions before YAML authoring
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Dosi native OSI dataset, relationship, metric, and structured-window authoring contract
Langue du texte source : anglais
Generate MetricFlow metrics from natural language business descriptions
Langue du texte source : anglais
MetricFlow semantic model authoring specification — YAML structure, field classification, validation, and Knowledge Base publishing
Langue du texte source : anglais
OSI core schema metric authoring specification — metric expression shape, Datus extension hints, window/period-over-period semantics, and skip gates
Langue du texte source : anglais
OSI core schema semantic model authoring specification — field roles, structural keys, Datus extension hints, relationships, and validation
Langue du texte source : anglais
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".
Langue du texte source : anglais
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.
Langue du texte source : anglais
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)
Langue du texte source : anglais
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…
Langue du texte source : anglais
Lightweight post-transfer reconciliation example — verify tool-reported row count parity and run a small target-side sanity check without re-scanning the source.
Langue du texte source : anglais
Profile data quality and distributions
Langue du texte source : anglais
Generate formatted data reports from SQL query results
Langue du texte source : anglais
Execution guide for Airflow scheduled jobs — troubleshooting, updating, conn_id conventions, and cron references
Langue du texte source : anglais
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.
Langue du texte source : anglais
Create, view, and manage Grafana dashboards with panels and datasources
Langue du texte source : anglais
Create, view, and manage Superset dashboards with charts and datasets
Langue du texte source : anglais
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
Langue du texte source : anglais
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…
Langue du texte source : anglais
Administrative database tools (restricted access)
Langue du texte source : anglais
Guided workflow for SQL data analysis using db_tools
Langue du texte source : anglais
SQL query optimization techniques and best practices
Langue du texte source : anglais