Datus-ai/Datus-agent

The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data.

1.7kStars on the repository
31Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

airflow-workflow

01

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 24 tokens

bi-validation

02

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 getchartdata when supported.

not rated 1.7k +20 yesterday A 47 tokens

build-kb

03

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 parallel with explore subagents (the validated-query SQL…

not rated 1.7k +20 yesterday A 158 tokens

create-skill

04

Datus-ai/Datus-agent

Skill Claude CodeCodex

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".

not rated 1.7k +20 yesterday A 61 tokens

create-subagent

05

Datus-ai/Datus-agent

Skill Claude CodeCodex

Create or update custom Datus subagents by editing the loaded agent.yml. Use when a workflow needs persistent agenticnodes scoped to already-built tables, metrics, or reference SQL.

not rated 1.7k +20 yesterday A 40 tokens

dashboard-bootstrap

06

Datus-ai/Datus-agent

Skill Claude CodeCodex

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.

not rated 1.7k +20 yesterday A 50 tokens

data-migration

07

Datus-ai/Datus-agent

Skill Claude CodeCodex

Activate when the genjob 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 transferqueryresult, and lightweight reconciliation.

not rated 1.7k +20 yesterday A 49 tokens

extract-knowledge

09

Datus-ai/Datus-agent

Skill Claude CodeCodex

Mine shortest atomic facts from (question + goldsql) pairs into ./knowledge/.md; either by simulating SQL drafting (lite) or by driving the gensql subagent in blind iteration (deep).

not rated 1.7k +20 yesterday A 45 tokens

gen-metrics

10

Datus-ai/Datus-agent

Skill Claude CodeCodex

Generate MetricFlow metrics from natural language business descriptions.

not rated 1.7k +20 yesterday A 13 tokens

gen-table

11

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 16 tokens

grafana-dashboard

12

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 18 tokens

init

13

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 domains, then write an AGENTS.md inventory skeleton plus the cheap…

not rated 1.7k +20 yesterday A 113 tokens

memory-organization

14

Datus-ai/Datus-agent

Skill Claude CodeCodex

Audit and reorganize every persistent store — semanticmodels, metrics, referencesql, 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…

not rated 1.7k +20 yesterday A 95 tokens

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 27 tokens

optimize-skill

16

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 skill", "edit skill", "fix skill", "skill not triggering".

not rated 1.7k +20 yesterday A 68 tokens

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 33 tokens

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 30 tokens

Datus-ai/Datus-agent

Skill Claude CodeCodex

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.

not rated 1.7k +20 yesterday A 37 tokens

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 24 tokens

session-summarize

21

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 right store. Present a Summary Manifest and STOP for…

not rated 1.7k +20 yesterday A 86 tokens

storage-classify

22

Datus-ai/Datus-agent

Skill Claude CodeCodex

Decide where a produced artifact must be persisted before writing it, then route semanticmodels and metrics through semanticmodeling, referencesql through gensqlsummary, knowledge through extract-knowledge (lite), memory through addmemory, skills through create-skill, and AGENTS.md edits directly. Load before…

not rated 1.7k +20 yesterday A 86 tokens

superset-dashboard

23

Datus-ai/Datus-agent

Skill Claude CodeCodex

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

not rated 1.7k +20 yesterday A 17 tokens

table-validation

24

Datus-ai/Datus-agent

Skill Claude CodeCodex

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 skills.

not rated 1.7k +20 yesterday A 51 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: