datarobot-model-training
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:model-training
Train models, manage projects, and run AutoML experiments on DataRobot.
application/ai-skill
artifact →
AI Catalog manifest · DataRobot
DataRobot Agent Skills
DataRobot serves an AI Catalog
manifest at /.well-known/ai-catalog.json on datarobot.com, declaring
10 agentic resources
that a discovery service can index without asking anyone’s permission.
Structural grade · AI Catalog 1.0
Flavored
Fails a hard check in the data model. A catalog in spirit rather than in schema.
ARD conformance-test v0.9.1 (ards-project/ard-spec)
FAIL
Run against this exact body with the project’s own
conformance CLI — 21 critical errors.
Discovery path
predecessor
Answered only at
/.well-known/ai-catalog.json. ARD v0.91 renamed the path to /.well-known/ard.json and made the old one an optional courtesy, so a consumer implementing only the current spec will not find this manifest.
Declared spec version
1.0
The
specVersion in the manifest. 1.0 is current for the AI Catalog data model; anything lower is an earlier draft. ARD reads this field as transport-defined and ignores it.
⚠ Hard checks failed. An ARD client cannot assume this manifest parses to the model the specification defines.
entry-identifier-not-urn-airhost-no-identifier
The urn:ai: prefix is not sloppiness — it is the identifier scheme ARD itself
specified until ADR-0009
moved the namespace identifier from ai to air for URN validity. This publisher implemented against the earlier draft.
Optional affordances missing. None of these break a client, but each one costs the publisher search relevance or verifiability.
content-type-not-ai-catalog-jsonentry-no-representativeQueries
What this manifest advertises
datarobot-model-deployment
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:model-deployment
Deploy models, manage deployments, and configure prediction environments on DataRobot.
application/ai-skill
artifact →
datarobot-predictions
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:predictions
Make predictions, batch score, and generate prediction datasets on DataRobot.
application/ai-skill
artifact →
datarobot-feature-engineering
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:feature-engineering
Engineer features, run feature discovery, and analyze feature importance on DataRobot.
application/ai-skill
artifact →
datarobot-model-monitoring
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:model-monitoring
Monitor model performance, track data drift, and manage model health on DataRobot.
application/ai-skill
artifact →
datarobot-model-explainability
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:model-explainability
Explain model predictions, compute SHAP values, and run model diagnostics on DataRobot.
application/ai-skill
artifact →
datarobot-data-preparation
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:data-preparation
Upload datasets, manage data assets, and validate data for DataRobot workflows.
application/ai-skill
artifact →
datarobot-app-framework-cicd
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:app-framework-cicd
Set up CI/CD pipelines for DataRobot application templates with GitLab and GitHub Actions.
application/ai-skill
artifact →
datarobot-external-agent-monitoring
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:external-agent-monitoring
Instrument external agents with OpenTelemetry for DataRobot observability. Supports LangGraph, CrewAI, LlamaIndex, PydanticAI, and others.
application/ai-skill
artifact →
datarobot-agent-assist
urn:ai:github.com:datarobot-oss:datarobot-agent-skills:agent-assist
Build and deploy AI agents on DataRobot. Supports LangGraph, CrewAI, LlamaIndex, and base agents with MCP server and React frontend bundling.
application/ai-skill
artifact →
How it is served
The publishing guide asks for three things at the transport layer, because a crawler is the
consumer that matters and a crawler is a browser-shaped client.
- HTTPS only — yes (HTTP 200)
Content-Type: application/json— yesAccess-Control-Allow-Origin: *— yes
Evidence. Fetched
https://datarobot.com/.well-known/ai-catalog.json on 2026-09-13, HTTP
200. The verbatim body is stored alongside its manifest in the
DataRobot repository
as ai-catalog/datarobot-ai-catalog.json. Nothing on this page is derived
or generated: an AI Catalog manifest is served from the publisher’s own domain or it does not
exist, which makes it — like an
A2A Agent Card — one of the few agent artifacts that cannot be
produced on a provider’s behalf. Grades are recomputed on every build; the specification is a
v0.9 draft and
these verdicts will move when it does.
Work with this as data
Every descriptor here is available over the APIs.io API and to AI agents over MCP. Agent Discovery is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.