Home / datarobot-oss / datarobot-agent-skills · skills/datarobot-agent-llm-selection/SKILL.md · GitHub

datarobot-agent-llm-selection skillC

datarobot-agent-llm-selection is agent-read markdown (skill) from datarobot-oss/datarobot-agent-skills: Use when the user wants to configure LLM integration for a DataRobot agent application. This skill helps to change LLM model, switch between the LLM integrations the project supports (LLM Gateway, a DataRobot-deployed LLM, an external provider, an LLM Blueprint, and any others its config declares), or set up provider credentials. The skill reads the project's .datarobot/cli/llm.yml for the real options, interviews the user, then runs sync_llm_env.py with the chosen values as CLI args to merge in.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# DataRobot LLM gateway configuration

Configure LLM integration **without hand-editing `.env`**. The skill drives
`sync_llm_env.py` with the user's answers as CLI arguments.

## Resolve script path once per session

`<skill_scripts_dir>` = the `scripts/` subdirectory of the directory containing this `SKILL.md`.

```shell
ls <skill_scripts_dir>/sync_llm_env.py
```

## Hard rules

1. **Never** ask the user to paste API keys or `DATAROBOT_API_TOKEN` in chat
2. **Never** read, copy, echo, or pass `DATAROBOT_API_TOKEN` yourself. The
   token lives in `$XDG_CONFIG_HOME/datarobot/drconfig.yaml` (default
   `~/.config/datarobot/drconfig.yaml`), populated by `dr auth login`, and
   the `dr` CLI reads it internally. Do not run `cat drconfig.yaml`,
   `cat .env`, `env | grep TOKEN`, `echo $DATAROBOT_API_TOKEN`,
   `curl -H "Authorization: Bearer $..."`, or any equivalent one-liner
3. **Never** pass secrets as CLI args to `sync_llm_env.py` or write them to
   tracked files
4. **Never** set provider credentials for an integration whose config section
   doesn't declare them. Let `sync_llm_env.py` decide — it reads the section
   from the project's config
…

Read the whole file at its exact version.

How to install

Latest version
mdr add datarobot-oss/datarobot-agent-skills/datarobot-agent-llm-selection@git:20260827.173ef3c
Exact content
mdr add datarobot-oss/datarobot-agent-skills/datarobot-agent-llm-selection@sha256:b5444ba253544552

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wfec46xf3fetayqa.svg)](https://markdownregistry.com/a/art_wfec46xf3fetayqa)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260827.173ef3c latest2026-08-27 173ef3c 14,457 BC view

Audit of the latest version

C  15 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No prompt-injection phrasing (matched: Do not tell the user)
  • fail: No instruction to read or print local credentials (matched: cat .env)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14457 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

datarobot-oss/datarobot-agent-skills · 27 stars · license Apache-2.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wfec46xf3fetayqa
GET https://markdownregistry.com/api/v1/resolve?ref=datarobot-oss/datarobot-agent-skills/datarobot-agent-llm-selection
GET https://markdownregistry.com/api/v1/blob/b5444ba253544552e9b93ecfd990540b78b2e1f3b3f25113116c972001d216eb

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from datarobot-oss/datarobot-agent-skills

progressive-disclosure skill
datarobot-oss/datarobot-agent-skills · .skills/progressive-disclosure/SKILL.md · Refactor large DataRobot skill files by moving detailed content into directly linked reference files while preserving…
git:20260522.e07bcb1 · audit A · 27 stars
AGENTS.md agents
datarobot-oss/datarobot-agent-skills · AGENTS.md
git:20260827.ad4f673 · audit A · 27 stars
CLAUDE.md claude
datarobot-oss/datarobot-agent-skills · CLAUDE.md
git:20260519.505d6df · audit B · 27 stars
datarobot-agent-assist skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-agent-assist/SKILL.md · Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive model) to DataRobot…
git:20260921.83fdf11 · audit B · 27 stars
datarobot-agent-assist-build skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-agent-assist/agent-assist-build/SKILL.md · Use when the user wants to design, build, code, or deploy an AI agent on DataRobot; mentions agent_spec.md, dress…
git:20260921.783ecc2 · audit A · 27 stars
datarobot-agent-assist-simulate skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-agent-assist/agent-assist-simulate/SKILL.md · Use when the user wants to adversarially test, evaluate, or harden an implemented AI agent before deployment; mentions…
git:20260805.1ef1aa0 · audit B · 27 stars
datarobot-app-framework-cicd skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-app-framework-cicd/SKILL.md · Guidance for setting up CI/CD pipelines for DataRobot application templates using GitLab, GitHub Actions, and Pulumi…
git:20260519.3111310 · audit B · 27 stars
datarobot-data-preparation skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-data-preparation/SKILL.md · Tools and guidance for data upload, dataset management, data validation, and preparing data for DataRobot projects. Use…
git:20260825.cfbd8e9 · audit A · 27 stars
datarobot-discover skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-discover/SKILL.md · Use when the user wants to find DataRobot capabilities — skills, MCP servers, agents, or platform resources — for a…
git:20260623.fa30c37 · audit A · 27 stars
datarobot-external-agent-monitoring skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-external-agent-monitoring/SKILL.md · Instrument any external or existing AI agent with OpenTelemetry to send traces, logs, and metrics to DataRobot for…
git:20260713.606fd37 · audit C · 27 stars
datarobot-feature-engineering skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-feature-engineering/SKILL.md · Guidance for feature engineering, feature discovery, feature importance analysis, and understanding DataRobot's…
git:20260825.cfbd8e9 · audit A · 27 stars
datarobot-model-deployment skill
datarobot-oss/datarobot-agent-skills · skills/datarobot-model-deployment/SKILL.md · Tools and guidance for deploying DataRobot models, managing deployments, configuring prediction environments, and…
git:20260825.cfbd8e9 · audit A · 27 stars

Every file in datarobot-oss/datarobot-agent-skills

Browse by kind, by grade C, or by owner.