datarobot-agent-assist

Name: datarobot-agent-assist
Author: datarobot-oss

22stars19forks

How to install datarobot-agent-assist?

datarobot-oss/datarobot-agent-skills/datarobot-agent-assist

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-agent-assist

Installs into the current project.

Summary

Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive model) to DataRobot; mentions agent_spec.md, dr-assist, datarobot-agent-assist, dress rehearsal, or the DataRobot agent template; wants to scaffold a LangGraph, CrewAI, LlamaIndex, N

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Agent Assist
2
3	This skill merges agent design, coding, and deployment with an optional dress-rehearsal simulation — a try-before-you-build session that lets you chat with your agent design before writing any code.
4
5	Assistance falls into three categories:
6
7	1. Designing an AI agent → Clarify requirements, build `agent_spec.md`, optionally simulate the agent before coding
8	2. Coding an AI agent → Adapt the DataRobot agent application template to the spec
9	3. Deploying an AI agent → Follow `AGENTS.md` deployment instructions
10
11	If the user's first message is simply `1`, `2`, or `3`, treat it as selecting one of these categories.
12
13	---
14
15	## On Activation
16
17	Present the three options clearly:
18
19	```
20	Welcome! I help you design, code, and deploy AI agents.
21
22	What would you like to do?
23	1. Design an AI agent → Describe your idea (optional dress rehearsal before coding)
24	2. Code an AI agent → Load and implement an existing agent_spec.md
25	3. Deploy an AI agent → Deploy an implemented agent to DataRobot
26	```
27
28	Show this menu first. After the user selects an option (`1`, `2`, or `3`), run the [Pre-requisite Check](#pre-requisite-check) and then the [Script Path Resolution](#script-path-resolution).
29
30	- Options 1 and 2 — read and follow [references/workspace-resolution.md](references/workspace-resolution.md), then proceed to the selected workflow.
31	- Option 3 — skip Workspace Resolution; `<target_dir>` is resolved in the [Pre-deployment Checklist](references/pre-deployment-checklist.md) when unset.
32
33	---
34
35	## Script Path Resolution
36
37	Before invoking any helper script, resolve `<skill_scripts_dir>` once for the session:
38
39	- `<skill_scripts_dir>` is the `scripts/` subdirectory of the directory containing this `SKILL.md` file.
40	- Confirm it exists with `ls <path_to_this_skill_dir>/scripts/`. If the directory is missing, tell the user the skill installation is incomplete and stop.
41	- Use the resolved absolute path for every `<skill_scripts_dir>/...` reference in this skill.
42
43	---
44
45	## Session State
46
47	Track these for the conversation:
48
49	- `<target_dir>` — project root for design, coding, and deployment. Set during [Workspace Resolution](references/workspace-resolution.md) or the [Pre-deployment Checklist](references/pre-deployment-checklist.md). Reuse across phases in the same session. Only change when the user explicitly asks, during [pre-coding subdir recovery](references/pre-coding-checklist.md), or in a new session.
50	- `<dependency_check_passed>` — `false` until a passing `dr dependency check` in `<target_dir>`.
51	- `<dependency_check_target_dir>` — the `<target_dir>` value when the last check passed.
52
53	### Dependency check session rule
54
55	Before running `dr dependency check`:
56
57	- If `<dependency_check_passed>` is true and `<target_dir>` equals `<dependency_check_target_dir>`, skip the check.
58	- Otherwise, run `dr dependency check` in `<target_dir>`. On zero exit: set `<dependency_check_passed>` = true and `<dependency_check_target_dir>` = `<target_dir>`. On non-zero exit: hard stop — return full output; do not attempt to resolve automatically.
59
60	Invalidate `<dependency_check_passed>` (set to false) when:
61
62	- `<target_dir>` changes
63	- `clone_template.py`, `select_framework.py`, or `setup_template.py` runs in `<target_dir>`
64
65	---
66
67	## Workspace Resolution
68
69	Read and follow [references/workspace-resolution.md](references/workspace-resolution.md) after menu options 1 or 2.
70
71	---
72
73	## Pre-requisite Check
74
75	Run in order before proceeding:
76
77	1. Git — run `git --version`. If missing, tell the user to install from https://git-scm.com and stop.
78	2. Python — run `python --version`. If missing or below 3.11, tell the user to install Python 3.11+ from https://python.org and stop.
79	3. DataRobot CLI — follow DataRobot CLI Setup at the bottom:
80	- If missing, ALWAYS RUN the install command before proceeding
81	- ALWAYS RUN the upgrade command before proceeding
82	- If not authenticated, ALWAYS RUN the auth command before proceeding
83	4. Codespace — run `python <skill_scripts_dir>/check_codespace.py` (no-op outside a Codespace). On non-zero exit, relay its message and stop; otherwise relay any exposed-ports warning it prints.
84
85	---
86
87	## 1. Designing an AI Agent
88
89	### Cla

People who liked this also viewed

6 picks

Type

datarobot-agent-assist

22stars19forks

View on GitHub

How to install datarobot-agent-assist?

datarobot-oss/datarobot-agent-skills/datarobot-agent-assist

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-agent-assist

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Agent Assist
2
3	This skill merges agent design, coding, and deployment with an optional dress-rehearsal simulation — a try-before-you-build session that lets you chat with your agent design before writing any code.
4
5	Assistance falls into three categories:
6
7	1. Designing an AI agent → Clarify requirements, build `agent_spec.md`, optionally simulate the agent before coding
8	2. Coding an AI agent → Adapt the DataRobot agent application template to the spec
9	3. Deploying an AI agent → Follow `AGENTS.md` deployment instructions
10
11	If the user's first message is simply `1`, `2`, or `3`, treat it as selecting one of these categories.
12
13	---
14
15	## On Activation
16
17	Present the three options clearly:
18
19	```
20	Welcome! I help you design, code, and deploy AI agents.
21
22	What would you like to do?
23	1. Design an AI agent → Describe your idea (optional dress rehearsal before coding)
24	2. Code an AI agent → Load and implement an existing agent_spec.md
25	3. Deploy an AI agent → Deploy an implemented agent to DataRobot
26	```
27
28	Show this menu first. After the user selects an option (`1`, `2`, or `3`), run the [Pre-requisite Check](#pre-requisite-check) and then the [Script Path Resolution](#script-path-resolution).
29
30	- Options 1 and 2 — read and follow [references/workspace-resolution.md](references/workspace-resolution.md), then proceed to the selected workflow.
31	- Option 3 — skip Workspace Resolution; `<target_dir>` is resolved in the [Pre-deployment Checklist](references/pre-deployment-checklist.md) when unset.
32
33	---
34
35	## Script Path Resolution
36
37	Before invoking any helper script, resolve `<skill_scripts_dir>` once for the session:
38
39	- `<skill_scripts_dir>` is the `scripts/` subdirectory of the directory containing this `SKILL.md` file.
40	- Confirm it exists with `ls <path_to_this_skill_dir>/scripts/`. If the directory is missing, tell the user the skill installation is incomplete and stop.
41	- Use the resolved absolute path for every `<skill_scripts_dir>/...` reference in this skill.
42
43	---
44
45	## Session State
46
47	Track these for the conversation:
48
49	- `<target_dir>` — project root for design, coding, and deployment. Set during [Workspace Resolution](references/workspace-resolution.md) or the [Pre-deployment Checklist](references/pre-deployment-checklist.md). Reuse across phases in the same session. Only change when the user explicitly asks, during [pre-coding subdir recovery](references/pre-coding-checklist.md), or in a new session.
50	- `<dependency_check_passed>` — `false` until a passing `dr dependency check` in `<target_dir>`.
51	- `<dependency_check_target_dir>` — the `<target_dir>` value when the last check passed.
52
53	### Dependency check session rule
54
55	Before running `dr dependency check`:
56
57	- If `<dependency_check_passed>` is true and `<target_dir>` equals `<dependency_check_target_dir>`, skip the check.
58	- Otherwise, run `dr dependency check` in `<target_dir>`. On zero exit: set `<dependency_check_passed>` = true and `<dependency_check_target_dir>` = `<target_dir>`. On non-zero exit: hard stop — return full output; do not attempt to resolve automatically.
59
60	Invalidate `<dependency_check_passed>` (set to false) when:
61
62	- `<target_dir>` changes
63	- `clone_template.py`, `select_framework.py`, or `setup_template.py` runs in `<target_dir>`
64
65	---
66
67	## Workspace Resolution
68
69	Read and follow [references/workspace-resolution.md](references/workspace-resolution.md) after menu options 1 or 2.
70
71	---
72
73	## Pre-requisite Check
74
75	Run in order before proceeding:
76
77	1. Git — run `git --version`. If missing, tell the user to install from https://git-scm.com and stop.
78	2. Python — run `python --version`. If missing or below 3.11, tell the user to install Python 3.11+ from https://python.org and stop.
79	3. DataRobot CLI — follow DataRobot CLI Setup at the bottom:
80	- If missing, ALWAYS RUN the install command before proceeding
81	- ALWAYS RUN the upgrade command before proceeding
82	- If not authenticated, ALWAYS RUN the auth command before proceeding
83	4. Codespace — run `python <skill_scripts_dir>/check_codespace.py` (no-op outside a Codespace). On non-zero exit, relay its message and stop; otherwise relay any exposed-ports warning it prints.
84
85	---
86
87	## 1. Designing an AI Agent
88
89	### Cla

People who liked this also viewed

6 picks

Type