Name: datarobot
Rating: 60 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

datarobot

Datarobot integration. Manage Projects, Users. Use when the user wants to interact with Datarobot data.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/datarobot/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and a well-structured connection workflow, but it carries some unnecessary explanatory prose and inlines a large reference table that could be split out for better progressive disclosure.

Suggestions

Trim the opening DataRobot overview paragraph and auth-plumbing prose to assume Claude's competence and improve token efficiency.

Add a verification/check step before destructive actions (e.g. confirm the project ID via get-project before running delete-project).

Move the full Popular actions table into a references file (e.g. ACTIONS.md) and keep only the most common actions inline, with a clear pointer.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient commands and tables, but the opening paragraph explaining what DataRobot is and prose like 'so you can focus on the integration logic rather than auth plumbing' are trimmable, placing it at mostly-efficient anchor-3 rather than the lean anchor-4.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, action search/run, and proxying, plus a full actions table and flag reference, fully covering common cases as in the anchor-5 example.	5 / 5
Workflow Clarity	The connection workflow has an explicit state-check sequence with validation and feedback loops (poll until READY, handle CLIENT_ACTION_REQUIRED, re-poll), but destructive actions (delete-project/deployment/dataset) lack pre-execution verification, a minor validation gap that holds it below anchor-5.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers and the single-file content is appropriately placed, but the 20-row actions table is inlined and there are no one-level-deep reference files, so it is good-structure anchor-4 rather than the clearly-split anchor-5.	4 / 5
	Total	16 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description includes an explicit 'Use when' trigger and a clear branded niche, but its capability statement is generic ('Manage Projects, Users') and lacks the specific natural-language terms and action coverage that would distinguish it more sharply.

Suggestions

Replace the generic verb 'Manage' with concrete actions, e.g. 'List, get, create, and delete Projects, Deployments, Datasets, and Models'.

Broaden trigger terms to include natural phrases users say, such as 'DataRobot projects, deployments, predictive models, batch predictions, or use cases'.

Tighten the 'when' clause to specific intents rather than the broad 'interact with Datarobot data'.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete entities ("Manage Projects, Users"), but the verb "Manage" is generic and coverage is not comprehensive versus the body's full action set, so it sits at the anchor-3 level rather than 4.	3 / 5
Completeness	It states both what ("Manage Projects, Users") and when ("Use when the user wants to interact with Datarobot data"), but the 'when' clause is broad and the 'what' is generic, so it is above anchor-3 yet short of the fully concrete anchor-5.	4 / 5
Trigger Term Quality	The natural keyword "Datarobot" and the trigger phrase "interact with Datarobot data" are present, but common variations/synonyms are missing, matching the anchor-3 example of some relevant keywords without fuller coverage.	3 / 5
Distinctiveness Conflict Risk	The trigger is tied to a single branded product ("Datarobot"), giving it a clear niche with minimal overlap risk against other skills, matching the anchor-5 example.	5 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/datarobot/SKILL.md
Commit: f484c82

Reviewed: ~16 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.