deepnote-notebooks

Use when reading, reviewing, inspecting, or reasoning about hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook outputs through the Deepnote app tools.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

85%Weight 40%Scale 1-3

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

A well-organized, highly actionable inspection skill that names exact tools and parameters and sequences the workflow with validation checkpoints. The main weakness is mild verbosity: an elaborate output template and a duplicated inputs description could be tightened.

Suggestions

Consolidate the inputs guidance: describe input fields once (either in the workflow or in the output template) rather than repeating name/type/value/label in both places.

Trim the Notebook Inspection Output template by making the status table and block map clearly optional fallbacks, since the leading brief plus cautions already carry most of the signal.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the six-part Notebook Inspection Output template with three tables is elaborate, and inputs are described twice (workflow step 4 and the inputs output table), so it could be tightened rather than earning the fully lean anchor.	2 / 3
Actionability	It names concrete tools (get_notebook, list_integrations, get_integration, list_notebook_runs, get_run) and concrete parameters (create_run.inputs, snapshotDelivery: "inline") plus the exact input fields to report (name, type, value, label), giving fully executable, specific guidance even though it is instruction-only.	3 / 3
Workflow Clarity	The eight-step inspection workflow is a clear sequenced checklist with explicit validation checkpoints ("verify notebook structure before making claims", confirm integration usage "instead of inferring solely from names", say plainly if a run did not execute), and it routes destructive/editing operations to a separate skill.	3 / 3
Progressive Disclosure	The single file is organized into four clearly headed sections with no nested reference chains, no bundle files are needed for this read-only skill, and the only cross-reference is appropriate routing to the deepnote-notebook-editing skill.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

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

A strong, third-person description with an explicit "Use when" trigger, concrete actions, and a clear Deepnote niche. Its only real gap is trigger-term coverage: a few common user-facing terms (runs, cells, schedule) are missing and "reasoning about" is not a natural user phrase.

Suggestions

Add common user-facing trigger terms such as "runs/run history", "cells", and "schedule/scheduled" so the description matches how users actually ask about Deepnote notebooks.

Replace the unnatural phrase "reasoning about" with a more user-natural verb such as "explaining" or "answering questions about".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("reading, reviewing, inspecting, or reasoning about") paired with concrete objects ("hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook outputs"), matching the anchor for several specific concrete actions rather than vague language.	3 / 3
Completeness	It explicitly answers both what (the reading/reviewing/inspecting actions over notebook artifacts) and when via the explicit "Use when reading, reviewing, inspecting..." trigger clause, matching the anchor that clearly answers both with explicit triggers.	3 / 3
Trigger Term Quality	It includes relevant natural terms (notebooks, blocks, inputs, SQL, outputs, reading/reviewing/inspecting), but "reasoning about" is not phrasing a user would naturally say and common variations users actually use—runs/run history, cells, schedule/scheduled—are absent, so it stops at "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The scoped phrase "hosted Deepnote notebooks... through the Deepnote app tools" carves a clear niche tied to a specific platform and toolset, making it unlikely to fire for unrelated notebook or code skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/deepnote/skills/deepnote-notebooks/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.