deepnote-data-execution

Use when running Deepnote notebooks, inspecting notebook inputs, reviewing integration references and cached table structure, listing run history, or interpreting run status and snapshot outputs through the Deepnote app tools.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

The body is highly actionable and well-sequenced with strong validation checkpoints, but it is verbose — key behaviors (notably snapshotDelivery defaults) are restated across sections — and monolithic with no external reference split, limiting conciseness and progressive disclosure.

Suggestions

Consolidate the snapshotDelivery default behavior into one section and have other sections reference it, removing the verbatim repetition across 'Available Context', 'Execution Workflow', and 'Run Snapshots'.

Move the detailed tool catalog and input-value type map into a references/ file (e.g. TOOL_REFERENCE.md) linked from a concise overview, so SKILL.md stays a lean entry point and improves progressive disclosure.

Tighten the run-report guidance so the summary table shape is defined once and the debugging table inherits from it, rather than presenting two near-parallel templates.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it repeats material — e.g., the snapshotDelivery default behavior is restated in 'Available Context', 'Execution Workflow', and again verbatim in 'Run Snapshots', and get_run's role recurs across sections — so it could be tightened rather than earning the lean, every-token-counts level 3.	2 / 3
Actionability	It gives concrete, copy-paste-ready guidance: exact tool names, parameters like 'pageSize: 100' and 'snapshotDelivery: "inline"', a precise input-value type map (checkbox->booleans, multi-select->arrays, slider->numeric strings), and ready-made report tables, which is fully actionable even without code.	3 / 3
Workflow Clarity	The 7-step Execution Workflow is clearly sequenced with explicit validation checkpoints — step 6 stops on a create_run tool error and forbids calling get_run without a run ID, and a pre-run warning requires confirmation for mutating or risky notebooks — matching the clear-sequence-with-feedback-loops anchor.	3 / 3
Progressive Disclosure	There are no bundle files and the skill is a single self-contained document with good section headers, but the full tool catalog and detailed input/snapshot semantics are all inline with no one-level-deep references or content split, so it does not reach the level-3 'appropriately split / clear references' anchor (and exceeds the simple under-50-line case).	2 / 3
	Total	10 / 12 Passed

Description

100%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 description: it opens with an explicit 'Use when' trigger, enumerates concrete Deepnote-centric actions, and stays tightly scoped to the platform, so it clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('running Deepnote notebooks, inspecting notebook inputs, reviewing integration references and cached table structure, listing run history, or interpreting run status and snapshot outputs'), matching the 'lists multiple specific concrete actions' anchor rather than the partial coverage of level 2.	3 / 3
Completeness	It explicitly answers 'when' via the 'Use when...' clause and 'what' via the enumerated actions, satisfying the 'clearly answers both what AND when with explicit triggers' anchor and avoiding the level-2 cap where 'when' is only implied.	3 / 3
Trigger Term Quality	Natural user phrasings like 'running Deepnote notebooks', 'run history', 'run status', and 'snapshot outputs' give good coverage of terms a user would actually say, rather than the jargon-only or partial-variation cases at lower levels.	3 / 3
Distinctiveness Conflict Risk	The Deepnote-specific scope ('through the Deepnote app tools') carves a clear niche with distinct triggers unlikely to collide with other skills, rather than the overlapping level-2 case.	3 / 3
	Total	12 / 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-data-execution/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.