jupyter-notebook

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

1.49x

Quality

92%

Does it follow best practices?

Impact

88%

1.49x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-structured, actionable skill body with executable commands, a sequenced workflow, validation, and clean progressive disclosure into real bundle files. The only weakness is mild redundancy where paths and references are stated more than once.

Suggestions

Remove the duplicate script path: keep it in either the 'Skill path' section or 'Templates and helper script', not both, to avoid drift.

Drop the terminal 'Reference map' section or the inline citations in the workflow — one navigation path is enough; keeping both is redundant.

If retaining the reference map, shorten it to a one-line index (file → purpose) since each reference is already introduced where it is used.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids over-explaining known concepts, but the script path is restated across 'Skill path' and 'Templates and helper script', and the reference files are cited inline in the workflow and again in the final 'Reference map'.	2 / 3
Actionability	Provides copy-paste-ready, fully executable commands ('uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" --kind experiment --title ... --out ...') with concrete worked examples for both notebook modes.	3 / 3
Workflow Clarity	A clearly sequenced 6-step workflow with a decision tree and an explicit validation checkpoint (step 6: run top-to-bottom, use quality-checklist.md), including handling for when execution is not possible.	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled, one-level-deep references to references/.md and assets/.ipynb (all verified to exist), plus a consolidated reference map for navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 that states concrete capabilities and an explicit 'Use when...' trigger with natural terms and a distinct niche. No verbosity or over-claims; voice and structure match the exemplar descriptions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, scaffold, or edit Jupyter notebooks' and 'generate a clean starting notebook' — rather than vague language.	3 / 3
Completeness	Answers both what (create/scaffold/edit notebooks, generate a starting notebook) and when via an explicit 'Use when the user asks...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'Jupyter notebooks', '.ipynb', 'experiments, explorations, or tutorials' — with good variation coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (Jupyter .ipynb notebooks for experiments/tutorials) with distinct triggers unlikely to fire for unrelated skills.	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/skills
Commit: 49f948f

Reviewed: 19 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.