CtrlK
BlogDocsLog inGet started
Tessl Logo

jupyter-notebooks

Create, edit, or validate reproducible SQL or Python notebooks. Use for notebooks, SQL/Python scratchpads, reproducible exploration, audit trails, or runnable companions where the analysis should be reviewable or rerunnable.

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/opencode/src/skill/builtin/.bundle/data-analytics/workflows/jupyter-notebooks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 delivers a strong, well-sequenced workflow with explicit validation and a checklist, and its commands and section templates are mostly executable. Its main weaknesses are duplication between the Workflow and Standards sections and one nonstandard command invocation (python -m jupyter nbconvert).

Suggestions

Deduplicate the Workflow and Standards sections — source recording, bounded outputs, and refactoring-preservation each appear twice; consolidate them into one location and cross-reference it.

Correct the execution command to the documented form: "jupyter nbconvert --execute --to notebook --inplace path/to/notebook.ipynb".

Consider moving the mode-specific section templates (analysis vs. tutorial) into a short reference file or collapsing them, trimming the main body toward a leaner overview.

DimensionReasoningScore

Conciseness

The Workflow steps and Standards bullets repeat the same guidance — source recording appears in step 5 and again under "Reproducibility", bounded outputs in steps 6-7 and again under "Code And Data Hygiene" — and directives like "Use data sources deliberately" add little. It is mostly efficient but could be meaningfully tightened, so it sits at the midpoint anchor rather than the minor-trimmings anchor.

3 / 5

Actionability

Concrete, mostly executable guidance: a real nbconvert invocation, an install command, and two explicit section-order templates. It falls short of fully copy-paste-ready because "python -m jupyter nbconvert" is not the documented invocation ("jupyter nbconvert ...") and several steps (e.g., "Use data sources deliberately") remain at the directive level.

4 / 5

Workflow Clarity

An 8-step sequence with explicit validation checkpoints ("Validate results before writing conclusions", "Execute and record validation status"), a feedback loop for surprising results ("add a local reasonableness check... before promoting it to the summary"), and a closing Validation Checklist — matching the top anchor with validation steps, error-recovery loops, and a checklist all present.

5 / 5

Progressive Disclosure

A well-organized single-file skill with clear section headers and no bundle files to navigate. At ~127 lines, mode-specific template material could arguably live in a reference file, so structure is good with minor organization gaps rather than an exemplarily split overview.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description with an explicit 'Use for...' trigger clause, third-person voice, and concrete domain-scoped actions. Its main gaps are missing high-frequency synonyms ("Jupyter", ".ipynb") and slightly broad trailing triggers that overlap with general analysis skills.

Suggestions

Add the highest-frequency natural terms users actually say — "Jupyter", "Jupyter notebooks", and ".ipynb" — to the trigger clause.

Tighten the trailing triggers ("reproducible exploration, audit trails") so they clearly imply notebook files rather than any reviewable analysis, reducing overlap with general data-analysis skills.

DimensionReasoningScore

Specificity

"Create, edit, or validate reproducible SQL or Python notebooks" names the domain plus three concrete actions, matching the 'several specific actions; minor gaps' anchor. Not a 5 because coverage stops at those three verbs rather than a comprehensive capability list.

4 / 5

Completeness

It explicitly answers both parts: the "what" ("Create, edit, or validate reproducible SQL or Python notebooks") and an explicit "Use for..." clause with concrete trigger phrases including "where the analysis should be reviewable or rerunnable", matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural phrasings like "notebooks", "SQL/Python scratchpads", "reproducible exploration", and "audit trails" give good keyword coverage, but common terms a user would actually say — "Jupyter", ".ipynb", "cells" — are missing, so it falls short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

"SQL or Python notebooks" carves a fairly distinct niche, but "reproducible exploration" and "audit trails" could bleed into general data-analysis or documentation skills, so it is mostly distinct with minor overlap risk rather than a clear niche with minimal conflict.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
XiaomiMiMo/MiMo-Code
Reviewed

Table of Contents

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.