CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

working-with-notebooks

Fixing and validating Jupyter notebooks in pymc-marketing. Use when notebooks fail CI, need arviz_plots 2.x migration fixes, or when source code changes require notebook output updates.

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

Excellent operational content — lean, fully executable, and with explicit validation loops and a pre-push checklist. The single weakness is organization across files: the body is a monolith carrying a large pattern catalog, and one referenced file is neither bundled nor clearly pathed.

Suggestions

Move the section 4 failure-pattern catalog (B10–B25) into a reference file such as references/notebook-failure-patterns.md, keeping one or two of the most common patterns inline in SKILL.md with a clearly signaled link.

Give the "notebook-release-changes.md" reference a proper relative path and add it to the bundle (e.g., references/notebook-release-changes.md), since it is currently a dangling pointer.

Consider also splitting the section 7 release workflow into the same reference file, leaving SKILL.md as a compact overview of mock-run → fix → validate → push with clearly signaled one-level-deep references.

DimensionReasoningScore

Conciseness

The body is almost entirely commands and broken→fixed code pairs with no padding or explanations of concepts Claude already knows; even the brief prose (why to isolate figure code in sandbox/) earns its place by justifying a non-obvious workflow.

5 / 5

Actionability

Every command is copy-paste executable (mock runner, jupyter execute --inplace, gh run view, ruff, pre-commit, checkpoint cleanup) and each failure pattern B10–B25 is given as concrete before/after code covering the common cases.

5 / 5

Workflow Clarity

Section 3 defines a numbered iteration loop with an explicit repeat-until-pass feedback loop, a CRITICAL "Never push until all targeted notebooks pass locally" gate, a pre-push checklist, and a JSON error-output validation script in section 7 — validation checkpoints and error recovery are all explicit.

5 / 5

Progressive Disclosure

Scored against the actual bundle (a single 320-line SKILL.md with no references/ directory): the ~130-line failure-pattern catalog in section 4 is inline content that belongs in a separate reference file, and "notebook-release-changes.md" is cited without a path and is absent from the bundle, leaving one dangling pointer alongside the clear scripts/run_notebooks/README.md reference.

3 / 5

Total

18

/

20

Passed

Description

82%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: third-person gerund style, an explicit "Use when" clause with concrete repo-specific triggers, and a tightly scoped niche. The only weakness is that the 'what' half names just two actions rather than the full capability set.

DimensionReasoningScore

Specificity

"Fixing and validating Jupyter notebooks in pymc-marketing" names the domain with two concrete actions, but does not enumerate the broader capability set (re-execution, migration patterns, pre-push validation), matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

It clearly states what the skill does ("Fixing and validating Jupyter notebooks in pymc-marketing") and explicitly answers when with an explicit "Use when" clause listing three concrete trigger scenarios, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like "notebooks fail CI", "arviz_plots 2.x migration fixes", "notebook output updates", and "Jupyter notebooks" give good trigger coverage, but common variations such as ".ipynb" or "re-run notebooks" are missing, so it falls just short of the comprehensive synonym coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to pymc-marketing notebooks and arviz_plots 2.x migration — a clear niche with distinct triggers and minimal overlap with any other skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 7 missing, 7 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

pymc-labs/pymc-marketing

Path

.claude/skills/working-with-notebooks/SKILL.md

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.