CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-jupyter

Use when testing the golden_jupyter golden build

Quality

46%

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 ./tests/golden/phase2/jupyter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 content is an auto-generated notebook index: it organizes material with real, clearly-signaled references, but it pads the context with a redundant truncated code dump and statistics, ships a broken code example, and provides no actual workflow or actionable guidance. It reads as a structural overview rather than a skill that tells Claude what to do.

Suggestions

Remove the truncated x0–x37 long_example code dump (or move it entirely into references/analysis.md) and drop the redundant Notebook Statistics block that duplicates the Section Overview.

Replace or annotate the broken '%timeit broken()' example so the body only shows executable, illustrative cells, and add a one-line note on what each example demonstrates.

Add a short workflow section describing how to use the notebook material (e.g., review sections in order, reproduce code cells, check outputs) so the skill provides an actionable sequence rather than only an index.

DimensionReasoningScore

Conciseness

The body is noticeably padded: a truncated x0–x37 variable-assignment code dump earns no value, and the Notebook Statistics section duplicates overview information already stated above, fitting the verbose-with-padded-sections anchor rather than mostly-efficient.

2 / 5

Actionability

Some executable code is present ('pip install pandas', the pandas read_csv cell), but one example is intentionally broken ('%timeit broken()') and the body offers no instructional guidance on what to do with these cells, matching the some-concrete-but-incomplete anchor.

3 / 5

Workflow Clarity

There is no multi-step workflow or sequence whatsoever — the body is pure structural metadata with no ordered process or validation, matching the steps-missing/incoherent anchor.

1 / 5

Progressive Disclosure

Real one-level-deep reference files (analysis.md, index.md) are present and clearly signaled in the Navigation section, but a large code dump is inlined rather than kept in the reference, placing it at good-structure-with-minor-gaps rather than the clean fully-split anchor at 5.

4 / 5

Total

10

/

20

Passed

Description

32%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.

The description is barely functional: it has a trigger clause and a distinctive niche name, but it specifies no concrete capabilities and relies on jargon rather than natural user language. It would benefit from naming the actual actions performed and the terms a user would say.

Suggestions

Replace the generic 'testing' with the concrete actions the skill performs (e.g., 'reproduce analysis steps, reference code examples and outputs, review modeling results').

Add natural trigger terms a user would actually say, such as 'golden_jupyter notebook', 'reproduce notebook analysis', or 'review jupyter results', instead of only the internal 'golden build' phrase.

Separate the 'what' from the 'when' so the description states capabilities first and trigger conditions second, rather than collapsing both into one vague clause.

DimensionReasoningScore

Specificity

The description names the domain ('golden_jupyter') but the only stated action ('testing') is minimal and generic, matching the anchor for naming a domain with minimal actions rather than the 1-2 concrete actions needed for a 3.

2 / 5

Completeness

A 'Use when' trigger clause is present, but the 'what' is vague and essentially repeats the 'when', fitting the anchor where only a weak 'when' is present without a real 'what' rather than the 3 which requires a clear 'what'.

2 / 5

Trigger Term Quality

'golden_jupyter golden build' is niche internal jargon rather than natural user phrasing, and 'testing' is a single generic keyword, so it lands at the one-or-two-generic-keywords anchor rather than offering the natural phrases users would actually say.

2 / 5

Distinctiveness Conflict Risk

'golden_jupyter' is a distinct niche term unlikely to fire for unrelated skills, placing it mostly-distinct with only minor overlap risk rather than the fully distinct, comprehensively-triggered anchor at 5.

4 / 5

Total

10

/

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

yusufkaraaslan/Skill_Seekers

Path

tests/golden/phase2/jupyter/SKILL.md

Revision

5b5d8df

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill