CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-jupyter-kw

Use when testing the golden_jupyter_kw 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_kw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%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 functions as an auto-generated notebook catalog: it has solid progressive disclosure with real, well-labeled reference files, but the body itself is padded with redundant statistics and non-executable code snippets rather than actionable, sequenced guidance. It describes a notebook's contents rather than instructing Claude how to test the golden build.

Suggestions

Deduplicate the repeated statistics (Total Sections, cell counts) into a single Statistics section and remove the truncated long_example code dump to tighten token usage.

Replace the passive catalog with an actionable testing workflow: ordered steps to reproduce the notebook (install deps -> load data -> run modeling -> verify the accuracy/recall metrics against the recorded values).

Remove or replace broken/non-instructive cells (e.g. '%timeit broken()', the truncated x0..x3 block) with copy-paste-ready commands that actually exercise the golden build.

DimensionReasoningScore

Conciseness

The body restates the same statistics multiple times (Total Sections: 5 appears in three sections) and inlines a truncated, pointless code dump (x0..x3 then '...'), making it noticeably verbose with several padded sections rather than mostly efficient.

2 / 5

Actionability

It offers a few generic snippets ('pip install pandas', 'pd.read_csv') but no guided, executable task; the long example is truncated and one cell is literally 'broken()', leaving only high-level hints without the specific steps to execute.

2 / 5

Workflow Clarity

There is no sequenced workflow — the 'When to Use' list is a loose use-case catalog, not a process with checkpoints, and the actual action ('testing the golden build') has no defined steps, fitting the score-2 anchor of poorly defined steps with many gaps.

2 / 5

Progressive Disclosure

The overview points to real one-level-deep reference files (verified to exist) listed in a dedicated Navigation section with descriptions and an index.md, giving good structure with content appropriately split, matching the score-4 anchor with only minor organization gaps.

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 terse and has a clear trigger ('Use when testing') plus a distinct project-specific subject, but it fails to state any concrete capability and relies on project jargon rather than natural user vocabulary. It reads as an auto-generated label rather than a capability statement.

Suggestions

Add concrete capabilities after the trigger, e.g. 'Use when testing the golden_jupyter_kw golden build: reproduce the notebook's modeling results, verify setup steps, and re-run data-loading and analysis cells.'

Replace or augment 'golden build' jargon with natural terms a user would say (e.g. 'notebook analysis', 'reproducing notebook results', 'Jupyter notebook testing').

State the 'what' explicitly — name the actions (reproduce analysis, verify setup, inspect modeling outputs) rather than only the 'when'.

DimensionReasoningScore

Specificity

The description names the domain ('golden_jupyter_kw golden build') but the only action stated is the generic 'testing', with no concrete capabilities enumerated, matching the score-2 anchor of naming a domain with minimal/generic actions.

2 / 5

Completeness

A clear 'when' is present ('Use when testing the golden_jupyter_kw golden build') but the 'what' is essentially absent — 'testing a golden build' conveys no concrete capability, fitting the score-2 anchor where 'when' is present without a real 'what'.

2 / 5

Trigger Term Quality

'Use when testing' is a natural trigger phrase, but 'golden build' and 'golden_jupyter_kw' are project-specific jargon rather than terms a user would naturally say, leaving only one generic keyword ('testing').

2 / 5

Distinctiveness Conflict Risk

The highly specific project artifact name 'golden_jupyter_kw golden build' carves out a clear niche with minimal conflict risk against other skills, aligning with the score-4 anchor of being mostly distinct with only minor overlap risk.

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_kw/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