CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-jupyter-dir

Use when testing the golden_jupyter_dir golden build

Quality

54%

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_dir/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

40%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 is an auto-generated notebook index: it correctly offloads detail to real reference files but pads the overview with redundant statistics and a truncated, low-quality code example. There is no actionable workflow, only a catalog of sections and a few hit-or-miss code snippets.

Suggestions

Remove the redundant 'Notebook Statistics' and duplicate 'Total Sections' counts; keep one concise overview of structure to improve conciseness.

Drop or complete the truncated x0-x37 long_example and the broken '%timeit broken()' snippet; keep only executable, illustrative code.

Add a short, sequenced workflow for reproducing the notebook (load -> model -> evaluate) so the skill is actionable rather than purely an index.

DimensionReasoningScore

Conciseness

The body is noticeably verbose with auto-generated padding: redundant 'Total Sections' counts appear twice, a 'Notebook Statistics' section restates counts already given, and a truncated x0-x37 variable example occupies many lines for no instructional value, matching the 2-anchor's 'several unnecessary explanations or padded sections'.

2 / 5

Actionability

There are some concrete executable snippets ('pip install pandas', the pandas read_csv block), but the long_example is truncated mid-statement and '%timeit broken()' is non-functional, so guidance is incomplete like the 3-anchor's 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

This is a reference index rather than a process; there is no sequenced multi-step workflow and no validation checkpoints, fitting the 2-anchor's 'rough sequence present but many gaps' — here the sequence is essentially absent beyond a list of use cases.

2 / 5

Progressive Disclosure

The Navigation section clearly signals one-level-deep reference files (references/section_s*.md and references/index.md), all of which exist, and the body acts as an overview pointing into them, matching the 4-anchor's 'good structure; references mostly clear'; it does not reach 5 because substantial content (stats, code examples) is inlined that could live in references.

4 / 5

Total

11

/

20

Passed

Description

45%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 a circular, auto-generated one-liner that technically satisfies the 'what' and 'when' structure but offers no concrete capabilities and relies on project-internal jargon rather than natural user triggers. It is distinctive only because the project name is unique, not because the description articulates a clear purpose.

Suggestions

Replace the circular 'Use when testing the golden_jupyter_dir golden build' with a concrete 'what' (e.g., 'Reproduces the golden_jupyter_dir analysis notebook: data loading, modeling, and evaluation') and a distinct 'when' clause naming natural user triggers.

Add concrete actions the skill performs (e.g., load data, run modeling, evaluate results) instead of the generic verb 'testing'.

Use natural terms a user would say (e.g., 'golden_jupyter_dir notebook', 'reproduce analysis', 'data modeling results') rather than internal jargon like 'golden build'.

DimensionReasoningScore

Specificity

The description names the domain ('golden_jupyter_dir') but the only action ('testing') is generic and minimal, matching the 'names the domain but actions are minimal or generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

An explicit 'Use when...' clause is present (so it is not capped at 3 by the missing-trigger rule), but the 'when' merely restates the 'what' ('testing the golden_jupyter_dir golden build') without adding concrete trigger phrases, fitting the 3-anchor of a clear what with a weak/implied when rather than the 4-anchor's distinct when.

3 / 5

Trigger Term Quality

'golden_jupyter_dir golden build' is project-specific jargon that a user would not naturally utter; it offers one or two keywords but misses the natural phrases users say, so it does not reach the 3-anchor's 'some relevant keywords'.

2 / 5

Distinctiveness Conflict Risk

The 'golden_jupyter_dir' identifier carves out a clear niche with distinct triggers and minimal conflict risk against other skills, matching the 5-anchor; it is clearly more distinct than the 4-anchor's 'minor overlap risk'.

5 / 5

Total

12

/

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_dir/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