CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dask

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/dask/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, highly actionable overview with exemplary reference-file signaling and real bundle files matching every cited path. Main weaknesses are redundancy within the body (duplicated when-to-use and key-points material) and placeholder variables in a minority of code examples.

Suggestions

Remove the redundancy between 'When to Use This Skill', the per-component 'When to Use' lists, and the 'Selecting the Right Component' decision guide — keep one canonical decision path to tighten conciseness.

Replace undefined placeholders ('python_function', 'problematic_computation', 'large_dataset', 'parameters') in the scheduler, debugging, and custom-workflow examples with concrete runnable definitions.

Move the 'Common Workflow Patterns' and 'Debugging and Development' sections into references/best-practices.md (or a new patterns reference), leaving one-line pointers in SKILL.md to shorten the 450-line body.

DimensionReasoningScore

Conciseness

The body is dense with operational specifics rather than concept explanations, but contains clear redundancy: 'When to Use This Skill' repeats the frontmatter description, each component's 'When to Use' list is duplicated by the later 'Selecting the Right Component' decision guide, and 'Key Points' restate material already in the reference files. Not 2 because nearly everything written is Dask-operational rather than filler Claude already knows.

3 / 5

Actionability

Nearly all code blocks are copy-paste ready (read_csv with glob, groupby-mean-compute, client.map/gather, scatter pattern), covering the common cases per component. Not 5 because several examples reference undefined placeholders such as 'python_function', 'problematic_computation', 'large_dataset', and 'parameters'.

4 / 5

Workflow Clarity

The 'Iterative Development Workflow' gives a clear sequenced progression (test on small data with synchronous scheduler, validate on a 1000-row sample, scale with distributed and dashboard monitoring) with explicit checkpoints. Not 5 because the ETL and custom-parallel patterns lack explicit validation/verification steps despite being batch operations.

4 / 5

Progressive Disclosure

Excellent reference structure: every component section signals its 'references/<file>.md' with a bullet list of what it contains, all six referenced files exist, they are one level deep, and a final 'Reference Files' index aids navigation. Not 5 because the ~450-line body inlines substantial material ('Common Workflow Patterns', 'Debugging and Development', full 'Best Practices' rules) that mirrors or belongs in the reference files.

4 / 5

Total

15

/

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 with an explicit what+when structure, good natural trigger synonyms, and unusually good distinctiveness via explicit routing to vaex/polars. The only deduction is the second-person 'you need to' phrasing, which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

The description lists several concrete capabilities ('scale existing pandas/NumPy code beyond memory or across clusters', 'parallel file processing, distributed ML'), which would rate 4, but the explicit second-person phrasing 'Use when you need to...' incurs the rubric's 1-point specificity penalty. It is not a 2 because the domain is named with multiple specific use cases rather than generic actions.

3 / 5

Completeness

Explicitly answers both what ('Distributed computing for larger-than-RAM pandas/NumPy workflows') and when ('Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML...') with concrete trigger phrases. Clearly matches the top anchor rather than the 4 anchor's 'when could be more explicit'.

5 / 5

Trigger Term Quality

Good natural keyword coverage with synonyms for the core trigger ('larger-than-RAM', 'out-of-core', 'beyond memory') plus 'pandas/NumPy', 'clusters', 'distributed ML'. Not 5 because common user phrasings like 'data doesn't fit in memory' or 'too much data' are absent, though the synonym cluster comes close.

4 / 5

Distinctiveness Conflict Risk

Clear niche (larger-than-RAM pandas/NumPy scaling) with active disambiguation against neighboring skills ('For out-of-core analytics on single machine use vaex; for in-memory speed use polars'), which exceeds the top anchor's example of minimal conflict risk.

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/dask/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.