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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/dask/SKILL.md

Quality

Content

68%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 skill body with executable examples for every component and a solid progressive-disclosure layout pointing to real reference files. Main weaknesses are minor verbosity/redundancy and the absence of explicit validation checkpoints in batch/write workflows.

Suggestions

Add explicit validation checkpoints to write/batch workflows — e.g. after ETL `to_parquet` or array `to_zarr`, verify row/chunk counts or re-read output before declaring success, so workflow_clarity can exceed the batch-operation cap of 3.

Remove the closing 'Reference Files' section (or trim it to a one-line pointer) since each component already cites its own `references/*.md` inline, reducing token redundancy.

Tighten the Overview and 'When to Use This Skill' sections to avoid restating the description's triggers and Dask's general capabilities that Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and decision guides, but includes some tightening opportunities — the Overview restates capabilities, 'When to Use This Skill' repeats the description's triggers, and the closing 'Reference Files' section re-lists the same six references already cited inline per component.	3 / 5
Actionability	Fully executable, copy-paste-ready code with imports across all five components plus install commands and concrete workflow patterns (ETL, array normalization, scatter/submit) covering the common cases.	5 / 5
Workflow Clarity	Sequences exist (e.g. the three-step iterative development workflow, ETL/extract-transform-load patterns) but write/batch workflows lack explicit validation checkpoints, and the rubric caps batch/destructive operations without validation at 3.	3 / 5
Progressive Disclosure	Well-signaled, verified one-level-deep references (all six `references/*.md` files exist and are cited inline per component) with a clear overview structure; not a 5 because the closing reference listing duplicates inline citations and some inline best-practice detail overlaps the dedicated `best-practices.md`.	4 / 5
	Total	15 / 20 Passed

Description

87%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 that clearly states what the skill does and when to use it, with concrete trigger phrases and explicit boundary guidance against competing tools. Minor room to sharpen a couple of broad action terms and add a few synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'scale existing pandas/NumPy code beyond memory or across clusters', 'parallel file processing', 'distributed ML', 'integration with existing pandas code' — with only minor gaps; not a 5 because 'distributed ML' is somewhat broad rather than a crisp concrete action.	4 / 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'), with concrete trigger phrases and additional 'Best for...' guidance.	5 / 5
Trigger Term Quality	Strong natural terms practitioners would say — 'pandas/NumPy workflows', 'larger-than-RAM', 'parallel file processing', 'across clusters' — plus distinguishing tool names (vaex, polars); not a 5 because a few common synonyms (e.g. 'big data', 'out-of-core') are only partially covered.	4 / 5
Distinctiveness Conflict Risk	Clear niche (distributed scaling of pandas/NumPy) with explicit boundary guidance against adjacent tools ('For out-of-core analytics on single machine use vaex; for in-memory speed use polars'), minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: K-Dense-AI/scientific-agent-skills
Path: skills/dask/SKILL.md
Commit: b2a92ba

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.