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

86%

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

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable skill with excellent progressive disclosure to six real reference files. Its main weaknesses are moderate verbosity in overview/when-to-use sections that restate known concepts, and workflows that omit explicit validation checkpoints for batch operations like ETL writes.

Suggestions

Tighten the Overview and 'When to Use This Skill' sections — they restate concepts Claude knows and duplicate the description; trim to the unique decision guidance.

Add explicit validation/verification checkpoints to batch workflows, e.g. verify row counts or schema after ETL transforms before writing to_parquet, and confirm graph size before large computes.

Move the detailed per-component 'When to Use' / 'Key Points' material into the corresponding reference files so the body stays a lean overview pointing to detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with strong concrete code and rules, but includes overview/definitional text Claude already knows ('Dask is a Python library for parallel and distributed computing...') and a 'When to Use This Skill' section that largely restates the description; the ~440-line body could be tightened given references hold the detail.	2 / 3
Actionability	Provides many copy-paste-ready, executable code examples across DataFrames, Arrays, Bags, Futures, and Schedulers, plus concrete numeric guidance ('~100 MB per chunk', '~1ms overhead per task') and explicit wrong-vs-correct patterns in Best Practices.	3 / 3
Workflow Clarity	Workflows (ETL, iterative dev) are sequenced, but lack explicit validation/verification checkpoints — the ETL pipeline writes to_parquet without verifying intermediate results, and batch operations have no validate-then-proceed gates, capping clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	SKILL.md is a well-structured overview that signals one-level-deep references for each component ('refer to references/X.md which includes:' with bullet previews), and a final 'Reference Files' section lists all six real reference files for easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

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: it states concrete capabilities, includes an explicit 'Use when' trigger, uses natural user vocabulary, and actively distinguishes Dask from vaex and polars to reduce mis-triggering. No significant weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and use cases — 'parallel file processing, distributed ML, integration with existing pandas code' and scaling 'beyond memory or across clusters' — rather than vague language.	3 / 3
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 an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Uses natural terms a user would say when needing this skill — 'pandas/NumPy', 'larger-than-RAM', 'scale', 'parallel', 'distributed', 'clusters', 'ML' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Explicitly carves out a distinct niche and differentiates from alternatives — 'For out-of-core analytics on single machine use vaex; for in-memory speed use polars' — making conflict with adjacent skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/dask/SKILL.md
Commit: 52845c3

Reviewed: about 10 hours 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.