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

82%

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%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 that leverages progressive disclosure effectively. Weaker on conciseness due to repeated trigger/example sections and on workflow clarity because batch/destructive operations lack validation checkpoints.

Suggestions

Consolidate the top-level 'When to Use This Skill' with the per-component 'When to Use' lists, and drop the final 'Reference Files' index since each reference is already linked inline in its section.

Add explicit validation/feedback loops around destructive or batch operations, e.g. verify a written Parquet/Zarr file by re-reading a sample after to_parquet/to_zarr, and treat `len(ddf.__dask_graph__())` as a pre-compute checkpoint.

De-duplicate the per-component quick examples that reappear verbatim in 'Common Workflow Patterns', keeping one canonical instance and cross-referencing it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the top-level 'When to Use' overlaps the per-component 'When to Use' lists, quick examples reappear in 'Common Workflow Patterns', and the closing reference index restates links already inline.	3 / 5
Actionability	Extensive copy-paste-ready, executable code across all five components and workflow patterns, naming specific APIs (dd.read_csv, map_partitions, client.scatter, scheduler='processes').	5 / 5
Workflow Clarity	A clear debugging sequence (synchronous -> threads -> distributed) plus troubleshooting exists, but batch/destructive writes (to_parquet, to_zarr) lack explicit validation checkpoints/feedback loops, capping this dimension at 3.	3 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled, one-level-deep references to six real reference files, each summarized inline, with bulk detail appropriately split out and a final navigation index.	5 / 5
	Total	16 / 20 Passed

Description

92%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, third-person description that concretely states capabilities and gives explicit use-when triggers plus boundary guidance against neighboring tools. Only minor room to broaden natural synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('scale existing pandas/NumPy code beyond memory or across clusters', 'parallel file processing, distributed ML, integration with existing pandas code') with comprehensive coverage.	5 / 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 triggers.	5 / 5
Trigger Term Quality	Strong natural terms ('pandas/NumPy workflows', 'parallel file processing', 'distributed ML', 'beyond memory', 'across clusters') but a few common synonyms/extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche with explicit boundary guidance steering to vaex and polars for adjacent cases, minimizing conflict risk.	5 / 5
	Total	19 / 20 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: 3a6c3a9

Reviewed: 1 day 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.