CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

61%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 well-structured with strong executable examples and clean progressive disclosure to real reference files. Its weaknesses are verbosity (redundant Key Points) and missing explicit validation checkpoints in batch/write workflows.

Suggestions

Add an explicit validation/verification step to the ETL and array-write workflows (e.g. verify row counts or read back the written Parquet/Zarr) so batch operations have feedback loops.

Trim the per-component 'Key Points' bullets that restate the preceding Quick Example, and shorten the Overview so SKILL.md reads as a lean overview.

Replace placeholders in examples (python_function, computation, large_dataset) with concrete definitions so every snippet is copy-paste runnable.

DimensionReasoningScore

Conciseness

The ~470-line body is mostly efficient and actionable, but the Overview restates what Dask is and Key Points sections often restate the adjacent Quick Example, so it could be tightened.

3 / 5

Actionability

Most examples are concrete and copy-paste ready (read_csv, groupby.compute, Client().map), but several use undefined placeholders like 'python_function', 'computation', and 'large_dataset'.

4 / 5

Workflow Clarity

The iterative-development workflow is sequenced, but Dask is inherently batch processing and the ETL/write workflows (to_parquet, to_zarr) lack explicit output validation checkpoints, which caps this dimension at 3.

3 / 5

Progressive Disclosure

Good one-level-deep references to real files (dataframes.md, arrays.md, bags.md, futures.md, schedulers.md, best-practices.md) with a clear Reference Files index, though the inline body is long for an overview and some sections could live in references.

4 / 5

Total

14

/

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.

The description is well-constructed: it answers both what and when, uses natural trigger terms, and explicitly differentiates Dask from adjacent tools (vaex, polars). It is specific and concise without fluff.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('scale existing pandas/NumPy code beyond memory or across clusters', 'parallel file processing', 'distributed ML', 'integration with existing pandas code'), but stops at the capability level rather than enumerating specific operations.

4 / 5

Completeness

Explicitly states what it does ('Distributed computing for larger-than-RAM pandas/NumPy workflows') and when to use it ('Use when you need to scale... beyond memory or across clusters') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keywords ('larger-than-RAM', 'scale pandas/NumPy', 'parallel file processing', 'distributed ML', 'out-of-core', 'in-memory') that users would say, though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche (distributed larger-than-RAM pandas/NumPy) and explicit boundary guidance contrasting vaex (out-of-core single machine) and polars (in-memory speed), minimizing conflict risk.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.