CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-data-wrangling

Universal data access patterns for downloading and parsing scientific data when ToolUniverse tools don't cover the source, only return metadata, or you need bulk records. Use for VCF/h5ad/BAM/SDF/GCT parsing, multi-step API workflows (search to filter to download to parse), thousands of records at once, or sources with no dedicated tool. Write Python code via Bash for every step.

76

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The content is a dense, actionable reference with executable code throughout and good progressive disclosure via a single offloaded reference file, weakened only by the absence of explicit verification checkpoints in its batch/bulk-download workflows.

Suggestions

Add an explicit verify-after-download checkpoint to the bulk-download patterns (e.g. check file size/unzip test) to satisfy the batch-operations validation requirement and lift workflow_clarity to 3.

Show a brief search->filter->download->parse end-to-end example with a validation step between stages so the multi-step workflow feedback loop is explicit rather than implied.

Include a one-line note on how to confirm a bulk fetch succeeded before parsing (e.g. guard against partial/empty files) alongside the existing HTML-error-page guard.

DimensionReasoningScore

Conciseness

Lean reference where nearly every line is an executable snippet or table row; it assumes Claude's competence and avoids explaining basic concepts like what a file format is, so every token earns its place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready Python across many formats and APIs (e.g. the VCF-to-DataFrame snippet and the NCBI esearch/efetch batching loop), with specific commands rather than pseudocode.

3 / 3

Workflow Clarity

Multi-step patterns like search->fetch->parse, pagination, and retry are clearly sequenced, but bulk download and batch operations lack explicit validation/verification checkpoints, which caps workflow clarity at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

The body is a concise overview that splits 14 specialized domains into a one-level-deep reference (references/specialized-domains.md) with a clearly signaled 'When to Read' table; the referenced file is real and navigation is easy.

3 / 3

Total

11

/

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.

The description is specific, complete, and clearly scoped: it names concrete formats and workflows, includes explicit 'Use for' trigger guidance, and occupies a distinct niche tied to ToolUniverse gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'downloading and parsing scientific data', 'VCF/h5ad/BAM/SDF/GCT parsing', and 'multi-step API workflows (search to filter to download to parse)', matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what it does ('Universal data access patterns for downloading and parsing scientific data') and when to use it via the 'Use for...' clause with explicit triggers.

3 / 3

Trigger Term Quality

Includes natural user-facing terms like 'VCF/h5ad/BAM/SDF/GCT', 'bulk records', 'metadata/search results', and 'no dedicated tool', giving good coverage of the phrases a user would say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to the niche of sources ToolUniverse tools do not cover, with distinct triggers that make it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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
mims-harvard/ToolUniverse
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.