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.

69

Quality

84%

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

The canonical home for this skill is tooluniverse-data-wrangling in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 dense, highly actionable reference cookbook of executable Python for many scientific formats and APIs, with good progressive disclosure via one external reference. Its main weakness is workflow clarity: batch operations lack explicit validation checkpoints despite good sequencing and error handling.

Suggestions

Add explicit per-batch validation checkpoints to bulk-download/bulk-fetch workflows (e.g., assert record count or schema before extending the next batch) to lift workflow clarity past the batch-operations cap.

Consider moving Sections A and/or B into a separate reference file (mirroring specialized-domains.md) so SKILL.md stays a tighter overview.

Add a brief top-level 'how to choose a section' decision line that ties the sections into a single sequenced workflow with a validate->fix->retry feedback loop.

DimensionReasoningScore

Conciseness

Largely lean code-with-inline-comment style with no conceptual padding and assumed competence, but the sheer volume and some repeated per-domain scaffolding keep it just below the score-5 'every token earns its place' anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready Python with real API endpoints (NCBI E-utilities, UniProt, GDC, ClinicalTrials.gov v2) and concrete patterns covering common cases.

5 / 5

Workflow Clarity

Multi-step sequences are shown (search->fetch batches, cursor/offset pagination, retry loops) and error handling is present, but batch operations lack explicit per-batch validation checkpoints, triggering the batch-operations cap at 3.

3 / 5

Progressive Disclosure

Clear section structure (A-D) with a well-signaled, verified one-level reference (specialized-domains.md) for domains 11-24, though Sections A and B inline a large amount of compact material that could be split further.

4 / 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.

The description is specific, complete, and distinctive, clearly framing the skill as a fallback for scientific data access when dedicated tools fall short. Trigger terms include concrete file extensions and natural user phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (downloading, parsing, multi-step API workflows, bulk records, writing Python via Bash) across a comprehensive range of formats and scenarios, matching the score-5 anchor.

5 / 5

Completeness

Explicitly states what the skill does ('downloading and parsing scientific data', 'Write Python code via Bash') and when to use it ('when ToolUniverse tools don't cover...', 'Use for...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keywords and file extensions (VCF/h5ad/BAM/SDF/GCT, 'bulk records', 'thousands of records') with good synonym coverage, just short of the fully comprehensive score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (escape hatch when ToolUniverse tools don't cover a source or return only metadata/bulk records), giving distinct triggers and minimal conflict risk.

5 / 5

Total

19

/

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
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.