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.

74

Quality

91%

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

83%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 highly actionable, token-efficient reference cookbook with executable code and clean section structure. The main gap is workflow clarity: batch operations show sequences but do not integrate explicit validation/feedback checkpoints inline, so the batch-operation cap holds workflow clarity at 3.

Suggestions

Weave validation checkpoints into the batch workflow examples (e.g., after each efetch batch, check for partial/empty results or HTTP errors before continuing) so the search→filter→download→parse loops have explicit feedback loops.

Add a short end-to-end worked example that shows the full search→download→parse→validate sequence with inline error checks, rather than separating error handling into Section D only.

Consider moving the larger Section A format cookbook or Section B API patterns into additional one-level reference files to further lighten the main SKILL.md body.

DimensionReasoningScore

Conciseness

A dense reference cookbook of code snippets with inline format-naming comments; it assumes Claude's competence and avoids explaining concepts Claude already knows, so every token earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready code throughout — real API URLs, query params, pagination/cursor loops, and per-format parsers covering the common scientific-data cases.

5 / 5

Workflow Clarity

Multi-step batch workflows (e.g., esearch→efetch in batches, cursor pagination) are sequenced but lack inline validate→fix→retry checkpoints; error handling and retries live in a separate Section D rather than being woven into the workflow steps, so the batch-operation cap applies.

3 / 5

Progressive Disclosure

Good section structure with a well-signaled, one-level-deep reference (references/specialized-domains.md, with a 'When to Read' table) for domains 11-24, though substantial cookbook and API content remains inline in the 390-line body rather than being split further.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An excellent description that concretely states capabilities, provides rich trigger terms with file extensions and synonyms, explicitly addresses both what and when, and carves out a distinct niche. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'downloading and parsing scientific data', 'VCF/h5ad/BAM/SDF/GCT parsing', 'multi-step API workflows (search to filter to download to parse)', and 'Write Python code via Bash' — with comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers 'what' (universal data access patterns for downloading and parsing scientific data) and 'when' via a concrete 'Use for...' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including file extensions (VCF, h5ad, BAM, SDF, GCT) and synonyms a user would say ('bulk records', 'thousands of records', 'sources with no dedicated tool').

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche — scientific data access when ToolUniverse tools don't cover the source or return only metadata — with distinct, format-specific triggers and minimal overlap risk.

5 / 5

Total

20

/

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.