CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-proteomics-data-retrieval

Find and retrieve proteomics datasets from MassIVE and ProteomeXchange. Search by species, keyword, or accession; retrieve detailed metadata (instruments, publications, species, PTMs studied). Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage across studies, and pre-download dataset evaluation.

67

Quality

80%

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 ./plugins/tooluniverse/skills/tooluniverse-proteomics-data-retrieval/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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, domain-rich skill body with concrete tool guidance, clear phase sequencing, and fallback strategies. Its main weaknesses are duplicated content (taxonomy IDs, response-format notes, interpretation guidance) and one incorrect tool reference, plus reference tables inlined that would fit better in a separate file.

Suggestions

Deduplicate content: keep the species taxonomy IDs only in the Common Species table (and point Phase 0/Key Principles at it) and state the Response Format Notes once, in the Tool Parameter Reference.

Fix the incorrect tool name 'Dataverse_get_dataset' in the Limitations section to 'ProteomeXchange_get_dataset'.

Move reference material (tool parameter reference, species taxonomy table, interpretation framework) into a references/ file, keeping SKILL.md as a concise workflow overview.

DimensionReasoningScore

Conciseness

The body is mostly dense, non-obvious domain content (tool parameters, response shapes, fallbacks), but species taxonomy IDs are stated three times (Key Principles, Phase 0, and the Common Species table), the Response Format Notes are repeated verbatim in Phase 1 and the Tool Parameter Reference, and the 'Domain Reasoning' paragraph largely restates the Interpretation Framework — clear tightening opportunities.

3 / 5

Actionability

Concrete tool names with exact parameter types, ranges, defaults, and example calls like 'MassIVE_search_datasets(page_size=20, species="9606")' make the guidance mostly executable, but 'get details via Dataverse_get_dataset' (Limitations) references a nonexistent tool, a minor gap.

4 / 5

Workflow Clarity

The four phases are clearly sequenced with explicit Phase 0 decision/routing logic and a Fallback Strategies table for error recovery, but there are no explicit validation checkpoints on retrieved results, keeping it below the top anchor.

4 / 5

Progressive Disclosure

The self-contained body is well organized with clear section headers and one-level-deep external links, though roughly a hundred lines of reference material (species taxonomy table, tool parameter reference, interpretation framework) are inlined that could live in a separate references file.

4 / 5

Total

15

/

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 description: concrete, comprehensive, third-person, with an explicit 'Use for' clause naming three distinct use cases. The only improvement would be adding 'mass spectrometry'/'MS' synonyms to widen trigger coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Find and retrieve proteomics datasets from MassIVE and ProteomeXchange', 'Search by species, keyword, or accession', 'retrieve detailed metadata (instruments, publications, species, PTMs studied)' — comprehensively covering all three search modes and both repositories with no evident gaps.

5 / 5

Completeness

It explicitly answers both what it does (find/retrieve datasets, search modes, metadata returned) and when to use it ('Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage across studies, and pre-download dataset evaluation') with concrete use-case triggers.

5 / 5

Trigger Term Quality

Good coverage of natural terms users would say ('proteomics datasets', 'PTMs', 'accession', 'MassIVE', 'ProteomeXchange'), but common synonyms like 'mass spectrometry', 'MS data', or 'mass spec' are missing, so a few natural phrasings would not trigger this skill.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — public proteomics dataset retrieval from two named repositories with PXD/MSV-style accessions and PTM metadata — making it highly unlikely to trigger for unrelated skills.

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.

Validation — 16 / 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.