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.

Well-structured and actionable reference material for a read-only retrieval skill, with a clear phased workflow and concrete tool guidance. It is somewhat verbose — re-explaining domain concepts Claude knows and duplicating response-format notes — and could offload reference tables to bundle files.

Suggestions

Trim or remove the 'Domain Reasoning' and 'Interpretation Framework' sections, which re-explain proteomics concepts (isobaric labeling bias, DIA vs DDA, instrument resolution) Claude already knows; keep only task-specific decision guidance.

De-duplicate the response-format notes, which appear both in Phase 1 ('Response Format Notes') and again in the 'Tool Parameter Reference' section.

Move the 'Common Species Taxonomy IDs' table and the 'Tool Parameter Reference' into a references/ bundle file and link to it from the body to reduce the monolithic length and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient but the 'Domain Reasoning' and 'Interpretation Framework' sections re-explain proteomics concepts (TMT/iTRAQ bias, DIA vs DDA, Orbitrap vs ion trap) Claude largely knows, and the response-format notes are duplicated between Phase 1 and the Tool Parameter Reference.

3 / 5

Actionability

Concrete tool names, parameters, return shapes, and example calls like 'MassIVE_search_datasets(page_size=20, species="9606")' plus a report template give mostly executable guidance, with only minor gaps (no worked end-to-end example).

4 / 5

Workflow Clarity

A clear four-phase sequence with explicit Phase 0 decision logic and a Fallback Strategies table for error recovery; the skill is read-only so the destructive-operation cap does not apply, though explicit pre-call validation checkpoints are absent.

4 / 5

Progressive Disclosure

No bundle files exist, but the single file is well-organized into phases and tables with clear section headers; the taxonomy table and tool-parameter reference could be split out, leaving only minor organization gaps.

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, specific description that clearly conveys both capabilities and use cases with repository-specific terminology. The only gap is the absence of accession-format synonyms (PXD/MSV) that users would naturally mention.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Find and retrieve proteomics datasets', 'Search by species, keyword, or accession', 'retrieve detailed metadata (instruments, publications, species, PTMs studied)' — covering the skill comprehensively, matching the level-5 anchor.

5 / 5

Completeness

Explicitly states both what ('Find and retrieve… retrieve detailed metadata') and when ('Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage… pre-download dataset evaluation') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage ('proteomics datasets', 'MassIVE', 'ProteomeXchange', 'species/keyword/accession', 'PTMs') but omits common synonyms and the accession formats (PXD/MSV) users would actually say, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — 'proteomics datasets from MassIVE and ProteomeXchange' — with repository-specific triggers that minimal conflict with other 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.

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.