tooluniverse-proteomics-analysis

Mass-spec proteomics analysis — protein identification, quantification (LFQ, TMT, iTRAQ), differential expression (tumor vs normal, treatment vs control), PTM identification, and pathway enrichment on protein lists. Use when you have proteomics MS output, asking about protein abundance differences, or doing systems-level proteomic interpretation.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-proteomics-analysis/SKILL.md

Quality

Content

50%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.

The body is well-structured with a clear phase overview, quantified minimums, and decision trees, but it leans on domain exposition Claude already knows, lacks executable analysis code, and references a PHASE_DETAILS.md file that is absent from the bundle.

Suggestions

Replace the domain tutorial in 'Interpretation Framework' (PMF/MS/MS/protein inference, PTM basics) with concise decision rules, since Claude already knows these concepts.

Add at least one executable Python snippet (e.g., a limma/MSstats-style DE workflow via pandas/statsmodels) so the skill instructs rather than describes.

Either create the referenced PHASE_DETAILS.md or remove the broken [PHASE_DETAILS.md](PHASE_DETAILS.md) link, and move the inlined phase detail into it to tighten the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but lengthy tutorial-style explanation of protein identification (PMF, MS/MS, protein inference) and PTM reasoning restates domain concepts Claude already knows; the 'Interpretation Framework' section is the main source of over-explanation.	3 / 5
Actionability	Gives concrete thresholds (FDR<0.05, loc prob>0.75, >=2 unique peptides) and named tools, but contains almost no executable code or commands — only one ToolUniverse invocation pattern; it describes strategy rather than providing copy-paste-ready analysis code.	3 / 5
Workflow Clarity	An 8-phase sequence is laid out with a 'RULE ZERO' pre-check, but the validation checkpoint is a single conditional ('only if none of the above exist') and there are no validate->fix->retry feedback loops for batch/destructive re-analysis; the destructive-operation cap applies.	3 / 5
Progressive Disclosure	Structure is present with a one-level reference to PHASE_DETAILS.md, but the referenced file does not exist in the bundle, and substantial phase detail that belongs in that file is instead inlined in the SKILL.md body.	3 / 5
	Total	12 / 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 with concrete capabilities and an explicit 'Use when' trigger clause covering both what and when. The only minor gap is trigger-term breadth — it omits common tool names and file extensions users may naturally mention.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'protein identification, quantification (LFQ, TMT, iTRAQ), differential expression (tumor vs normal, treatment vs control), PTM identification, and pathway enrichment' — with comprehensive coverage of the proteomics domain.	5 / 5
Completeness	Explicitly answers both 'what' (the analysis capabilities) and 'when' via a concrete 'Use when you have proteomics MS output, asking about protein abundance differences, or doing systems-level proteomic interpretation' clause.	5 / 5
Trigger Term Quality	Good natural coverage ('proteomics MS output', 'protein abundance differences', 'systems-level proteomic interpretation') but is missing common synonyms and explicit file/format extensions users might say (e.g., MaxQuant, .txt, 'volcano plot').	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (mass-spec proteomics) with distinct trigger phrases that are unlikely to fire for adjacent omics or general data skills; minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-proteomics-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.