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

82%

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

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, expert-level body with strong conciseness and good concrete thresholds, but it over-defers the actual analysis procedure and report template to PHASE_DETAILS.md, which is absent — leaving the workflow checkpoints and the progressive-disclosure pointer unresolved. Fixing the missing reference and adding per-phase validation checkpoints would lift the weaker dimensions.

Suggestions

Create the referenced PHASE_DETAILS.md (or inline the per-phase procedures) so the 'detailed procedures per phase' and 'report template' pointers actually resolve.

Add explicit per-phase validation checkpoints in the body (e.g., after normalization verify intensity distributions; after DE confirm replicate and peptide-count gates before reporting) to provide a validate->fix->retry loop for this batch statistical workflow.

Either provide runnable end-to-end analysis code in the body or in PHASE_DETAILS.md, since the current body gives decision criteria and tool names but not the executable analysis recipe.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it never explains basic concepts (what a peptide or mass spectrometer is) and every token earns its place via concrete thresholds ('padj < 0.01, FC > 2.0, >=5 unique peptides') and expert guidance (T1-T4 evidence grading, phospho-site localization probability > 0.75).	3 / 3
Actionability	It gives concrete tool invocations ('tu run read_executed_notebook ...', 'proteins_api_search', 'OpenTargets_get_target_safety_profile_by_ensemblID') and a precise quantification decision tree, but the actual end-to-end analysis recipe is deferred to PHASE_DETAILS.md ('See PHASE_DETAILS.md for detailed procedures per phase'), so the executable procedure is not present in the body.	2.5 / 3
Workflow Clarity	The eight phases are sequenced via the ASCII diagram and RULE ZERO provides an explicit pre-check, but for a batch statistical analysis there are no explicit per-phase validation/checkpoint steps in the body — those are deferred to the missing PHASE_DETAILS.md, so per the feedback-loop guidance workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned and signals a single one-level-deep reference ('See PHASE_DETAILS.md for detailed procedures per phase'), but that referenced file does not exist, so the navigation is broken — better than a monolithic wall or deep nesting, but it fails the score-3 bar of easy, resolving navigation.	2 / 3
	Total	9.5 / 12 Passed

Description

92%

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: specific, complete (explicit what + when), and distinctive, with only slightly incomplete trigger-term coverage. It would benefit from adding a couple more natural-language trigger phrasings to the 'Use when' clause.

Suggestions

Add more natural trigger phrasings to the 'Use when' clause — e.g., 'differential protein expression,' 'PTM analysis,' 'tumor vs normal proteomics' — so the trigger half mirrors the breadth of the capability list.

Replace 'systems-level proteomic interpretation' with phrasing a user would more naturally say, such as 'pathway or network-level proteomics interpretation.'

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions with specific technique variants — 'protein identification, quantification (LFQ, TMT, iTRAQ), differential expression (tumor vs normal, treatment vs control), PTM identification, and pathway enrichment' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (the long capability list) and 'when' ('Use when you have proteomics MS output...'), with explicit triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	The trigger clause ('Use when you have proteomics MS output, asking about protein abundance differences, or doing systems-level proteomic interpretation') gives several natural phrasings, but 'systems-level proteomic interpretation' leans jargon and common variations (e.g., 'protein expression differences,' 'PTM analysis') are not captured in the trigger half — good but incomplete coverage.	2.5 / 3
Distinctiveness Conflict Risk	The mass-spec proteomics niche with method-specific triggers (LFQ, TMT, iTRAQ, PTM) is clearly distinct and unlikely to fire for non-proteomics tasks, matching the score-3 anchor.	3 / 3
	Total	11.5 / 12 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: 089eb8e

Reviewed: about 7 hours 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.