tooluniverse-protein-interactions

Protein-protein interaction (PPI) network analysis — STRING (predicted + experimental), BioGRID (curated), SASBDB (small-angle scattering). Distinguishes physical interactions (binding) from functional associations (co-expression, co-regulation). Use for interactome queries, complex partner identification, and pathway-level interaction analysis.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-protein-interactions/SKILL.md

Quality

Content

63%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 content-rich body with strong, concrete tool guidance and a clear 4-phase workflow, undermined by substantial inlined biochemistry primers Claude already knows and missing bundle files that the body references.

Suggestions

Move the biochemistry primers (Multimeric Assemblies, Statistical Factors, Coiled-Coil, Detergent Effects) into a separate reference file and keep only the tool-specific decision rules inline, to improve conciseness.

Provide the cited bundle files (python_implementation.py, KNOWN_ISSUES.md) under scripts/ or references/ — currently the body references files that do not exist, which leaves progressive-disclosure navigation dangling.

Add explicit validation checkpoints between workflow phases (e.g., confirm STRING IDs resolved before network retrieval; verify escore availability before claiming physical binding) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	Core tool material (parameters, edge fields, workflow, troubleshooting) is lean, but large biochemistry primers (valency/avidity, Hill/Scatchard plots, coiled-coil heptads, detergent classes) over-explain concepts Claude already knows and are only loosely tied to the skill's tools.	3 / 5
Actionability	Concrete, executable guidance throughout (specific function calls, parameter tables with defaults, a working metadata-extraction snippet, troubleshooting env vars), though only one inline code example and the bulk of examples are deferred to a referenced file.	4 / 5
Workflow Clarity	A clearly sequenced 4-phase workflow with explicit primary/fallback tool choices, but no explicit validation checkpoints or feedback loops between phases.	4 / 5
Progressive Disclosure	Has section headers and points to python_implementation.py and KNOWN_ISSUES.md, but heavy reference and tutorial material is inlined in SKILL.md, and the referenced bundle files do not exist in references/, scripts/, or assets/.	3 / 5
	Total	14 / 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, concrete description that names specific databases and actions, distinguishes interaction types, and provides explicit 'use when' triggers. Minor keyword-synonym gaps keep trigger quality just below full marks.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (PPI network analysis, distinguishing physical vs functional interactions) across three named databases with their roles, giving comprehensive coverage rather than a minor gap.	5 / 5
Completeness	Explicitly answers both 'what' (PPI analysis across STRING/BioGRID/SASBDB, physical-vs-functional distinction) and 'when' ('Use for interactome queries, complex partner identification, and pathway-level interaction analysis') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('protein-protein interaction', 'PPI', 'interactome', 'complex partner identification', 'pathway-level interaction'), but a few domain synonyms users might say (e.g., 'binding partners') are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (PPI network analysis with specific named databases and a physical-vs-functional distinction) with triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-protein-interactions/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.