CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with a clear 4-phase workflow and concrete tool guidance, but it is weighed down by lengthy conceptual domain-reasoning sections that restate known concepts and act as a monolithic block with broken external file references.

Suggestions

Move the multimeric-assembly, coiled-coil, and detergent-effect domain-reasoning sections into a separate reference file (or trim to actionable LOOK-UP guidance only) to reduce tokens on concepts Claude already knows.

Either provide the referenced python_implementation.py and KNOWN_ISSUES.md as bundle files or remove the dangling references so navigation is not broken.

Add a brief validation checkpoint after identifier mapping (e.g., confirm STRING IDs resolved before retrieving the network) to make the workflow's error-recovery explicit.

DimensionReasoningScore

Conciseness

The core workflow and tool tables are lean and information-dense, but extended conceptual sections on multimer valency/statistical factors, coiled-coil heptad prediction, detergent effects, and avidity/Hill/Scatchard plots restate domain knowledge Claude largely already knows and exceed the skill's core PPI-analysis scope.

2 / 3

Actionability

Provides concrete tool names with specific parameters ('STRING_map_identifiers()', 'confidence_score=0.7', 'taxId=9606', 'uniprot_id'), a real executable snippet ('interaction_ids = result.get("metadata", {}).get("interaction_ids", [])'), and copy-paste troubleshooting commands.

3 / 3

Workflow Clarity

A clearly sequenced 4-phase workflow (Identifier Mapping → Network Retrieval → Enrichment → Structural Data) with numbered phases, parameter guidance, and a troubleshooting section covering failure modes; operations are non-destructive so missing hard validation checkpoints is acceptable.

3 / 3

Progressive Disclosure

Sections are well-organized, but the body is a monolithic ~160-line single file with no actual bundle structure, and it references 'python_implementation.py' and 'KNOWN_ISSUES.md' that do not exist in the bundle; extended domain-reasoning content that could be split out remains inline.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, cleanly answering both what the skill does and when to use it within a distinct domain niche. It is concise without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across named databases ('PPI network analysis', 'Distinguishes physical interactions (binding) from functional associations', 'interactome queries, complex partner identification, and pathway-level interaction analysis'), matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both 'what' (PPI network analysis via STRING/BioGRID/SASBDB, distinguishing physical vs functional) and 'when' via the 'Use for interactome queries, complex partner identification, and pathway-level interaction analysis' trigger clause.

3 / 3

Trigger Term Quality

Includes natural user-facing terms ('protein-protein interaction', 'PPI', 'interactome', 'complex partner identification', 'pathway-level interaction analysis') alongside database names, giving good coverage of phrases a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

The PPI/interactome niche with specific database names (STRING, BioGRID, SASBDB) and physical-vs-functional framing is clearly distinct and unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

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.