string-database

Access the STRING database to map identifiers, retrieve protein–protein interaction networks, and run functional/PPI enrichment when you need interaction context for a gene/protein set.

Quality

73%

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 ./scientific-skills/Evidence Insight/string-database/SKILL.md

Quality

Content

68%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 well-organized, mostly actionable skill body with a runnable example and properly signaled bundle references. The main weaknesses are missing validation/error-handling checkpoints in the workflow and incomplete code coverage of the advertised features.

Suggestions

Add a validation/error-handling checkpoint in the example workflow (e.g., check that map_id returns a non-empty identifier and handle HTTP errors) to lift workflow_clarity above 3.

Add short runnable examples for the interaction-partner and functional-enrichment (GO/KEGG) features so actionability covers all advertised capabilities.

Reduce redundancy between Key Features and Implementation Details, and move bulk API/endpoint detail into references/string_reference.md to tighten conciseness and improve the content split.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence (concise Dependencies, commented runnable example), but Key Features and Implementation Details overlap on network retrieval and visualization, leaving minor instances that could be trimmed — efficient but not the lean 5.	4 / 5
Actionability	Provides a copy-paste-ready, executable example importing StringClient and calling map_id, get_network_image, and get_ppi_enrichment, but examples for interaction partners and GO/KEGG functional enrichment are absent, so it stops at "mostly executable with minor gaps" rather than 5.	4 / 5
Workflow Clarity	The example lays out a clear numbered 1-2-3 sequence (map ID → network image → enrichment), but there are no validation checkpoints (e.g., verify map_id returned a valid identifier, handle API errors); the operations are read-only so the destructive-cap doesn't force a 3, but fully absent validation keeps it at 3 rather than 4.	3 / 5
Progressive Disclosure	Good section structure with a clearly signaled one-level-deep reference ("See references/string_reference.md for original API notes and endpoint details") and the wrapper placed in scripts/string_api.py, but the reference file is short and some Implementation Details content is inline that could be split out, leaving minor organization gaps below the 5.	4 / 5
	Total	15 / 20 Passed

Description

78%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 states both capability and a concrete use-trigger, well-targeted to its bioinformatics niche. It could reach the top band by adding the missing capabilities (visualization, interaction partners) and richer trigger synonyms.

Suggestions

Mention the visualization and interaction-partner capabilities in the description to close the specificity/completeness gap toward a 5.

Add natural trigger synonyms users might say, e.g., "STRING IDs", "PPI network", or "network image", to broaden trigger-term coverage.

Consider an additional trigger phrase (e.g., "Use when mapping gene symbols to STRING identifiers or retrieving PPI networks") to make the 'when' as explicit as the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("map identifiers", "retrieve protein–protein interaction networks", "run functional/PPI enrichment") but omits visualization and interaction-partner retrieval the skill supports, leaving minor coverage gaps that keep it just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Access the STRING database to map identifiers, retrieve...networks, and run...enrichment") and when ("when you need interaction context for a gene/protein set"), but the single trigger phrase is less specific/rich than the multi-trigger 5 anchor, so it sits at 4 rather than 5.	4 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ("STRING database", "protein–protein interaction", "PPI enrichment", "interaction context"), but it lacks common synonyms/variants (e.g., "STRING IDs", "network image", "PPI network"), so it falls short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The STRING/PPI-enrichment niche is specific and unambiguous with distinct triggers, giving minimal overlap risk with other skills — a clear match for the 5 anchor rather than the merely "mostly distinct" 4.	5 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/string-database/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.