string-database

Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.

Quality

78%

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 ./skills/string_database/SKILL.md

Quality

Content

57%Weight 40%Scale 1-3

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 strong progressive disclosure and sensible guardrails, but the core query workflow is only partially actionable because command specifics live in reference files and the sequencing lacks explicit feedback loops. Minor redundancy in the mandatory-species rule slightly reduces conciseness.

Suggestions

Add one complete, runnable example command (with a real command like `map` and species flag) in SKILL.md so the Tool Execution section is copy-paste ready rather than a placeholder template.

Condense the mandatory-species rule: state the requirement and the exact prompt once instead of repeating 'MUST' three times, and merge the standalone Notification rule into the Prerequisites license step to remove overlap.

Include a short numbered end-to-end workflow (ask species → map identifiers → run query → inspect output with jq/head) with an explicit verify step so the sequence is self-contained in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no explainer on what STRING/PPIs are), but the species rule restates the MUST-ask imperative three times and the Notification rule overlaps with the Prerequisites section, so it could be tightened.	2 / 3
Actionability	Gives a concrete CLI invocation pattern ("uv run scripts/string_cli.py <command> [options] --output /tmp/out.tsv") but uses placeholder <command> tokens and defers all real command details to the reference files, so it is not copy-paste ready.	2 / 3
Workflow Clarity	Core Rules and Prerequisites provide useful checkpoints (ask species first, notify on license), but the end-to-end query workflow is only implied and largely pushed into the reference files rather than sequenced with explicit feedback loops in SKILL.md.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep links to four real reference files (mapping.md, interactions.md, enrichment.md, valuesranks.md), each mapped to a feature domain with easy navigation.	3 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person description that clearly states capabilities and explicit use-when triggers tied to natural user language. It earns top marks across specificity, trigger quality, completeness, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "protein-protein interactions (PPIs), functional enrichment, and homology" — matching the anchor for specific concrete actions.	3 / 3
Completeness	Explicitly states both what ("Query the STRING database for...") and when ("Use when the user asks about...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural user phrasings such as "interactions between specific proteins", "interaction evidence", "confidence scores", "protein interaction partners", and "pathway enrichments", which users would actually say.	3 / 3
Distinctiveness Conflict Risk	The STRING/PPI niche is narrow and the triggers (PPIs, confidence scores, pathway enrichment) are unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 12 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: google-deepmind/science-skills
Path: skills/string_database/SKILL.md
Commit: 0b42509

Reviewed: 7 days 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.