string-database

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Quality

62%

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 ./backend/cli/skills/databases/string-database/SKILL.md

Quality

Content

57%

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

The skill body is well-structured with good progressive disclosure and mostly actionable code, but it is padded with concepts Claude already knows, lacks validation checkpoints in its batch workflows, and contains a broken import statement. Tightening redundancy and fixing the enrichment import would meaningfully raise the score.

Suggestions

Fix the enrichment import to 'from scripts.string_api import string_enrichment' so the example is actually executable.

Add explicit validation checkpoints to workflows (e.g., check for an 'Error:' prefix and handle empty results before proceeding) so batch protein-list operations have a validate->fix->retry loop.

Trim redundancy — explain the confidence thresholds once and remove license/citation boilerplate that duplicates the referenced documentation.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented and code-heavy but re-explains concepts Claude already knows (the full evidence-channel taxonomy, p-value interpretation, license/citation boilerplate) and repeats confidence-threshold guidance in three sections, so it is mostly efficient but could be tightened.	2 / 3
Actionability	Most examples are executable and copy-paste ready with real calls and output columns, but the enrichment section imports from a nonexistent module ('from scripts.string_enrichment import string_enrichment') when the function actually lives in string_api.py, which is incomplete/incorrect guidance.	2 / 3
Workflow Clarity	Five workflows give clear step sequencing, but none include explicit validation checkpoints or validate->fix->retry feedback loops for batch protein-list operations, which the rubric says should cap workflow clarity at 2.	2 / 3
Progressive Disclosure	The overview points cleanly to two real, one-level-deep bundle files (scripts/string_api.py and references/string_reference.md) with a 'Detailed Reference' section enumerating what the reference contains; navigation is easy and content is appropriately split.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 and well-differentiated, but it lacks an explicit 'when to use' trigger clause and natural trigger-term coverage is partial. Adding a 'Use when...' sentence with user-facing synonyms (STRING, PPI, interactome) would raise it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when querying protein-protein interactions, building interaction networks, or running functional enrichment on protein lists.'

Include natural user-facing synonyms such as 'STRING database', 'PPI', and 'interactome' alongside the technical terms.

Keep the concise action list but trim the parenthetical stats unless they aid triggering.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Query STRING API for protein-protein interactions', 'Network analysis', 'GO/KEGG enrichment', 'interaction discovery' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is explicit, but the 'when' is only implied by the trailing 'for systems biology' clause; there is no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('protein-protein interactions', 'GO/KEGG enrichment', 'Network analysis') but omits common variations a user would say ('STRING database', 'PPI', 'interactome', 'protein interactions'), so it is missing common variations rather than offering good coverage.	2 / 3
Distinctiveness Conflict Risk	The STRING API / protein-protein interaction niche is clearly delimited with distinctive triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (534 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/string-database/SKILL.md
Commit: 52845c3

Reviewed: about 12 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.