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

69%

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

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.

The body is well-structured, actionable, and uses progressive disclosure with real bundle files referenced one level deep. Its main weaknesses are missing validation/feedback loops in batch API workflows and one incorrect import path in the enrichment example.

Suggestions

Add explicit validation checkpoints to the workflows (e.g., after each API call, check for an 'Error:' prefix or empty result and retry/adjust threshold), turning them into validate -> fix -> retry loops.

Fix the enrichment import: section 5 imports from 'scripts.string_enrichment' but the function lives in 'scripts.string_api' — make all enrichment examples import from scripts.string_api.

Consolidate the duplicated confidence-threshold guidance and species table so each appears in one authoritative place and the other section links to it.

Dimension	Reasoning	Score
Conciseness	Largely efficient with no padding about concepts Claude already knows (no definitions of proteins, PPIs, or libraries), but confidence thresholds and the species table are repeated across sections and could be consolidated; efficient with minor trimming possible.	4 / 5
Actionability	Provides mostly executable, copy-paste-ready code with parameters, output columns, and interpretation for each operation, but section 5 imports string_enrichment from a non-existent 'scripts.string_enrichment' module (it lives in scripts.string_api), which would break that example.	4 / 5
Workflow Clarity	Five workflows are clearly sequenced with numbered steps, but batch/network API operations lack explicit validation checkpoints and feedback loops (e.g., check 'Error:' prefix, handle empty results, retry) — the best-practices error handling is not wired into the workflows, capping this at 3 for batch operations.	3 / 5
Progressive Disclosure	Body is a well-organized overview that signals one-level-deep references to the real bundle files references/string_reference.md and scripts/string_api.py, with bulk API detail deferred to the reference; minor gaps from duplicated threshold/species content that could be fully deferred.	4 / 5
	Total	15 / 20 Passed

Description

70%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.

The description is specific and distinctive with concrete actions and natural domain terms, but it lacks an explicit 'when to use' trigger clause, capping completeness. Adding a 'Use when ...' sentence would lift it to the top anchor band.

Suggestions

Add an explicit trigger clause, e.g. 'Use when querying protein-protein interaction networks, performing GO/KEGG enrichment, or finding interaction partners.'

Include common synonyms and file/format cues users actually say, such as 'PPI', 'interactome', and 'protein network'.

Lead with the concrete actions and keep the scale metrics (59M proteins, 20B interactions) as supporting detail rather than the opening phrase.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Query STRING API', 'Network analysis', 'GO/KEGG enrichment', 'interaction discovery' — with only minor coverage gaps; falls just below the comprehensive multi-action anchor of 5.	4 / 5
Completeness	Provides a clear 'what' (query STRING API for PPIs, enrichment, discovery) but has no explicit 'Use when...' or equivalent trigger clause — only a loose 'for systems biology' tag — so per the missing-trigger cap it cannot exceed 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('protein-protein interactions', 'GO/KEGG enrichment', 'interaction discovery', 'systems biology') but misses common synonyms like 'PPI', 'interactome', or 'protein network'; good but not comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly distinct niche (STRING protein-protein interaction database with specific scale metrics) with minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 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: 3a6c3a9

Reviewed: about 24 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.