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.

2.16x

Quality

73%

Does it follow best practices?

Impact

80%

2.16x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/string-database/SKILL.md

Quality

Content

65%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 content is highly actionable with executable code throughout, but it is overly long for a SKILL.md, repeats threshold guidance, references missing bundle files, and lacks explicit error-recovery feedback loops in its workflows.

Suggestions

Create the referenced bundle files (scripts/string_api.py, scripts/string_enrichment.py, references/string_reference.md) or remove the references; missing files undermine progressive disclosure.

Consolidate the confidence-threshold guidance into one section and move the full API/parameter reference into references/string_reference.md to reduce the body length.

Add explicit validation/retry steps to the workflows (e.g., check for the 'Error:' prefix and retry/handle) for the batch and network operations.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient with executable code and no concept-explaining fluff, but the ~525-line body repeats confidence-threshold guidance in three places (network parameters, 'Understanding Confidence Scores', and 'API Best Practices') and could be tightened.	2 / 3
Actionability	Every operation has fully executable Python code with concrete, copy-paste-ready examples plus explicit parameter tables, matching the anchor for complete executable guidance.	3 / 3
Workflow Clarity	Five numbered workflows give a clear sequence, and enrichment workflows include FDR-threshold filtering as implicit validation, but none include explicit error-recovery feedback loops despite API calls being failure-prone ('Error:' prefix handling is mentioned only in best practices, not in the workflows).	2 / 3
Progressive Disclosure	The body signals one-level-deep references to scripts/string_api.py, scripts/string_enrichment.py, and references/string_reference.md, but those bundle files do not exist in the skill directory, and the SKILL.md is itself a long monolithic block that should be partly externalized.	2 / 3
	Total	9 / 12 Passed

Description

82%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.

The description is specific, distinctive, and rich in natural trigger terms, but it omits an explicit 'Use when...' clause, which caps completeness. Adding explicit when-to-use guidance would raise it to a top score.

Suggestions

Add an explicit 'Use when...' clause naming the triggering scenarios (e.g., 'Use when working with protein-protein interactions, performing GO/KEGG enrichment, or querying the STRING database').

Confirm third-person voice is maintained (it currently is) and avoid any first/second person to preserve specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Network analysis, GO/KEGG enrichment, interaction discovery') plus interaction querying, matching the anchor that lists several specific actions rather than vague language.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the trailing 'for systems biology' is a purpose hint, not explicit when-to-use guidance, so completeness is capped at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes natural user-facing terms a bioinformatician would say — 'protein-protein interactions', 'GO/KEGG enrichment', 'STRING', 'systems biology' — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The STRING PPI niche is specific and its triggers (protein-protein interactions, GO/KEGG enrichment) are distinct, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/string-database/SKILL.md
Commit: df37802

Reviewed: 18 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.