ppi-network-analysis

Use when you need a standardized R CLI workflow to build a protein-protein interaction network from a local gene list and an offline STRING cache, export node and edge tables, and render a reproducible PDF network plot. NOT for online API fetching, arbitrary graph databases, multi-omics integration, or non-STRING interaction sources.

Quality

85%

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

Quality

Content

82%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-structured, highly actionable skill body with strong navigation and concrete executable commands. Its main weaknesses are a broken 'tests/data/' reference, a large inline argument table that duplicates the cli-guide reference, and the absence of an explicit validation checkpoint in the primary workflow.

Suggestions

Create the missing tests/data/ directory with the bundled small gene list, or remove the tests/data reference from the navigation table and Testing section.

Move the full Arguments table into references/cli-guide.md and keep only the required/core arguments inline to reduce token redundancy.

Add an explicit validate-then-fix step in the Usage flow (e.g. check expected output files exist and inspect ppi_summary.csv before declaring success) to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no padding about what PPI networks or STRING are, and uses tight tables throughout (4-anchor); the ~30-row inline Arguments table partly duplicates the dedicated cli-guide.md reference and could be trimmed, keeping it below a 5.	4 / 5
Actionability	Copy-paste-ready 'Rscript scripts/main.R ...' commands with real flags cover the basic run and plot-only cases, plus a runnable smoke test, matching the 5-anchor for fully executable guidance.	5 / 5
Workflow Clarity	The single-command workflow is unambiguous and supported by an error-code table (feedback for recovery) and a Testing section with expected-output verification (4-anchor); it is not a 5 because the main flow lacks an explicit validate-fix-retry checkpoint sequence.	4 / 5
Progressive Disclosure	The 'When to Read External Files' table provides excellent one-level-deep navigation to real files (algorithm.md, main.R, troubleshooting.md, cli-guide.md) (4/5-anchor), but the referenced 'tests/data/' path does not exist on disk and the large inline Arguments table overlaps cli-guide.md, preventing a 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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 with clear trigger guidance and explicit negative boundaries that distinguish it from相邻 skills. The only notable issue is second-person voice ('you need'), which lowers the specificity score per the rubric.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. 'Builds a protein-protein interaction network... Use when a standardized R CLI workflow is needed...'.

Add common file extensions or synonyms (e.g. '.csv', 'gene list', 'interactome') to push trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes 'build a protein-protein interaction network from a local gene list and an offline STRING cache, export node and edge tables, and render a reproducible PDF network plot' list multiple concrete actions (5-anchor), but the second-person 'Use when you need' triggers the voice penalty reducing specificity by 1.	4 / 5
Completeness	It explicitly answers both what (build/export/render) and when ('Use when you need a standardized R CLI workflow...') with concrete trigger phrases and an explicit 'NOT for' boundary, matching the 5-anchor.	5 / 5
Trigger Term Quality	Terms like 'protein-protein interaction network', 'gene list', 'STRING', 'node and edge tables', and 'PDF network plot' are natural domain keywords a bioinformatics user would say (4-anchor), though file extensions and common synonyms are absent so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined (offline STRING cache, R CLI, PPI networks) and the 'NOT for online API fetching, arbitrary graph databases, multi-omics integration, or non-STRING interaction sources' boundary minimizes conflict risk, matching the 5-anchor.	5 / 5
	Total	18 / 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: awesome-med-research-skills/Data Analysis/ppi-network-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~6 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.