cerna-analysis

Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory. NOT for: differential expression, single-cell analysis, enrichment analysis, or workflows without a key gene list.

Quality

87%

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.

The body is highly actionable with complete CLI reference, examples, and error handling, and its reference structure is clearly signaled and one level deep. The main gaps are minor redundancy (repeated igraph notes) and a few referenced bundle paths that do not actually exist.

Suggestions

Remove the duplicated igraph dependency note — keep it in one place (e.g. the Usage block) and link to troubleshooting.md from there instead of restating it in the file-reading table and error table.

Create tests/data/gene.txt (referenced in the file-reading table and Testing section) or remove those references, so every cited bundle path resolves.

Either add the per-source starbase/miRDB/miRTarbase miRNA_mRNA CSVs to references/database/ or note in the Database Directory section that only the combined file ships, to match the documented mirna_dataset modes.

Dimension	Reasoning	Score
Conciseness	Mostly lean and table-driven with no padding about concepts Claude already knows, but the igraph dependency note is repeated across three sections and the refusal quote is somewhat long, giving minor trim opportunities.	4 / 5
Actionability	Fully executable copy-paste-ready commands, a complete arguments table with types and defaults, worked examples, concrete error codes with solutions, and validation commands — covering the common cases.	5 / 5
Workflow Clarity	A clear four-step sequence with validation in Step 1 and an explicit stop condition in Step 3, plus an error-recovery table, but the checkpoints are described as script-internal behavior rather than explicit user-facing validation commands at each step.	4 / 5
Progressive Disclosure	A well-signaled 'When to Read External Files' table points one level deep to real reference files, but several referenced paths are absent from the bundle (tests/data/ and the per-source starbase/miRDB/miRTarbase mRNA CSVs), slightly undermining otherwise-excellent navigation.	4 / 5
	Total	17 / 20 Passed

Description

92%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, complete, and distinctive, with an explicit 'Use when' trigger and a 'NOT for' boundary that sharply scope the skill. The only minor gap is keyword variety — a few synonyms or file-extension triggers would round it out.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — building a ceRNA regulatory network, combining bundled miRNA-mRNA and miRNA-lncRNA database files, flat-file CSV exports, and PDF visualization in a single output directory — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly answers both what (build ceRNA network from a key gene list with CSV/PDF outputs) and when ('Use when building a ceRNA regulatory network from a key gene list'), with concrete trigger phrases and an explicit 'NOT for' boundary.	5 / 5
Trigger Term Quality	Strong domain keywords a user would actually say (ceRNA regulatory network, key gene list, miRNA-mRNA, miRNA-lncRNA) but no file-extension triggers or synonyms, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	A clear niche (ceRNA network from a key gene list) with distinct triggers and an explicit exclusion list (differential expression, single-cell, enrichment), keeping conflict risk minimal.	5 / 5
	Total	19 / 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/cerna-analysis/SKILL.md
Commit: 63c61d3

Reviewed: 3 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.