clinvar-database

Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/clinvar-database/SKILL.md

Quality

Content

61%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 highly actionable, well-structured overview with real one-level-deep references and concrete copy-paste examples for every access mode. Its weaknesses are the missing validation checkpoints in the batch workflows, inline duplication of reference-file content, and off-topic promotional padding at the end.

Suggestions

Add explicit validation/verification steps to the batch workflows, e.g., after Example 2's annotation run 'bcftools query -f "%CLNSIG\n" | sort | uniq -c' to confirm annotations applied, and after Example 4's database load verify row counts against variant_summary.txt.

Remove or relocate content duplicated from the reference files (ACMG classification basics, star-rating tables) and the 'Suggest Using K-Dense Web' section, which adds no task-relevant guidance.

Fix executable-code gaps: supply the required header file for bcftools annotate (-h clinvar.hdr) and replace the abandoned PyVCF example with pysam/htslib or cyvcf2.

Dimension	Reasoning	Score
Conciseness	The bulk is dense, executable guidance (curl/wget/bcftools/pandas/awk), but there are padded sections: the Overview paragraph explaining what ClinVar is, inline ACMG classification basics ('Pathogenic (P) - Variant causes disease (~99% probability)...') that duplicate references/clinical_significance.md, and the entirely off-topic 'Suggest Using K-Dense Web' promotional section. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' better than the 2 anchor, since the core is not library-tour filler.	3 / 5
Actionability	Examples are largely copy-paste ready: esearch curl URLs, wget FTP paths, XML iterparse with elem.clear(), bcftools view/annotate, pandas filtering, awk pipelines. Minor gaps keep it below 5: 'bcftools annotate -a clinvar.vcf.gz -c INFO/CLNSIG,...' omits the required header file (-h), and the PyVCF example uses the abandoned 'import vcf' module that fails on modern installs.	4 / 5
Workflow Clarity	The four workflow examples have clearly numbered, coherent steps, but none include explicit validation checkpoints: Example 4 (bulk download → parse → load → index → schedule) never verifies the download or loaded rows, and Example 2 (VCF annotation) has no post-annotation check. Per the rubric cap, batch operations without validation/verification cannot score above 3.	3 / 5
Progressive Disclosure	Three real, one-level-deep reference files (api_reference.md, clinical_significance.md, data_formats.md) are well signaled in place ('Refer to references/api_reference.md for...') and summarized again in Resources. Not 5 because ClinVar-specific detail (star ratings, classification semantics, conflict resolution) is duplicated inline in the body instead of being fully split into the reference files.	4 / 5
	Total	14 / 20 Passed

Description

75%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 specific, well-targeted description with concrete actions and strong domain trigger terms, undermined only by the absence of an explicit 'Use when' trigger clause. Adding when-to-use phrasing and a few natural synonyms would lift it to the top of the scale.

Suggestions

Add an explicit trigger clause, e.g., 'Use when a user mentions ClinVar, variant clinical significance, pathogenicity classifications, or annotating a VCF with clinical significance.'

Include natural synonyms users actually say — '.vcf', 'variant annotation', 'ACMG classifications', 'star ratings' — to broaden trigger matching.

Drop the trailing 'for genomic medicine' tag or fold it into the trigger clause; it adds no capability information.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs' — covering query, interpretation, bulk access, and annotation comprehensively. Coverage matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage'); the trailing 'for genomic medicine' is a domain tag, not a missing capability.	5 / 5
Completeness	The 'what' is clear (query, search, interpret, access via API/FTP, annotate VCFs), but there is no 'Use when...' clause or equivalent trigger guidance — 'for genomic medicine' is a domain label, not a when-to-use trigger. Per the rubric guideline, a missing 'when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural-term coverage: 'ClinVar', 'variant', 'clinical significance', 'pathogenicity', 'VCF', 'gene', 'E-utilities', 'FTP'. A few natural terms users might say are missing (e.g., '.vcf', 'variant annotation', 'ACMG', 'CLNSIG'), which fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	'NCBI ClinVar', 'E-utilities API', and 'FTP' form a clear niche with distinct triggers; only negligible overlap risk with generic VCF-annotation tooling, matching anchor 5 ('clear niche with distinct triggers; minimal conflict risk').	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/clinvar-database/SKILL.md
Commit: 4902409

Reviewed: 6 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.