clinvar-database

Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls for human genomic variants.

Quality

76%

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 ./skills/clinvar_database/SKILL.md

Quality

Content

75%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 thorough, highly actionable reference with executable commands, clear workflows, and useful validation/error-recovery guidance. The main drags are repetition (the credentials protocol appears three times) and a dangling `citation.bib` bundle file that the body never points to.

Suggestions

Consolidate the NCBI_API_KEY / safe-credentials protocol into a single section and reference it from Prerequisites and Core Rules instead of repeating the full instructions three times.

Reference `references/citation.bib` from the body (e.g. in Overview or a Citations section) so the bundle file is discoverable and not orphaned.

Inline the "verify total_count == fetched_count" check as an explicit numbered validation step inside the Count-First workflow rather than only mentioning it in Best Practices.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material, but the safe-credentials NCBI_API_KEY instruction is repeated three times (Prerequisites, Core Rules, Obtaining and Using an API Key), the Overview explains what ClinVar is (which Claude already knows), and several defaults are restated in multiple sections — tightening would remove noticeable padding.	3 / 5
Actionability	Every subcommand has copy-paste-ready `uv run scripts/clinvar_api.py …` invocations with concrete queries, full argument tables, and explicit output schemas covering the common search/count/summary/evidence cases.	5 / 5
Workflow Clarity	The Count-First and Triangulation workflows are clearly sequenced with commands, and the 429 → credentials → retry path is an explicit error-recovery feedback loop; however the "verify total_count == fetched_count" checkpoint and the retmax-completeness check live in Best Practices rather than inline as numbered validation steps within the workflows.	4 / 5
Progressive Disclosure	Section structure is good (Prerequisites, When to Use, Quick Start, Utility Scripts, Workflows, Best Practices, Common Mistakes) and `scripts/clinvar_api.py` is clearly referenced and exists, but `references/citation.bib` is present in the bundle yet never referenced or signaled in the body, and the detailed per-command output schemas could arguably live in a reference file.	4 / 5
	Total	16 / 20 Passed

Description

78%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 focused, trigger-rich description that clearly carves out the ClinVar clinical-classification niche with natural domain terms. Its main limitation is that the "what" is folded into the "Use when…" list rather than standing as an explicit action statement, and a few obvious synonyms are missing.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — "clinical significance", "pathogenicity classifications (e.g., Pathogenic, Benign, VUS)", "clinical evidence rationales", "hard positive benchmark controls" — but they are all retrieval-shaped noun phrases with a single "needing" verb rather than diverse distinct actions, so it falls just short of comprehensive.	4 / 5
Completeness	An explicit "Use when…" clause answers "when" with concrete trigger phrases, and the enumerated needs imply "what", but the "what" is merged into the when-list rather than stated as a standalone action (e.g. "Query ClinVar for…"), so it is not the cleanest dual statement.	4 / 5
Trigger Term Quality	Natural clinical-genomics terms a user would say ("Pathogenic", "Benign", "VUS", "clinical significance", "human genomic variants") are well covered, but obvious synonyms like "ClinVar" itself and "variant interpretation" are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The ClinVar niche — clinical significance and pathogenicity labels for human genomic variants — is sharply distinct from adjacent skills (gnomAD, dbSNP, OMIM) with triggers that would not fire for the wrong skill.	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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: google-deepmind/science-skills
Path: skills/clinvar_database/SKILL.md
Commit: 6883275

Reviewed: 4 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.