dbsnp-database

Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).

Quality

88%

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

77%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.

A thorough, highly actionable CLI skill with excellent executable examples and well-sequenced workflows. It loses points for repeated content across sections and for leaving bundle reference files unlinked from the body.

Suggestions

Dedupe the recurring guidance — keep the search-region-vs-resolve-variant caution, the --full warning, and the X/Y→23/24 rule in one canonical place and reference it elsewhere rather than restating each 2–3 times.

Link references/api-notes.md (and citation.bib) from the body — e.g. add a short '## Reference material' section signaling them — so the one-level-deep bundle is discoverable and the Commands section can stay an overview.

Consider moving the full per-command argument tables into a reference file and keeping SKILL.md as a concise command-selection + quick-start overview.

Dimension	Reasoning	Score
Conciseness	Accurate and free of irrelevant background, but ~350 lines with notable repetition — the search-region-vs-resolve-variant caution, the --full payload warning, and the X/Y→23/24 rule each appear two to three times across Core Rules, Commands, and Common Mistakes — so it is not fully lean.	2 / 3
Actionability	Every subcommand ships copy-paste-ready 'uv run scripts/dbsnp_cli.py ...' invocations with positional args, flags, defaults, and concrete output JSON shapes (e.g. {"rsids": [...]}).	3 / 3
Workflow Clarity	Sequenced Typical Workflows with numbered Step 1/Step 2 stages, a command-selection guide for first-try routing, and explicit auto-assembly-fallback plus troubleshooting with 'DO NOT RETRY' guidance; these are read-only queries so the destructive-ops validation cap does not apply.	3 / 3
Progressive Disclosure	The body correctly points to the real scripts/dbsnp_cli.py and the uv/credentials skills, but references/api-notes.md and references/citation.bib are never linked or signaled from the body, and the Commands section is a fairly monolithic inline reference rather than split with clear one-level navigation.	2 / 3
	Total	10 / 12 Passed

Description

100%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.

A tightly scoped, action-oriented description that names concrete capabilities and explicit triggers with strong domain keyword coverage. It clearly distinguishes dbSNP lookups from adjacent variant-database skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'look up, map, and search for short genetic variants', 'Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings', and enumerated return fields (variant type, gene associations, clinical significance, allele frequencies, genomic coordinates).	3 / 3
Completeness	Explicitly answers both what ('Resolves between rsIDs... returns variant type, gene associations...') and when ('Use when you want to look up, map, and search for short genetic variants'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural domain terms users would say — 'SNPs, indels', 'rsIDs', 'genomic coordinates in VCF format', 'HGVS strings', 'allele frequencies', 'GRCh38' — across the common ways a user would phrase these needs.	3 / 3
Distinctiveness Conflict Risk	Scoped to NCBI's dbSNP with concrete identifiers (rsID, VCF, HGVS) forming a clear niche unlikely to fire for sibling skills like clinvar, gnomad, or alphafold.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/dbsnp_database/SKILL.md
Commit: 0b42509

Reviewed: 8 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.