CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/clinvar_database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured, highly actionable command reference with explicit workflows, validation checkpoints, and error-recovery guidance. Its main weaknesses are a factual contradiction on the search retmax default, a malformed count example, and quadruplicated API-key instructions.

Suggestions

Resolve the retmax contradiction: 'Core Rules' says search 'defaults to --retmax 200' while the search section says 'Default is 0, which means fetch all matching results' — pick one and delete the other.

Consolidate the four repetitions of the NCBI_API_KEY/credentials protocol into a single section and cross-reference it from the other spots, cutting substantial tokens.

Fix the count example so it is a proper multi-line code block like the search examples, and either link references/citation.bib from the body or remove it from the bundle.

DimensionReasoningScore

Conciseness

Mostly efficient operational detail, but the NCBI_API_KEY/credentials instruction is repeated four times (Prerequisites, Core Rules, 'Obtaining and Using an API Key', Common Mistakes) and the Overview briefly explains what ClinVar is — noticeable padding that could be consolidated.

3 / 5

Actionability

Nearly all commands are copy-paste ready with full flags, output schemas, and a concrete dbSNP fallback (`uv run scripts/dbsnp_cli.py resolve-rsid {rsid}`), but the `count` example is malformed into a single line with literal backslashes, and 'Core Rules' contradicts the search docs on the retmax default (200 vs 0/fetch-all).

4 / 5

Workflow Clarity

Clear multi-step sequences with explicit validation checkpoints ('always verify these match to confirm complete retrieval', HGVS cross-checks, single-turn triangulation) and a 429 error-recovery loop, but the contradictory retmax default gives conflicting instructions on a core parameter of the recommended Count-First workflow.

4 / 5

Progressive Disclosure

Good section structure with the bundled script (scripts/clinvar_api.py) clearly signaled and used throughout; however references/citation.bib exists in the bundle but is never referenced in the body, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

70%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 has an explicit 'Use when' trigger clause with strong domain-specific keywords, but it never names ClinVar itself and describes needed objects rather than the concrete actions the skill performs. It is clearly distinguishable within the clinical-variant niche yet has minor overlap risk with adjacent genomics skills.

Suggestions

State the concrete action up front, e.g., 'Query the ClinVar database for clinical significance, pathogenicity classifications (Pathogenic, Likely pathogenic, Benign, VUS), clinician rationales, and 'hard positive' benchmark controls of human genomic variants. Use when...' — this would raise both specificity and completeness.

Include the term 'ClinVar' in the description, since users asking about variant classifications will most often say 'check ClinVar' rather than 'pathogenicity classification'.

Add one or two disambiguating 'do not use' trigger redirects (e.g., 'For allele frequencies use gnomAD') to further reduce overlap with neighboring genomics skills.

DimensionReasoningScore

Specificity

Names concrete topic objects ('clinical significance', 'pathogenicity classifications (e.g., Pathogenic, Benign, VUS)', 'clinical evidence rationales', "'hard positive' benchmark controls") but states no explicit actions — the verbs are only implied by 'Use when needing', so it lands at the domain-plus-concrete-items anchor rather than listing specific actions.

3 / 5

Completeness

The 'when' is fully explicit ('Use when needing clinical significance, pathogenicity classifications...'), but the 'what' is only weakly implied through the object list rather than stated as concrete capabilities (e.g., 'Query the ClinVar database for...').

4 / 5

Trigger Term Quality

Strong natural keyword coverage with synonyms domain users would actually say ('clinical significance', 'Pathogenic', 'Benign', 'VUS', 'human genomic variants'), but 'ClinVar' — the single most natural trigger term — is absent from the description.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive niche terms (VUS, pathogenicity classifications, 'hard positive' benchmark controls) minimize conflict risk, but 'clinical significance' and 'clinical evidence rationales' could overlap with closely related clinical-genomics skills (OMIM, gnomAD).

4 / 5

Total

15

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/dbsnp_cli.py)

Warning

Total

14

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/clinvar_database/SKILL.md

Reviewed

Table of Contents

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.