CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/clinvar-database/SKILL.md
SKILL.md
Quality
Evals
Security

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 well-structured, actionable body with real one-level-deep references and executable examples for the main workflows. Its weaknesses are duplicated content that inflates token cost and missing validation/verification checkpoints in the batch and annotation workflows.

Suggestions

Add validation steps to the batch workflows — verify downloaded files (checksums/file size) and confirm annotation applied (e.g., count annotated records with `bcftools query -f '%CLNSIG' | grep -c Pathogenic`) — to lift workflow clarity past the batch-operation cap.

Deduplicate content: star ratings, rate limits, and FTP file listings each appear in multiple sections and partly duplicate the reference files; keep the body lean and defer detail to the references.

Fix the first `bcftools annotate` example (it lacks the header lines/-c column spec needed to run as written) and replace the deprecated PyVCF example with a maintained library (e.g., cyvcf2).

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete examples, but includes unnecessary repetition — star ratings and API rate limits each appear in multiple sections, and the Resources section re-describes reference files already pointed to inline — so it fits the 'mostly efficient but could be tightened' anchor rather than the lean 4-anchor.

3 / 5

Actionability

Concrete, mostly copy-paste-ready curl, wget, bcftools, pandas, and awk examples cover the common cases, but minor gaps exist: the first `bcftools annotate` example omits header specification, the awk example uses unexplained hardcoded column indices ($7/$13), and PyVCF is a deprecated library — matching 'mostly executable with minor gaps'.

4 / 5

Workflow Clarity

Workflow examples present clear numbered sequences (e.g., Example 2's download → annotate → filter), but batch operations such as the bulk download/local-database build (Example 4) and VCF annotation lack validation or verification steps (no integrity checks, no confirmation the annotation applied), so workflow clarity is capped at 3 per the batch-operations guideline.

3 / 5

Progressive Disclosure

The body is a well-organized overview that clearly signals three real, one-level-deep references at the point of use ("Refer to `references/api_reference.md`..."), matching 'good structure, references mostly clear'. Minor gaps: some FTP directory and format detail duplicates what belongs solely in `data_formats.md`.

4 / 5

Total

14

/

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.

A strong, specific third-person description that clearly conveys what the skill does with concrete actions and a distinct database niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and slightly weakens trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g., "Use when a user mentions ClinVar, variant clinical significance, pathogenicity classifications, or needs to annotate a VCF with clinical significance."

Include natural synonyms and extensions users would say — "variant annotation", "clinical genetics", "VCF annotation", ".vcf" — to strengthen trigger-term coverage.

Mention bulk data download/use cases (FTP, local database builds) in the description to round out capability coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs" — with only minor coverage gaps (e.g., no mention of bulk downloads or submission workflows), matching the 'several specific actions with minor gaps' anchor rather than the comprehensive 5-anchor.

4 / 5

Completeness

The 'what' is clear (query, interpret, access, annotate), but there is no 'Use when...' clause or equivalent explicit trigger guidance — "for genomic medicine" only weakly implies when to use it — so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural keywords like "ClinVar", "variant", "clinical significance", "pathogenicity", "VCF", and "E-utilities" are present, but common variations users would say ("variant annotation", "clinical genetics", "variant classification") and file extensions are missing, fitting the 'good coverage with a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

It explicitly names a distinct resource ("NCBI ClinVar") with domain-specific triggers (pathogenicity, VCF, E-utilities) that other skills would not naturally fire on, giving it a clear niche with minimal conflict risk.

5 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
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.