variant-annotation

Query and annotate gene variants from ClinVar and dbSNP databases. Trigger when: - User provides a variant identifier (rsID, HGVS notation, genomic coordinates) and asks about clinical significance - User mentions "ClinVar", "dbSNP", "variant annotation", "pathogenicity", "clinical significance" - User wants to know if a mutation is pathogenic, benign, or of uncertain significance - User provides VCF content or variant data requiring interpretation - Input: variant ID (rs12345), HGVS notation (NM_007294.3:c.5096G>A), or genomic coordinates (chr17:43094692:G>A) - Output: clinical significance, ACMG classification, allele frequency, disease associations

Install with Tessl CLI

npx tessl i github:aipoch/medical-research-skills --skill variant-annotation

What are skills?

Review — 82%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

98%

26%

Hereditary Cancer Variant Annotation

Python API usage and output structure

Criteria

Without context

With context

Correct import path

100%

VariantAnnotator instantiation

100%

batch_query usage

100%

Multiple input format handling

100%

Output saved to JSON file

100%

ACMG fields present in output

100%

83%

clinical_significance field

100%

disease_associations present

100%

interpretation_summary present

100%

Rate limiting respected

100%

No hardcoded API credentials

100%

Without context: $0.8128 · 3m 52s · 25 turns · 32 in / 15,243 out tokens

With context: $0.8009 · 2m 10s · 31 turns · 8,301 in / 6,976 out tokens

100%

37%

Population Screening Variant Annotation Pipeline

Batch variant processing and CLI

Criteria

Without context

With context

Uses --file flag

100%

Uses --output flag

100%

Output file produced

100%

Shell script executable

100%

Rate limiting addressed

100%

Dependency install step

100%

VCF-style variants accepted

100%

JSON output format

70%

100%

No hardcoded API credentials

100%

Correct script path

100%

Without context: $1.0240 · 4m 33s · 40 turns · 45 in / 17,470 out tokens

With context: $0.7685 · 2m 15s · 29 turns · 8,301 in / 6,050 out tokens

100%

ACMG Variant Classification Report Generator

ACMG scoring logic and classification

Criteria

Without context

With context

PS criteria weight

100%

PM criteria weight

100%

PP criteria weight

100%

BA1 stand-alone weight

100%

BS criteria weight

100%

BP criteria weight

100%

Pathogenic threshold

100%

Benign stand-alone threshold

100%

VUS threshold

100%

Likely Benign threshold

100%

Likely Pathogenic threshold

100%

Numeric score in output

100%

Without context: $0.3452 · 1m 32s · 15 turns · 22 in / 6,026 out tokens

With context: $0.7566 · 2m 16s · 25 turns · 2,568 in / 7,690 out tokens

Evaluated: about 11 hours ago
Agent: Claude Code

Table of Contents

Hereditary Cancer Variant Annotation Population Screening Variant Annotation Pipeline ACMG Variant Classification Report Generator

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.