Onekgpd gives Claude Code a way to ask individual-level questions of the 1000 Genomes Project cohort: 3,202 whole-genome-sequenced people on GRCh38. You can pull the variants carried in a gene or region, find which individuals carry variants matching criteria, check homozygous-reference status at a position, or compute kinship between two named samples. Results come back with 1000 Genomes and gnomAD v4.1 allele frequencies, AlphaMissense scores, and HGVSp annotations. The docs are strict about one thing worth knowing up front: resolve gene coordinates to GRCh38 from an authoritative source before querying, because a misplaced region returns results for the wrong place with no error. Run the count command before selecting, since large result sets get heavy fast.
- skills.sh installs
- 1.2K
- GitHub stars
- 56.6K
- last updated
- Jul 31, 2026
Install
$ npx -y skills add K-Dense-AI/scientific-agent-skills --skill onekgpd --agent claude-codeInstalls into .claude/skills of the current project.
Files
OneKGPd: Individual-Level Queries over the 1000 Genomes Project
Scope
This skill queries the 1000 Genomes Project dataset — the extended high-coverage cohort
of 3,202 whole-genome-sequenced individuals, on the GRCh38 assembly. All results
are drawn from this cohort, and sample names returned by the skill (for example
HG00096 or NA21130) identify its participants.
Queries resolve against the cohort's per-individual genotype data. This supports two complementary classes of question: selecting variants carried within a region (across the whole cohort or within a specified set of individuals), and selecting the individuals who carry variants matching given criteria. Variant selection can be filtered by allele frequency, predicted consequence, clinical significance, AlphaMissense classification, and the other annotation axes listed below. Relatedness between two named individuals is also available.
The genotype state in which a variant is carried — heterozygous or homozygous — is a criterion that queries may specify; results are returned as variants or as sample names, not as raw genotypes.
When to Use
Use this skill when you need to:
Sponsors
Details
- Repository
- github.com/K-Dense-AI/scientific-agent-skills
- Categories
- AI & Agent Building, Data Science & ML
- License
- MIT
- First seen
- Aug 2, 2026
More from K-Dense-AI/scientific-agent-skills
All 17- Uncertainty And Units1.1K
- Analytical Method Validation1.1K
- Iso Standards Readiness1.1K
- Genomic Coordinates1.1K
- Ontology Term Resolution1.1K
- Openpiv1.1K
- Pathogen Variant Surveillance1.1K
- Pkpd Modeling1.1K
- Bids1.6K
- Liteparse1.6K
- Pacsomatic1.6K
- Experimental Design1.5K
- Bulk Rnaseq1.5K
- Pathway Enrichment1.5K
- Nextflow1.5K
- Statistical Power1.5K
