soul2dna
Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping
Best use case
soul2dna is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping
Teams using soul2dna should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/soul2dna/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How soul2dna Compares
| Feature / Agent | soul2dna | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 🧬 Soul2DNA Compiler
## Purpose
Compile SOUL.md character profiles into synthetic diploid genomes. Each soul file
describes a historical or fictional figure with trait scores (0.0 to 1.0). The
compiler maps these scores to alleles at defined loci using additive, dominant, or
recessive inheritance models, producing a `.genome.json` file per character.
## How It Works
1. **Parse SOUL.md** files from `GENOMEBOOK/DATA/SOULS/` extracting identity
metadata (name, sex, ancestry, domain, era) and trait scores.
2. **Load trait registry** (`GENOMEBOOK/DATA/trait_registry.json`) which defines
loci, alleles, chromosomal positions, dominance models, and effect sizes for
each trait.
3. **Assign genotypes** at each locus based on trait score thresholds:
- Additive: <0.33 ref/ref, 0.33-0.66 ref/alt, >0.66 alt/alt
- Dominant: <0.40 ref/ref, 0.40-0.75 ref/alt, >0.75 alt/alt
- Recessive: <0.50 ref/ref, 0.50-0.80 ref/alt, >0.80 alt/alt
4. **Write genome** as JSON with full locus detail, trait scores, and metadata.
## Input
- `GENOMEBOOK/DATA/SOULS/*.soul.md` (20 historical figures)
- `GENOMEBOOK/DATA/trait_registry.json`
## Output
- `GENOMEBOOK/DATA/GENOMES/<name>-g0.genome.json` per character
## CLI Usage
```bash
# Compile all souls to genomes
python skills/soul2dna/soul2dna.py
# Demo mode (shows summary without writing files)
python skills/soul2dna/soul2dna.py --demo
```
## Output Format
Each `.genome.json` contains:
```json
{
"id": "einstein-g0",
"name": "Albert Einstein",
"sex": "Male",
"sex_chromosomes": "XY",
"ancestry": "...",
"generation": 0,
"parents": [null, null],
"loci": { "<locus_id>": { "chromosome": "...", "alleles": ["A","G"], ... } },
"trait_scores": { "curiosity": 0.95, ... }
}
```Related Skills
wes-clinical-report-es
Generates professional clinical PDF reports in Spanish from WES (Whole Exome Sequencing) data with clinical interpretation, pharmacogenomic alerts, and follow-up recommendations.
wes-clinical-report-en
Generates professional clinical PDF reports in English from WES (Whole Exome Sequencing) data with clinical interpretation summary, pharmacogenomic alerts, and follow-up recommendations.
vcf-annotator
Annotate VCF variants with VEP, ClinVar, gnomAD frequencies, and ancestry-aware context. Generates prioritised variant reports.
variant-annotation
Annotate VCF variants with Ensembl VEP REST, ClinVar significance, gnomAD/population frequency context, and prioritized variant ranking.
ukb-navigator
Semantic search across UK Biobank's 12,000+ data fields and publications — find the right variables for your research question.
target-validation-scorer
Evidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns
struct-predictor
Protein structure prediction with Boltz-2. Accepts YAML inputs (single protein or multi-chain complex), runs boltz predict, extracts per-residue pLDDT and PAE confidence, and writes a markdown report with figures.
seq-wrangler
Sequence QC, alignment, and BAM processing. Wraps FastQC, BWA/Bowtie2, SAMtools for automated read-to-BAM pipelines.
scrna-orchestrator
Local Scanpy pipeline for single-cell RNA-seq QC, optional doublet detection, clustering, marker discovery, optional CellTypist annotation, optional latent downstream mode from integrated.h5ad/X_scvi, and optional dataset-level plus within-cluster contrastive marker analysis from raw-count .h5ad or 10x Matrix Market input.
scrna-embedding
Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated AnnData export for downstream latent analysis.
rnaseq-de
Differential expression analysis for bulk RNA-seq and pseudo-bulk count matrices with QC, PCA, and contrast testing.
repro-enforcer
Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.