New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Polygenic Risk Score

by lamm-mit in lamm-mit/scienceclaw

ToolUniverse workflow — Polygenic Risk Score. An agent skill from lamm-mit/scienceclaw.

Apache-2.0Auto-check passedResearch & Science

Install Polygenic Risk Score

skills CLI
$ npx skills add lamm-mit/scienceclaw --skill polygenic-risk-score -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lamm-mit/scienceclaw polygenic-risk-score --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/polygenic-risk-score .claude/skills/polygenic-risk-score && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
polygenic-risk-score
GitHub stars
244
Token cost
~3.7k tokens
SKILL.md length
1,704 words
Files
3 (incl. scripts)
Skills in repo
86
Repo updated
First seen
Licence
Apache-2.0

At a glance

ToolUniverse workflow — Polygenic Risk Score. An agent skill from lamm-mit/scienceclaw.

  • Works in 6 steps: Trait Selection → Association Collection → Effect Size Extraction → …
  • Tasks that involve Bioinformatics
  • SKILL.md covers Overview, Methodology, Data Sources and Key Concepts, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Polygenic Risk Score is an agent skill from lamm-mit/scienceclaw. ToolUniverse workflow — Polygenic Risk Score

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/run.py`).

It sits in Research & Science, covering Bioinformatics. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Bioinformatics

Example prompts

  • “/polygenic-risk-score”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Trait Selection
  2. Association Collection
  3. Effect Size Extraction
  4. SNP Filtering
  5. Score Calculation
  6. Risk Interpretation

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • pgscatalog.org
    • ldsc.broadinstitute.org
    • prsice.info
    • ebi.ac.uk

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Polygenic Risk Score loads about 3.7k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 1,704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 1,704 words, ~3,714 tokens.

Download SKILL.mdSave it as .claude/skills/polygenic-risk-score/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
polygenic-risk-score
description
ToolUniverse workflow — Polygenic Risk Score
source
https://github.com/mims-harvard/ToolUniverse/tree/main/skills/tooluniverse-polygenic-risk-score

name: tooluniverse-polygenic-risk-score description: Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Calculates genetic risk profiles, interprets PRS percentiles, and assesses disease predisposition across conditions including type 2 diabetes, coronary artery disease, and Alzheimer's disease. Use when asked to calculate polygenic risk scores, interpret genetic risk for complex diseases, build custom PRS from GWAS data, or answer questions like "What is my genetic predisposition to breast cancer?"

Polygenic Risk Score (PRS) Builder

Build and interpret polygenic risk scores for complex diseases using genome-wide association study (GWAS) data.

Overview

Use Cases:

  • "Calculate my genetic risk for type 2 diabetes"
  • "Build a polygenic risk score for coronary artery disease"
  • "What's my genetic predisposition to Alzheimer's disease?"
  • "Interpret my PRS percentile for breast cancer risk"

What This Skill Does:

  • Extracts genome-wide significant variants (p < 5e-8) from GWAS Catalog
  • Builds weighted PRS models using effect sizes (beta coefficients)
  • Calculates individual risk scores from genotype data
  • Interprets PRS as population percentiles and risk categories

What This Skill Does NOT Do:

  • Diagnose disease (PRS is probabilistic, not deterministic)
  • Replace clinical assessment or genetic counseling
  • Account for non-genetic factors (lifestyle, environment)
  • Provide treatment recommendations

Methodology

PRS Calculation Formula

A polygenic risk score is calculated as a weighted sum across genetic variants:

PRS = Σ (dosage_i × effect_size_i)

Where:

  • dosage_i: Number of effect alleles at SNP i (0, 1, or 2)
  • effect_size_i: Beta coefficient or log(odds ratio) from GWAS
Standardization

Raw PRS is standardized to z-scores for interpretation:

z-score = (PRS - population_mean) / population_std

This allows comparison to population distribution and percentile calculation.

Significance Thresholds
  • Genome-wide significance: p < 5×10⁻⁸ (default threshold)
  • This corrects for ~1 million independent tests across the genome
  • Relaxed thresholds (e.g., p < 1×10⁻⁵) can include more SNPs but may add noise
Effect Size Handling
  • Continuous traits (e.g., height, BMI): Beta coefficient (units of trait per allele)
  • Binary traits (e.g., disease): Odds ratio converted to log-odds (beta = ln(OR))
  • Missing effect sizes or non-significant SNPs are excluded

Data Sources

This skill uses ToolUniverse GWAS tools to query:

  1. GWAS Catalog (EMBL-EBI)

    • Curated GWAS associations
    • 5000+ studies, millions of variants
    • Tools: gwas_get_associations_for_trait, gwas_get_snp_by_id

  2. Open Targets Genetics

    • Integrated genetics platform
    • Fine-mapped credible sets
    • Tools: OpenTargets_search_gwas_studies_by_disease, OpenTargets_get_variant_info

Key Concepts

Polygenic Risk Scores (PRS)

Polygenic risk scores aggregate the effects of many genetic variants to estimate an individual's genetic predisposition to a trait or disease. Unlike Mendelian diseases caused by single mutations, complex diseases involve hundreds to thousands of variants, each with small effects.

Key Properties:

  • Continuous distribution: PRS forms a bell curve in populations
  • Relative risk: Compares individual to population average
  • Probabilistic: High PRS doesn't guarantee disease, low PRS doesn't guarantee protection
  • Ancestry-specific: PRS accuracy depends on matching GWAS and target ancestry
GWAS (Genome-Wide Association Studies)

GWAS compare allele frequencies between cases and controls (or correlate with trait values) across millions of SNPs to identify disease-associated variants.

Study Design:

  • Discovery cohort: Initial identification of associations
  • Replication cohort: Validation in independent samples
  • Sample size: Larger studies detect smaller effects (power ∝ √N)
  • Multiple testing correction: Bonferroni-type correction for ~1M tests
Effect Sizes and Odds Ratios
  • Beta (β): Change in trait per copy of effect allele
    • Example: β = 0.5 kg/m² means each allele increases BMI by 0.5 units
  • Odds Ratio (OR): Multiplicative change in disease odds
    • OR = 1.5 means 50% increased odds per allele
    • Convert to beta: β = ln(OR)
Linkage Disequilibrium (LD) and Clumping

Nearby variants are often inherited together (LD). To avoid double-counting:

  • LD clumping: Select independent variants (r² < 0.1 within 1 Mb windows)
  • Fine-mapping: Statistical methods to identify causal variants
  • This skill uses raw associations; production PRS should include LD pruning
Population Stratification

GWAS and PRS are most accurate when ancestries match:

  • Population structure: Different ancestries have different allele frequencies
  • Transferability: European-trained PRS perform worse in non-European populations
  • Solution: Train PRS on diverse cohorts or use ancestry-matched references

Applications

Clinical Risk Assessment

PRS can stratify individuals for:

  • Screening programs: Target high-risk individuals (e.g., mammography, colonoscopy)
  • Prevention strategies: Lifestyle interventions for high genetic risk
  • Drug response: Pharmacogenomics based on metabolism genes

Example: Khera et al. (2018) showed PRS identifies 3× more individuals at >3-fold coronary artery disease risk than monogenic mutations.

Research Applications
  • Gene discovery: PRS-based phenome-wide association studies (PheWAS)
  • Genetic correlation: Compare PRS across traits
  • Causal inference: Mendelian randomization using PRS as instruments
  • Simulation studies: Model polygenic architecture
Personal Genomics

Consumer genetic testing (23andMe, Ancestry DNA) provides raw genotypes. Users can:

  • Calculate PRS for traits not reported
  • Compare to published PRS models
  • Understand genetic contribution vs. lifestyle factors

Caution: Personal PRS should not replace medical advice. Results may cause anxiety if not properly contextualized.

Limitations and Considerations

Scientific Limitations

  1. Heritability Gap: PRS explains a fraction of genetic heritability

    • Type 2 diabetes: ~50% heritable, PRS explains ~10-20%
    • Rare variants, epistasis, and gene-environment interactions not captured

  2. Ancestry Bias: Most GWAS are European ancestry

    • PRS accuracy drops in non-European populations
    • Need for diverse cohort recruitment

  3. Winner's Curse: Discovery effect sizes often overestimated

    • Replication studies show smaller effects
    • Meta-analyses provide better estimates

  4. Missing Heritability: Unexplained genetic contribution from:

    • Rare variants not captured by SNP arrays
    • Structural variants (CNVs, inversions)
    • Epigenetic factors
Clinical Limitations

  1. Not Diagnostic: PRS is probabilistic, not deterministic

    • High PRS doesn't mean you will get disease
    • Low PRS doesn't mean you won't get disease

  2. Environmental Factors: Many complex diseases are 50%+ environmental

    • Smoking, diet, exercise, stress, pollution
    • PRS doesn't account for these

  3. Pleiotropy: Same variants affect multiple traits

    • Genetic correlation between diseases
    • Risk for one may protect against another

  4. Actionability: Not all high-risk predictions have interventions

    • Alzheimer's PRS has limited actionability currently
    • Ethical considerations for testing
Ethical Considerations

  1. Privacy: Genetic data is identifiable and permanent

    • Can't be changed like passwords
    • Familial implications (relatives share genetics)

  2. Discrimination: Potential for genetic discrimination

    • GINA protects against health/employment discrimination (US)
    • Life insurance and long-term care not protected

  3. Psychological Impact: Knowledge of high risk can cause anxiety

    • Need for genetic counseling
    • Risk communication training

  4. Equity: Ancestry bias means unequal benefits

    • Europeans benefit most from current PRS
    • Exacerbates health disparities

References

Show full SKILL.md (716 more words)Show less
Key Publications

  1. Lambert et al. (2021): "The Polygenic Score Catalog as an open database for reproducibility and systematic evaluation"

  2. Khera et al. (2018): "Genome-wide polygenic scores for common diseases identify individuals with risk equivalent to monogenic mutations"

    • Nature Genetics, 50:1219–1224
    • Demonstrated clinical utility of PRS

  3. Torkamani et al. (2018): "The personal and clinical utility of polygenic risk scores"

    • Nature Reviews Genetics, 19:581–590
    • Comprehensive review of PRS applications

  4. Martin et al. (2019): "Clinical use of current polygenic risk scores may exacerbate health disparities"

    • Nature Genetics, 51:584–591
    • Addresses ancestry bias and equity concerns

  5. Choi et al. (2020): "Tutorial: a guide to performing polygenic risk score analyses"

    • Nature Protocols, 15:2759–2772
    • Practical guide to PRS calculation and evaluation
Resources

Workflow

1. Trait Selection

Identify the disease or trait of interest:

  • Use standard terminology (e.g., "type 2 diabetes" not "T2D")
  • Check GWAS Catalog for availability
  • Verify sufficient GWAS studies exist (n > 10,000 samples ideal)
2. Association Collection

Query GWAS databases for genome-wide significant associations:

python
prs = build_polygenic_risk_score(
    trait="coronary artery disease",
    p_threshold=5e-8,  # Genome-wide significance
    max_snps=1000
)

Considerations:

  • P-value threshold: 5e-8 is conservative, 1e-5 includes more variants
  • LD clumping: Production systems should prune correlated SNPs
  • Study quality: Prefer large meta-analyses over small studies
3. Effect Size Extraction

Extract beta coefficients or odds ratios:

  • Beta for continuous traits (direct use)
  • OR for binary traits (convert to log-odds)
  • Handle missing values (exclude or impute from meta-analysis)
4. SNP Filtering

Quality control filters:

  • MAF filter: Exclude rare variants (MAF < 0.01) for robustness
  • Genotype QC: Remove SNPs with high missingness (> 10%)
  • Hardy-Weinberg: Exclude SNPs violating HWE (p < 1e-6)
  • Ambiguous SNPs: Remove A/T and G/C SNPs (strand ambiguity)
5. Score Calculation

Calculate weighted sum of genotype dosages:

python
result = calculate_personal_prs(
    prs_weights=prs,
    genotypes=my_genotypes,
    population_mean=0.0,
    population_std=1.0
)

Genotype Sources:

  • 23andMe raw data export
  • Ancestry DNA raw data
  • Whole genome sequencing (VCF files)
  • SNP array data (Illumina, Affymetrix)
6. Risk Interpretation

Convert to percentiles and risk categories:

python
result = interpret_prs_percentile(result)
print(f"Percentile: {result.percentile:.1f}%")
print(f"Risk: {result.risk_category}")

Risk Categories:

  • Low risk: < 20th percentile (genetic protection)
  • Average risk: 20-80th percentile (typical genetic predisposition)
  • Elevated risk: 80-95th percentile (moderately increased risk)
  • High risk: > 95th percentile (substantially increased risk)

Clinical Interpretation:

  • Percentiles assume normal distribution
  • Relative risk vs. average (not absolute risk)
  • Combine with family history, clinical risk factors
  • PRS is NOT diagnostic - many high-risk individuals never develop disease

Best Practices

PRS Construction

  1. Use validated PRS from PGS Catalog when available

    • Published models have been externally validated
    • Include LD clumping and ancestry-specific weights

  2. Match ancestries between GWAS and target population

    • European GWAS for European individuals
    • Use multi-ancestry GWAS when available

  3. Include as many SNPs as practical

    • More SNPs = better prediction (up to a point)
    • Balance between coverage and genotyping cost

  4. Consider trait architecture

    • Highly polygenic traits (height, education): benefit from relaxed thresholds
    • Oligogenic traits (IBD, T1D): few large-effect variants, strict thresholds
Clinical Use

  1. Combine with clinical risk scores

    • Add PRS to Framingham Risk Score, QRISK, etc.
    • Integrated models improve prediction

  2. Stratify screening and prevention

    • Intensify surveillance for high PRS (e.g., earlier mammography)
    • Lifestyle interventions for modifiable risk

  3. Provide genetic counseling

    • Explain probabilistic nature of PRS
    • Discuss limitations and uncertainty
    • Address psychological impact

  4. Consider actionability

    • Is there an intervention for high risk?
    • Benefits vs. harms of knowing genetic risk
Research Use

  1. Report methods transparently

    • Document SNP selection criteria
    • Report LD clumping parameters
    • Specify ancestry of GWAS and target

  2. Validate in held-out cohorts

    • Split data: training vs. testing
    • Report out-of-sample prediction accuracy (R², AUC)

  3. Compare to existing PRS

    • Benchmark against PGS Catalog models
    • Report incremental improvement

  4. Test across ancestries

    • Evaluate transferability to non-European populations
    • Report performance stratified by ancestry

Disclaimer

This skill is for educational and research purposes only.

  • Not for clinical diagnosis or treatment decisions
  • Not validated for clinical use - use PGS Catalog models for clinical-grade PRS
  • Requires genetic counseling - interpretation requires expertise
  • Does not account for family history, environment, or lifestyle factors
  • Ancestry-specific - accuracy depends on matching GWAS ancestry

For clinical genetic testing, consult:

  • Genetic counselors (certified by ABGC/ABMGG)
  • Medical geneticists
  • Healthcare providers with genomics training

PRS is a rapidly evolving field. Guidelines and best practices will continue to change as research progresses.

Regulatory Status:

  • FDA does not currently regulate PRS (as of 2024)
  • Some countries restrict direct-to-consumer genetic risk reporting
  • Check local regulations before clinical implementation

© lamm-mit, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/polygenic-risk-score of lamm-mit/scienceclaw.

  • SKILL.md
  • scripts/__pycache__/run.cpython-313.pyc
  • scripts/run.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Polygenic Risk Score next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Polygenic Risk Score compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Polygenic Risk Score this skilllamm-mit/scienceclaw244—~3.7kAutomated safety check: PassApache-2.0
Alphagenome Single Variant Analysisgoogle-deepmind/science-skills3.2k2 repos~3kAutomated safety check: NotesApache-2.0
13C Metabolic Flux AnalysisK-Dense-AI/scientific-agent-skills48k1 repos~3.2kAutomated safety check: PassMIT
Clinvar Databasegoogle-deepmind/science-skills3.2k2 repos~3.9kAutomated safety check: NotesApache-2.0
Metabolic Study Planneraiming-lab/AutoResearchClaw15k—~1.9kAutomated safety check: PassMIT
Dbsnp Databasegoogle-deepmind/science-skills3.2k2 repos~3.4kAutomated safety check: NotesApache-2.0

Similar skills

  • Alphagenome Single Variant Analysis

    google-deepmind/science-skills

    Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.

    3.2k GitHub starsUsed in 2 repos~3k tokens
    Research & ScienceAuto-check: notes

  • 13C Metabolic Flux Analysis

    K-Dense-AI/scientific-agent-skills

    Estimates reaction fluxes inside cells from steady-state carbon-13 labeling data with a bundled mfapy-based solver, and reports which fluxes the data pin down.

    48k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check passed

  • Clinvar Database

    google-deepmind/science-skills

    A skill your agent uses when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls…

    3.2k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes

  • Metabolic Study Planner

    aiming-lab/AutoResearchClaw

    Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

    15k GitHub stars~1.9k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Dbsnp Database

    google-deepmind/science-skills

    A skill your agent uses when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database.

    3.2k GitHub starsUsed in 2 repos~3.4k tokens
    Research & ScienceAuto-check: notes

  • MFA Pipeline Orchestrator

    aiming-lab/AutoResearchClaw

    Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.

    15k GitHub stars~923 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from lamm-mit/scienceclaw

All 86 skills in this repo

  • Fred Economic Data

    lamm-mit/scienceclaw

    Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.

    244 GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed

  • Drug Research

    lamm-mit/scienceclaw

    Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.

    244 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed

  • Imaging Data Commons

    lamm-mit/scienceclaw

    Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

    244 GitHub starsUsed in 5 repos~11k tokens
    Auto-check passed

  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    244 GitHub starsUsed in 4 repos~3.1k tokens
    Auto-check: warnings

  • Infographics

    lamm-mit/scienceclaw

    Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

    244 GitHub starsUsed in 6 repos~4.4k tokens
    Auto-check: notes

  • Disease Research

    lamm-mit/scienceclaw

    Generate comprehensive disease research reports using 100+ ToolUniverse tools.

    244 GitHub stars~946 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Polygenic Risk Score

What does Polygenic Risk Score do?

ToolUniverse workflow — Polygenic Risk Score. An agent skill from lamm-mit/scienceclaw. Polygenic Risk Score is an agent skill from lamm-mit/scienceclaw.

When should I use Polygenic Risk Score?

Polygenic Risk Score fits situations like: tasks that involve Bioinformatics.

How do I install Polygenic Risk Score in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill polygenic-risk-score -a claude-code`. Or copy the skill folder (skills/polygenic-risk-score in lamm-mit/scienceclaw) into .claude/skills/polygenic-risk-score in your project. Claude Code loads it when a task matches its description.

How do I install Polygenic Risk Score in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill polygenic-risk-score -a codex`. Or copy the skill folder (skills/polygenic-risk-score in lamm-mit/scienceclaw) into .agents/skills/polygenic-risk-score in your project. Codex loads it when a task matches its description.

Can I use Polygenic Risk Score in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill polygenic-risk-score -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/polygenic-risk-score, .gemini/skills/polygenic-risk-score, .github/skills/polygenic-risk-score and .opencode/skills/polygenic-risk-score in your project.

What does Polygenic Risk Score need to run?

Going by SKILL.md and its folder, Polygenic Risk Score needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Polygenic Risk Score access the network?

SKILL.md names 4 domains. As links in the text: pgscatalog.org, ldsc.broadinstitute.org, prsice.info and ebi.ac.uk. This is read from the text; nothing was executed.

Is Polygenic Risk Score safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Polygenic Risk Score use?

Polygenic Risk Score is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Polygenic Risk Score use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Polygenic Risk Score?

Skills that share tags, products or a category with Polygenic Risk Score: Alphagenome Single Variant Analysis (google-deepmind/science-skills, 3.2k stars), 13C Metabolic Flux Analysis (K-Dense-AI/scientific-agent-skills, 48k stars), Clinvar Database (google-deepmind/science-skills, 3.2k stars) and Metabolic Study Planner (aiming-lab/AutoResearchClaw, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Polygenic Risk Score?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.