What is prs-trait-interpretation?

A procedure for interpreting polygenic risk scores for one trait from personal genome files in VCF format. It narrows many model results into a shortlist while checking genetic ancestry, because ancestry-mismatched reference groups can make percentiles misleading.

Use it to resolve a trait, inspect genome metadata, calculate or compare scores across genomes, and produce a cautious, interpretable genetic-risk summary.

A raw score panel can contain conflicting percentiles that reflect reference-panel coverage rather than a clear genetic signal. The procedure keeps uncertainty and ancestry mismatches visible instead of presenting one score as definitive.

How dna-seq/just-prs-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dna-seq/just-prs-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dna-seq/just-prs-mcp/main/.agents/skills/prs-trait-interpretation/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dna-seq/just-prs-mcp

Made for: Claude Code.

Or install just-prs, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dna-seq/just-prs-mcp/prs-trait-interpretation/github.svg)](https://agentmods.dev/skills/dna-seq/just-prs-mcp/prs-trait-interpretation)

Your own site

<a href="https://agentmods.dev/skills/dna-seq/just-prs-mcp/prs-trait-interpretation"><img src="https://agentmods.dev/badge/skills/dna-seq/just-prs-mcp/prs-trait-interpretation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dna-seq/just-prs-mcp/prs-trait-interpretation"><img src="https://agentmods.dev/badge/skills/dna-seq/just-prs-mcp/prs-trait-interpretation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,239 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00109	$0.01239
Opus 5	$0.00055	$0.00620
Sonnet 5	$0.00022	$0.00248
Haiku 4.5	$0.00011	$0.00124

Measured 9d ago against content hash e49072eba436, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prs-trait-interpretation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/prs-trait-interpretation/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRS trait interpretation

A raw by-trait PRS panel can be 100+ scores whose percentiles for the same person on the same trait span the full 0–100 range — mostly a coverage/ancestry artifact, not real signal. Do not dump the panel. Trim it to a trustworthy shortlist and report the consensus. When several genomes are in play, compare medians (via compare_genomes), not a single "best" model.

The canonical methodology is the server-side MCP prompt interpret_prs_for_trait. The reusable write-up text is build_prs_prompt (same output as prs prompt / the UI Ask-AI buttons).

The recipe

Resolve the trait. search_traits / trait_info → the ontology ID (EFO or MONDO). If several match, confirm which one with the user.
Confirm ancestry. Percentiles are only meaningful when the reference panel matches each person's genetic ancestry. Call vcf_metainfo first — it detects WGS/array/gVCF + genome build and infers the sample's super-population, returning recommended_superpopulation and recommended_reference_restoration. Or pass superpopulation="auto" to compute_prs_by_trait to infer ancestry once per genome. Flag mismatches; never hide them.
By-trait computation. Always a list — one genome is fine: compute_prs_by_trait(trait_id, samples=["Anton=<path>"], superpopulation=<ancestry or "auto">). Several genomes: samples=["Anton=<path>", "Livia=<path>"]. interpret defaults to True. profile defaults to "all" (every associated score). Pass profile="curated" only if the user asks for a shortlist. reference_restoration defaults to "auto" (recovers absent-hom-ref coverage on WGS/array). Read each report's filter_summary / n_filtered.
Compare when there are 2+ genomes. Pass the returned result_paths to compare_genomes. The headline number is the median in-scope percentile. Do not declare a winner until you know whether a high percentile is favorable for this trait.
Read shortlist concordance. Do the surviving high-quality models agree? Note weight_mass_coverage (C_wt) and percentile_reliable.
Reusable write-up. build_prs_prompt(result_paths=...) — follow that prompt (or interpret_trait_results). For one PGS ID use kind="score".
State caveats. Coverage, ancestry match, quality tier, and that a PRS is one predisposition factor among many — not a diagnosis. For disease traits with a z-score, call absolute_risk.

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 90 lines · 109 tokens per session scan A e49072eba436

Subscribe to this mod's changes

prs-trait-interpretation is a skill published in the GitHub repository dna-seq/just-prs-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 109 tokens to every session and 1,239 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

just-prs-mcp: Skill for Claude Code