polygenic-risk
Skill4 starsChanged 7 months agoMITView on GitHub
Run optional polygenic or trait-style scoring workflows and label all
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- annotate-variantsSkill
- detect-build-normalizeSkill
- generate-reportSkill
- ingest-vcfSkill
- nextflow-runnerSkill
- pharmacogenomicsSkill
- polygenic-riskSkill
- prioritize-findingsSkill
- query-variantsSkill
- setup-workstationSkill
- annotate-variantsSkill
- detect-build-normalizeSkill
- generate-reportSkill
- ingest-vcfSkill
- nextflow-runnerSkill
- pharmacogenomicsSkill
- prioritize-findingsSkill
- query-variantsSkill
- setup-workstationSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 17
Run optional polygenic or trait-style scoring workflows and label all outputs as probabilistic.
- Distinctive: line 32
Run optional PRS-style analysis without letting probabilistic signals look clinical.
- Distinctive: line 39
Keep PRS outputs in their own file and summary block.
- Very specific: line 43
Never merge PRS output into verified findings.
- Distinctive: line 44
Never present a timeline or certainty.
- Distinctive: line 45
If score portability is unclear, say so explicitly.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Polygenic risk
Run optional polygenic or trait-style scoring workflows and label all outputs as probabilistic. Use only when requested and keep results separate from direct variant findings.
When to use
- the user explicitly requests PRS or broad predisposition scoring
Do not use when
- the user expects diagnosis-like certainty
- the toolchain or reference score set is not available
Expected outputs
prs_scores.jsonprs_notes.md
Goal
Run optional PRS-style analysis without letting probabilistic signals look clinical.
Procedure
- Confirm that the user explicitly wants this class of output.
- Record which score set or method was used.
- Present results as relative or exploratory signals only.
- Keep PRS outputs in their own file and summary block.
Guardrails
- Never merge PRS output into
verifiedfindings. - Never present a timeline or certainty.
- If score portability is unclear, say so explicitly.
References
See references/README.md for durable notes and scripts/ for deterministic helpers.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

