メニュー
Synthesize population, clinical, functional, regulatory, expression, and cohort evidence for a genomic variant. Use for research interpretation of rsIDs or genomic alleles, not patient-specific diagnosis or treatment.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/eightmm/codex-science --skill variant-evidence-synthesisコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Execute auditable quantitative research across preregistered study design, statistical inference, numerical verification, dimensional analysis, uncertainty propagation, counterexample search, and formal proof. Use when a scientific or mathematical question needs actual computation and machine-readable evidence rather than only explanation.
Compare finite actions under uncertainty with explicit states, loss, utility or risk-neutral payoff, priors, experiment likelihoods, and a declared decision criterion. Use for Bayes risk, expected utility or payoff, pure-action minimax, minimax regret, dominance, posterior decision policies, EVPI/EVSI, experiment-cost decisions, and prior-threshold sensitivity; do not use for ordinary statistical testing, causal identification, strategic games, or MDP/POMDP/RL planning.
Compare finite actions under uncertainty with explicit states, loss, utility or risk-neutral payoff, priors, experiment likelihoods, and a declared decision criterion. Use for Bayes risk, expected utility or payoff, pure-action minimax, minimax regret, dominance, posterior decision policies, EVPI/EVSI, experiment-cost decisions, and prior-threshold sensitivity; do not use for ordinary statistical testing, causal identification, strategic games, or MDP/POMDP/RL planning.
| name | variant-evidence-synthesis |
| description | Synthesize population, clinical, functional, regulatory, expression, and cohort evidence for a genomic variant. Use for research interpretation of rsIDs or genomic alleles, not patient-specific diagnosis or treatment. |
| license | MIT |
Define assembly, normalized allele, transcript or regulatory context, phenotype, population, evidence cutoff, intended research decision, and non-goals; keep multiallelic records and allele-specific claims separate.
Retrieve population frequency and constraint, clinical assertions, predicted molecular consequences, curated associations, regulatory and expression evidence, and cross-cohort PheWAS only when relevant; preserve effect allele, strand, ancestry, phenotype definition, model, sample size, uncertainty, correction scope, source release, and assertion review status.
Triangulate independent lanes rather than counting portals, test direction and allele alignment, distinguish primary evidence from propagated summaries, and reconcile conflicts with $cx-biomedical-evidence-reconciliation.
Return a claim-evidence matrix, allele-alignment audit, cohort comparison, conflicts, missing evidence, confidence by claim, and falsifiable functional or replication follow-ups.
Do not equate association, in-silico effect, a ClinVar assertion, one cohort, or regulatory overlap with causality or clinical actionability; explicitly mark ancestry, ascertainment, LD, transcript, and tissue limitations.
Store exact queries, normalized records, source snapshots, and evidence tables with $science-provenance; run $science-review before reporting an interpretation.