メニュー
Map free-text sequencing-sample metadata to controlled-vocabulary ontology terms. Use this skill whenever labelling a sample's organism, tissue/cell type, disease, or assay from its metadata.
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/nextflow-io/nextflow --skill metadata-ontology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
Format a sequencing or genome-assembly summary as a standardized QC report. Use this skill whenever the user asks for a sequence, assembly, or read-QC summary or verdict.
Format an assembly QC report as the standardized MOD-QA block. Use this skill whenever the user asks for an assembly, sequencing or read-QC report or verdict.
House writing style for this module's reports. Use whenever writing any report text, note or summary.
| name | metadata-ontology |
| description | Map free-text sequencing-sample metadata to controlled-vocabulary ontology terms. Use this skill whenever labelling a sample's organism, tissue/cell type, disease, or assay from its metadata. |
You assign controlled-vocabulary labels to a sequencing sample from its (often messy, free-text) metadata. Follow these rules exactly.
Every facet is either a single term written as label [ONTOLOGY:ID], or the
literal string unknown when the metadata does not evidence it. Never invent an
ID: only use IDs from the tables below (or a NCBITaxon: id when the record
gives an explicit tax_id). If the right term is not in a table, use the
closest listed parent term, or unknown.
Organism (from scientific_name / tax_id):
| term | id |
|---|---|
| Homo sapiens | NCBITaxon:9606 |
| Mus musculus | NCBITaxon:10090 |
| Drosophila melanogaster | NCBITaxon:7227 |
| Saccharomyces cerevisiae | NCBITaxon:4932 |
Tissue / cell type (UBERON tissues, CL cell types):
| term | id |
|---|---|
| B lymphocyte | CL:0000236 |
| epithelial cell | CL:0000066 |
| lung | UBERON:0002048 |
| blood | UBERON:0000178 |
| liver | UBERON:0002107 |
| breast | UBERON:0000310 |
Disease (MONDO):
| term | id |
|---|---|
| lung adenocarcinoma | MONDO:0005097 |
| none | — |
Use none [—] only when the sample is clearly a normal/healthy or engineered
non-disease sample; otherwise unknown.
Assay (functional-genomics assay term):
| term |
|---|
| RNA-seq |
| ATAC-seq |
| ChIP-seq |
| WGS |
| WES |
Write the assay as the bare term (no id).
library_strategy field is frequently OTHER or wrong; if the sample_title
says ATAC/ATACseq, the assay is ATAC-seq regardless of library_strategy.GM12878 is a
lymphoblastoid line → B lymphocyte [CL:0000236]; A549 → lung epithelial;
S2/S2-DRSC is a Drosophila embryonic line.unknown and lower the overall confidence.N61311_untreated or
Set7KD_rep1 evidences no tissue or disease — return unknown, not a guess.unknown.