Communitygithub.com

folklore-variant-evidence

透過 Folklore Clinical Variant Interpretation MCP 檢索 ClinGen 基因-疾病關聯性驗證,並取得單一公開 GRCh38 生殖細胞核 SNV 或簡單插入/缺失的來源連結公共證據與文獻。

folklore-variant-evidence 是什麼?

此技能整合 Folklore Clinical Variant Interpretation MCP,為 AI 代理提供結構化的公共變異證據、ACMG/AMP 自動分類決策輔助、來源追溯與連結文獻。支援 GRCh38 組裝的生殖細胞核 SNV 或簡單插入/缺失,並明確處理回傳狀態(如 resolved、ambiguous、not_found),強制分支決策邏輯。亦包含 ClinGen 基因-疾病關聯性查詢。技能強調不接受病患、表型、家族、分離或私人病例數據,確保證據來源純粹為公開資料。適用於需要可重現、可證偽的公共變異證據鏈,並可串接至文獻查詢與出版細節。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/folklore-variant-evidence

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Folklore 變異證據

使用 Folklore Clinical Variant Interpretation MCP 來檢索結構化的公共變異證據、自動化變異層級 ACMG/AMP 決策輔助、來源追溯及連結文獻,以供專業審閱。保持工作流程僅限於公共識別碼,並保留每一個明確的結果狀態。Adapter 1.5.0 亦提供 ClinGen 基因-疾病關聯性驗證;來源涵蓋範圍有限,並非所有已知關聯皆包含在內。

Folklore Clinical Variant Interpretation MCP 由 Helena Bioinformatics 發布。其託管端點為:

https://api.helena.bio/folklore/v1/mcp

無需帳戶或 API 金鑰。公開的 Apache-2.0 Adapter 與合約位於 https://github.com/helena-bioinformatics/folklore-mcp。

最簡連線範例

沒有原生 MCP 支援的主機仍可透過相同的公開 JSON-RPC 呼叫:

curl --silent --show-error --fail-with-body --max-time 60 \
  -X POST https://api.helena.bio/folklore/v1/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2026-07-28' \
  -H 'Mcp-Method: tools/call' \
  -H 'Mcp-Name: search_variant_evidence' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}},"name":"search_variant_evidence","arguments":{"assembly":"GRCh38","query":"rs80357914"}}}'

在繼續之前,請檢查回傳的結果。此範例可能回傳 ambiguous 且包含多個候選項目:請停止並要求一個明確的公共變異註記,而不是自動選擇一個候選項目。

選擇正確的技能

當任務是將單一公共變異對應到結構化的 Folklore 證據、明確的解析狀態處理、變異連結文獻或 ClinGen 基因到疾病/疾病到基因的關聯性時,請使用此技能。

  • 對於跨 ClinVar、dbSNP、gnomAD、Ensembl VEP、COSMIC 或多個資料庫的廣泛直接查詢,請使用 database-lookup。
  • 當組裝、座標慣例、重疊群名稱或變異表示方式不確定時,請先使用 genomic-coordinates。
  • 請勿將此技能用於 VCF 註解、批次處理、體細胞變異、結構變異、多基因風險評分或病患特定判讀。

Folklore Clinical Variant Interpretation MCP 透過一個來源連結的公共證據合約來補充這些技能。它不能取代直接資料庫審查或合格的臨床判斷。

強制執行輸入邊界

在進行變異工具呼叫前:

  1. 提取恰好一個公共變異識別碼或註記。
  2. 要求使用 GRCh38 以及生殖細胞核 SNV 或簡單插入/缺失。
  3. 移除或拒絕病患姓名、病例識別碼、表型、家族史、分離證據、臨床記錄、上傳檔案以及其他私人或病患特定背景資訊。
  4. 如果任務依賴於病患背景,請停止並解釋 Folklore Clinical Variant Interpretation MCP 不接受或評估此類資訊。
  5. 絕不能將病患特定的請求轉換為公共變異查詢,同時暗示結果回答了病患特定的問題。

接受的公共變異形式包括基因組座標、基因組/編碼/蛋白質 HGVS、SPDI、rsID 或 Folklore Clinical Variant Interpretation MCP 回傳的 canonical_key。

驗證即時工具目錄

連線至託管端點並呼叫 tools/list。請驗證可用的工具,而非依賴模型記憶。已記錄的公共目錄包含:

  • search_variant_evidence
  • search_variant_literature
  • get_publication_details
  • search_literature_corpus
  • get_gene_disease_associations
  • search_disease_genes

單獨的第七個工具 support_helena 並非科學證據;僅在明確要求時使用。

如果探索或工具呼叫失敗,請將該失敗視為可用性問題。請勿將其重新解釋為缺乏科學證據。

在組合工具呼叫或解釋回應狀態之前,請閱讀公共 MCP 合約。

檢索基因-疾病關聯性

使用 get_gene_disease_associations 查詢一個精確的基因名稱或 HGNC 識別碼,或使用 search_disease_genes 查詢一個精確的 MONDO 識別碼或公共疾病名稱子字串。兩者都接受 limit(預設 20,範圍 1–50)和 offset(預設 0,範圍 0–1000)。請參閱參考文件中的請求範例。這是一個獨立的來源查詢,無需變異輸入或組裝。

保留每個回傳的疾病身分、遺傳模式、證據評估、來源 URL、日期與快照。請勿合併不同的疾病,或在名稱匹配項目中默默地選擇。基因-疾病關聯性並非對特定變異進行分類。空結果表示在可用的 ClinGen 來源中沒有匹配的關聯性,並非沒有關聯。不得發送病患、表型、家族、分離、私人病例數據或定序檔案。仍需合格的專業審閱。

執行變異-證據工作流程

1. 解析與檢索證據

使用以下參數呼叫 search_variant_evidence:

assembly: GRCh38
query: <一個公共變異識別碼或註記>

請勿在此呼叫中添加表型、疾病、病患、家族或治療背景。保留回傳的合約欄位、來源連結、限制與使用邊界。

2. 根據回傳的狀態進行分支

將狀態視為控制流程值,而非敘述性文字:

狀態必要動作
resolved重複使用回傳的 canonical_key;審查結構化解釋、來源追溯、來源連結與限制。
ambiguous顯示回傳的候選項目,並要求明確的公共變異選擇。絕不能自動選擇一個候選項目。
not_found報告在此服務與查詢範圍內未找到結果。請勿聲稱全域性的缺失。
invalid_request報告驗證問題,並請求一個修正後的公共變異。請勿默默地重新解釋輸入。
unsupported說明相關的服務邊界並停止。請勿強行將查詢轉換為支援的形式。
resolution_unavailable報告暫時性的解析或可用性失敗。請勿將其視為證據缺失。

只有 resolved 的結果可以自動進入變異連結的文獻工作流程。如果一個已解析的解釋本身報告了證據不可用,請保留此單獨的限制。

3. 審查證據而不誇大

對於已解析的結果:

  • 呈現回傳的變異身分與 canonical_key。
  • 完全按照回傳的內容保留自動化的變異層級 ACMG/AMP 決策輔助結果。
  • 引用回傳的公共來源與來源追溯。
  • 將回傳的事實與代理的綜合分析分開。
  • 聲明需要合格的專業審閱。
  • 請勿將結果轉變為診斷、個人風險評估、治療建議或獨立的臨床報告。

串聯至文獻

變異連結文獻

在已解析的證據呼叫之後,將回傳的 canonical_key 傳遞給 search_variant_literature。保持 assembly 為 GRCh38。可選的 question 可以縮小文獻範圍,但其必須保持為公共科學問題,且不得包含病患背景。

區分每個結果的匹配類型:

  • exact_variant:與已解析變異的直接匹配
  • variant_alias:透過報告的別名匹配
  • gene_association:更廣泛的基因層級關聯,非變異特異性證據

文獻關聯不會改變回傳的 ACMG/AMP 分類。

出版細節

僅對文獻工具回傳的 PMID 呼叫 get_publication_details。保留 PubMed URL、DOI/PMCID 欄位(如有)、撤稿狀態,以及基因提及與變異提及之間的區別。

語意語料庫搜尋

使用 search_literature_corpus 進行公共自然語言科學問題、或透過出版識別碼、基因、變異、表型、HPO 或 OMIM 概念進行探索。將結果視為來源連結的候選項目,以供專業審閱。零結果回應表示在該有限查詢範圍內沒有回傳結果,並非在任何地方都沒有相關出版品存在。

即使查詢並非變異特異性,也不得將病患資訊放入語料庫查詢中。

報告可重現的結果

包含:

  1. 精確的公共查詢與 GRCh38 組裝。
  2. 回傳的狀態,若為 resolved,則包含 canonical_key。
  3. 結構化的證據或文獻結果,不改變其意義。
  4. 來源連結與出版識別碼。
  5. 文獻結果的匹配類型。
  6. 存取日期與任何可用性限制。
  7. 以下邊界聲明:

此為供合格專業審閱之用的公共、變異層級決策輔助。它不會評估病患、表型、家族、分離或私人病例數據,亦非診斷或治療建議。

可證偽的煙霧測試

使用公共 rsID rs80357914 來測試模糊性處理:

使用組裝 GRCh38 與查詢 rs80357914 呼叫 search_variant_evidence。如果結果為 ambiguous,列出回傳的候選項目並停止以進行明確選擇。請勿選擇候選項目或呼叫下游文獻工具。

只有當 ambiguous 回應導致工作流程中斷且不自動選擇候選項目時,測試才算通過。

官方參考資料

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

alphagenome

Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

analytical-method-validation

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

arbor

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g.

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

astropy

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

autoskill

Observe the user

benchling-integration

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

bgpt-paper-search

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

bids

>

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g.

cellxgene-census

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

citation-management

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

clinical-reports

Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.

相關技能