start
帶生物研究人員檢查已連接的 MCP、盤點 skill 並選起手工作流
中文翻譯
--- name: start description: 設定你的生物研究環境並探索可用的工具。適用於第一次熟悉這個 plugin、檢查已連接哪些文獻、藥物開發或視覺化的 MCP server，或在開始新專案前先盤點可用的分析 skill。 --- # Bio-Research 起手式 > 如果看到不熟悉的佔位符，或需要確認哪些工具已連接，請見 [CONNECTORS.md](../../CONNECTORS.md)。 你正在協助一位生物研究人員熟悉 bio-research plugin。依序走過以下步驟。 ## 步驟 1：歡迎 顯示這段歡迎訊息： ``` Bio-Research Plugin Your AI-powered research assistant for the life sciences. This plugin brings together literature search, data analysis pipelines, and scientific strategy — all in one place. ``` ## 步驟 2：檢查可用的 MCP Server 列出可用的工具，測試哪些 MCP server 已連接。把結果分組： **文獻與資料來源：** - ~~literature database — 生物醫學文獻搜尋 - ~~literature database — 預印本存取（生物與醫學） - ~~journal access — 學術出版品 - ~~data repository — 協作研究資料（Sage Bionetworks） **藥物開發與臨床：** - ~~chemical database — 生物活性化合物資料庫 - ~~drug target database — 藥物標靶探索平台 - ClinicalTrials.gov — 臨床試驗登錄系統 - ~~clinical data platform — 臨床試驗場址排名和平台協助 **視覺化與 AI：** - ~~scientific illustration — 製作科學圖表和示意圖 - ~~AI research platform — 生物領域的 AI（組織病理學、藥物開發） 回報哪些 server 已連接、哪些還沒設定。 ## 步驟 3：盤點可用的 Skill 列出這個 plugin 裡可用的分析 skill： | Skill | What It Does | |-------|-------------| | **Single-Cell RNA QC** | 用 MAD 過濾對 scRNA-seq 資料做品質控制 | | **scvi-tools** | 單細胞多體學的深度學習（scVI、scANVI、totalVI、PeakVI 等） | | **Nextflow Pipelines** | 執行 nf-core 流程（RNA-seq、WGS/WES、ATAC-seq） | | **Instrument Data Converter** | 把實驗儀器輸出轉成 Allotrope ASM 格式 | | **Scientific Problem Selection** | 選擇研究問題的系統性框架 | ## 步驟 4：選用設定，二進位 MCP Server 說明另外有兩個 MCP server 需要單獨安裝： - **~~genomics platform**：存取雲端分析資料和工作流程 安裝：從 https://github.com/10XGenomics/txg-mcp/releases 下載 `txg-node.mcpb` - **~~tool database**（Harvard MIMS）：科學發現用的 AI 工具 安裝：從 https://github.com/mims-harvard/ToolUniverse/releases 下載 `tooluniverse.mcpb` 這兩個需要下載二進位檔，屬於選用。 ## 步驟 5：問要怎麼幫忙 問研究人員今天在做什麼。依常見的工作流程建議起點： 1. **文獻回顧**：「Search ~~literature database for recent papers on [topic]」 2. **分析定序資料**：「Run QC on my single-cell data」或「Set up an RNA-seq pipeline」 3. **藥物開發**：「Search ~~chemical database for compounds targeting [protein]」或「Find drug targets for [disease]」 4. **資料標準化**：「Convert my instrument data to Allotrope format」 5. **研究策略**：「Help me evaluate a new project idea」 等使用者回應，再引導他們使用合適的工具和 skill。
英文原文
--- name: start description: Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project. --- # Bio-Research Start > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). You are helping a biological researcher get oriented with the bio-research plugin. Walk through the following steps in order. ## Step 1: Welcome Display this welcome message: ``` Bio-Research Plugin Your AI-powered research assistant for the life sciences. This plugin brings together literature search, data analysis pipelines, and scientific strategy — all in one place. ``` ## Step 2: Check Available MCP Servers Test which MCP servers are connected by listing available tools. Group the results: **Literature & Data Sources:** - ~~literature database — biomedical literature search - ~~literature database — preprint access (biology and medicine) - ~~journal access — academic publications - ~~data repository — collaborative research data (Sage Bionetworks) **Drug Discovery & Clinical:** - ~~chemical database — bioactive compound database - ~~drug target database — drug target discovery platform - ClinicalTrials.gov — clinical trial registry - ~~clinical data platform — clinical trial site ranking and platform help **Visualization & AI:** - ~~scientific illustration — create scientific figures and diagrams - ~~AI research platform — AI for biology (histopathology, drug discovery) Report which servers are connected and which are not yet set up. ## Step 3: Survey Available Skills List the analysis skills available in this plugin: | Skill | What It Does | |-------|-------------| | **Single-Cell RNA QC** | Quality control for scRNA-seq data with MAD-based filtering | | **scvi-tools** | Deep learning for single-cell omics (scVI, scANVI, totalVI, PeakVI, etc.) | | **Nextflow Pipelines** | Run nf-core pipelines (RNA-seq, WGS/WES, ATAC-seq) | | **Instrument Data Converter** | Convert lab instrument output to Allotrope ASM format | | **Scientific Problem Selection** | Systematic framework for choosing research problems | ## Step 4: Optional Setup — Binary MCP Servers Mention that two additional MCP servers are available as separate installations: - **~~genomics platform** — Access cloud analysis data and workflows Install: Download `txg-node.mcpb` from https://github.com/10XGenomics/txg-mcp/releases - **~~tool database** (Harvard MIMS) — AI tools for scientific discovery Install: Download `tooluniverse.mcpb` from https://github.com/mims-harvard/ToolUniverse/releases These require downloading binary files and are optional. ## Step 5: Ask How to Help Ask the researcher what they're working on today. Suggest starting points based on common workflows: 1. **Literature review** — "Search ~~literature database for recent papers on [topic]" 2. **Analyze sequencing data** — "Run QC on my single-cell data" or "Set up an RNA-seq pipeline" 3. **Drug discovery** — "Search ~~chemical database for compounds targeting [protein]" or "Find drug targets for [disease]" 4. **Data standardization** — "Convert my instrument data to Allotrope format" 5. **Research strategy** — "Help me evaluate a new project idea" Wait for the user's response and guide them to the appropriate tools and skills.