/ 目录 / 演练场 / SciAgent-Skills
← 全部服务器 ↗ GitHub
● 社区 jaechang-hits ⚡ 即开即用

SciAgent-Skills

作者 jaechang-hits · jaechang-hits/SciAgent-Skills

197 bioinformatics and life-science skills — RNA-seq, single-cell, drug discovery, proteomics — 92% on BixBench. Powers OmicsHorizon.

SciAgent Skills is a large library of life-science skills for Claude Code and other agents: RNA-seq and scRNA-seq workflows, drug discovery pipelines, proteomics analysis, sequence alignment, and common wet-lab-adjacent tasks. Reported 92.0% accuracy on BixBench. Designed for scientists who want an agent that follows canonical bioinformatics patterns.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

sciagent-skill.replay ▶ 就绪
0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： SciAgent-Skills

How to run a bulk RNA-seq differential expression analysis

👤 Biologists and bioinformaticians with FASTQ files and a need for DE results ⏱ ~120 min advanced

何时使用： You have paired-end FASTQ, a reference, and a condition table.

步骤
  1. Plan the pipeline
    Plan a bulk RNA-seq DE workflow for 2 conditions x 3 reps with salmon + tximport + DESeq2. Output expected files per step.✓ 已复制
    → Step list with tools and intermediate outputs
  2. Run quantification
    Run salmon quant for each sample; produce a script.✓ 已复制
    → Bash script with salmon invocations
  3. DE analysis
    Load quants via tximport, run DESeq2, produce MA + volcano plots and a top-50 gene table.✓ 已复制
    → R script + output files

结果： A DE table + plots you can hand to a PI or collaborator.

注意事项
  • Mis-matched reference versus annotation GTF — Check release numbers explicitly; salmon and DESeq2 can silently run on mismatched IDs
  • Low-count filtering removes biological signal — Use independent filtering or raise threshold gradually; don't blanket filter

Single-cell RNA-seq QC and clustering baseline

👤 Researchers starting scRNA analysis from 10x output ⏱ ~90 min advanced

何时使用： You have a cellranger output directory and need a first-pass Seurat or Scanpy analysis.

步骤
  1. Load + QC
    Load 10x data from cellranger output, do QC (pct.mt, counts, features), filter, normalize.✓ 已复制
    → QC plots + filtered object
  2. Cluster
    Run PCA, find neighbors, cluster at resolution 0.5, and UMAP.✓ 已复制
    → Cluster labels + UMAP plot
  3. Marker genes
    Find cluster markers, produce a top-5-per-cluster heatmap.✓ 已复制
    → Marker table + heatmap

结果： An annotated UMAP and marker table ready for biological interpretation.

注意事项
  • Over-clustering at the default resolution — Try a sweep 0.2-1.0 and pick based on silhouette + biological plausibility

Germline variant calling from WGS

👤 Genomics teams calling SNPs and indels ⏱ ~180 min advanced

何时使用： You have aligned BAMs and need a VCF using best-practices (GATK).

步骤
  1. Plan pipeline
    Plan GATK best-practices germline pipeline from aligned BAMs: BQSR, HaplotypeCaller, joint genotyping with GenomicsDBImport.✓ 已复制
    → Pipeline outline with expected runtimes
  2. Generate scripts
    Produce Snakemake rules for each step.✓ 已复制
    → Snakefile with rules and config

结果： A reproducible Snakemake pipeline ready to run on your cluster.

注意事项
  • Skipping BQSR on small cohorts — Still do it — GATK's downstream filters assume recalibrated quality scores

Triage small-molecule hits from a screen

👤 Med-chem groups triaging HTS results ⏱ ~60 min advanced

何时使用： You have a hit list and want to rank by drug-likeness + novelty.

步骤
  1. Filter by Lipinski + PAINS
    Compute Lipinski and PAINS flags on this SMILES list, output a filtered table.✓ 已复制
    → RDKit-based script + filtered CSV
  2. Similarity to known drugs
    For remaining hits, compute Tanimoto similarity to ChEMBL approved drugs; flag >0.85 as known-scaffold.✓ 已复制
    → Similarity table with flags

结果： A triaged hit list prioritized for follow-up.

组合

与其他 MCP 搭配，撬动十倍杠杆

sciagent-skill + filesystem

Read local FASTQ/BAM files and have SciAgent plan the analysis pipeline on actual data

List the FASTQ files in ~/data/rnaseq/, then use SciAgent to plan a salmon + DESeq2 pipeline for these samples.✓ 已复制
sciagent-skill + github

Search nf-core or Bioconductor repos for reference implementations, then adapt with SciAgent

Search nf-core/rnaseq on GitHub for how they handle trimming, then use SciAgent to adapt that step for my pipeline.✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
Bulk RNA-seq workflow FASTQ + design Standard DE analysis compute
scRNA-seq workflow 10x output Single-cell baseline compute
Variant calling BAMs WGS/WES cohorts compute
Proteomics analysis MS data MS-based proteomics compute
Drug discovery triage SMILES list Hit triage compute

成本与限制

运行它的成本

API 配额
None at skill level
每次调用 Token 数
10-50k per pipeline design
费用
Free skills; compute costs depend on dataset size
提示
Plan the pipeline as a script first, then run; don't keep Claude in the loop during long compute.

安全

权限、密钥、影响范围

凭据存储： No credentials
数据出站： Pipeline designs and snippets go to Claude. Actual patient data should stay on HIPAA-compliant compute.

故障排查

常见错误与修复

tximport fails on missing transcript-to-gene mapping

Regenerate tx2gene from the same GTF you used for the salmon index; mismatch is the usual cause.

Seurat object too large for available RAM

Subsample or switch to on-disk storage with BPCells or DelayedArray-backed Seurat

Conda environment conflicts during pipeline setup

Use mamba instead of conda for faster resolution; pin exact versions in environment.yml rather than floating constraints

验证： mamba env create -f environment.yml --dry-run
Generated script references wrong genome build (hg19 vs hg38)

Explicitly state the genome build in your first prompt; SciAgent defaults may not match your data

替代方案

SciAgent-Skills 对比其他方案

替代方案何时用它替代权衡
Galaxy / nf-coreYou want audited, community pipelines rather than LLM-generated scriptsLess conversational; slower to customize

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills