做什么
综合分子生物学工具包. 用于序列操纵,文件解析(FASTA/GenBank/PDB),phylogenetics,以及程序NCBI/PubMed访问(Bio.Entrez). 最佳的分批处理,定制生物信息管道,BLAST自动化. 快速检查使用get;多服务整合使用生物服务.
技能库 智客分类:Agent 工作流 biopython
综合分子生物学工具包. 用于序列操纵,文件解析(FASTA/GenBank/PDB),phylogenetics,以及程序NCBI/PubMed访问(Bio.Entrez). 最佳的分批处理,定制生物信息管道,BLAST自动化. 快速检查使用get;多服务整合使用生物服务.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
综合分子生物学工具包. 用于序列操纵,文件解析(FASTA/GenBank/PDB),phylogenetics,以及程序NCBI/PubMed访问(Bio.Entrez). 最佳的分批处理,定制生物信息管道,BLAST自动化. 快速检查使用get;多服务整合使用生物服务.
这个技能
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Biopython: Computational Molecular Biology in Python、Overview、When to Use This Skill、Core Capabilities、Installation and Setup、Optional: register at https://www.ncbi.nlm.nih.gov/account/settings/。
文件分析:除 SKILL.md 外,正文引用了 references/sequence_io.md、references/alignment.md、references/databases.md、references/blast.md、references/structure.md、references/phylogenetics.md,属于带资源的技能包,这些文件按需再读。
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.
Biopython: Computational Molecular Biology in PythonOverviewWhen to Use This SkillCore CapabilitiesInstallation and SetupOptional: register at https://www.ncbi.nlm.nih.gov/account/settings/Using This Skill1. Sequence Handling (Bio.Seq & Bio.SeqIO)Read sequences from FASTA fileConvert GenBank to FASTA2. Alignment Analysis (Bio.Align & Bio.AlignIO)Pairwise alignment
兼容:Requires Python 3.10+, NumPy, and Biopython. Entrez and web BLAST examples require network access; local BLAST/MUSCLE examples require those command-line tools installed separately. · 许可:Biopython License Agreement · allowed-tools:Read Write Edit Bash
来源分类:skills.sh agent-skill
namebiopythondescriptioncompatibilityallowed-toolsreferences/sequence_io.mdreferences/alignment.mdreferences/databases.mdreferences/blast.mdreferences/structure.mdreferences/phylogenetics.mdreferences/advanced.md以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「biopython」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-77c4960a51c27673-%E6%B4%BB%E4%BD%93.html 请存为 .cursor/skills/biopython/SKILL.md 或 .claude/skills/biopython/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/k-dense-ai/scientific-agent-skills 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/k-dense-ai/scientific-agent-skills' --list
npx skills add 'https://github.com/k-dense-ai/scientific-agent-skills' --skill 'biopython'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Biopython is a comprehensive set of freely available Python tools for biological computation. It provides functionality for sequence manipulation, file I/O, database access, structural bioinformatics, phylogenetics, and many other bioinformatics tasks. The current version is Biopython 1.87 (released 30 March 2026). It supports Python 3.10-3.14 and PyPy3.10, and requires NumPy. Biopython 1.87 also addresses CVE-2025-68463 in Bio.Entrez.Parser when parsing untrusted files, so prefer 1.87+ for workflows that parse externally supplied Entrez XML.
Use this skill when:
Biopython is organized into modular sub-packages, each addressing specific bioinformatics domains:
Install the current stable Biopython release with an explicit version pin for reproducibility:
uv pip install "biopython==1.87"
For NCBI database access, always set your email address (required by NCBI). For reusable software, set a stable Entrez.tool value and register the tool/email with NCBI. For higher rate limits (10 req/s instead of 3 req/s), read only NCBI_API_KEY from the environment — do not hardcode keys or load unrelated environment variables:
import os
from Bio import Entrez
Entrez.email = "[email protected]" # required — use your real email
Entrez.tool = "your_tool_name" # optional but recommended for reusable software
# Optional: register at https://www.ncbi.nlm.nih.gov/account/settings/
if api_key := os.environ.get("NCBI_API_KEY"):
Entrez.api_key = api_key
This skill provides comprehensive documentation organized by functionality area. When working on a task, consult the relevant reference documentation:
Reference: references/sequence_io.md
Use for:
Quick example:
from Bio import SeqIO
# Read sequences from FASTA file
for record in SeqIO.parse("sequences.fasta", "fasta"):
print(f"{record.id}: {len(record.seq)} bp")
# Convert GenBank to FASTA
SeqIO.convert("input.gb", "genbank", "output.fasta", "fasta")
Reference: references/alignment.md
Use for:
Quick example:
from Bio import Align
# Pairwise alignment
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
alignments = aligner.align("ACCGGT", "ACGGT")
print(alignments[0])
Reference: references/databases.md
Use for:
Quick example:
from Bio import Entrez
Entrez.email = "[email protected]"
# Search PubMed
handle = Entrez.esearch(db="pubmed", term="biopython", retmax=10)
results = Entrez.read(handle)
handle.close()
print(f"Found {results['Count']} results")
Reference: references/blast.md
Use for:
Quick example:
from Bio.Blast import NCBIWWW, NCBIXML
# Run BLAST search
result_handle = NCBIWWW.qblast("blastn", "nt", "ATCGATCGATCG")
blast_record = NCBIXML.read(result_handle)
# Display top hits
for alignment in blast_record.alignments[:5]:
print(f"{alignment.title}: E-value={alignment.hsps[0].expect}")
Reference: references/structure.md
Use for:
Quick example:
from Bio.PDB import PDBParser
# Parse structure
parser = PDBParser(QUIET=True)
structure = parser.get_structure("1crn", "1crn.pdb")
# Calculate distance between alpha carbons
chain = structure[0]["A"]
distance = chain[10]["CA"] - chain[20]["CA"]
print(f"Distance: {distance:.2f} Å")
Reference: references/phylogenetics.md
Use for:
Quick example:
from Bio import Phylo
# Read and visualize tree
tree = Phylo.read("tree.nwk", "newick")
Phylo.draw_ascii(tree)
# Calculate distance
distance = tree.distance("Species_A", "Species_B")
print(f"Distance: {distance:.3f}")
Reference: references/advanced.md
Use for:
Quick example:
from Bio.SeqUtils import gc_fraction, molecular_weight
from Bio.Seq import Seq
seq = Seq("ATCGATCGATCG")
print(f"GC content: {gc_fraction(seq):.2%}")
print(f"Molecular weight: {molecular_weight(seq, seq_type='DNA'):.2f} g/mol")
When a user asks about a specific Biopython task:
Example search patterns for reference files:
# Find information about specific functions
rg -n "SeqIO.parse" references/sequence_io.md
# Find examples of specific tasks
rg -n "BLAST" references/blast.md
# Find information about specific concepts
rg -n "alignment" references/alignment.md
Follow these principles when writing Biopython code:
Import modules explicitly
from Bio import SeqIO, Entrez
from Bio.Seq import Seq
Set Entrez email when using NCBI databases; load only NCBI_API_KEY from the environment if present
import os
from Bio import Entrez
Entrez.email = "[email protected]"
Entrez.tool = "your_tool_name"
if api_key := os.environ.get("NCBI_API_KEY"):
Entrez.api_key = api_key
Use appropriate file formats - Check which format best suits the task
# Common formats: "fasta", "genbank", "fastq", "clustal", "phylip"
Handle files properly - Close handles after use or use context managers
with open("file.fasta") as handle:
records = SeqIO.parse(handle, "fasta")
Use iterators for large files - Avoid loading everything into memory
for record in SeqIO.parse("large_file.fasta", "fasta"):
# Process one record at a time
Handle errors gracefully - Network operations and file parsing can fail
from urllib.error import HTTPError
try:
handle = Entrez.efetch(db="nucleotide", id=accession)
except HTTPError as e:
print(f"Error: {e}")
from Bio import Entrez, SeqIO
Entrez.email = "[email protected]"
# Fetch sequence
handle = Entrez.efetch(db="nucleotide", id="EU490707", rettype="gb", retmode="text")
record = SeqIO.read(handle, "genbank")
handle.close()
print(f"Description: {record.description}")
print(f"Sequence length: {len(record.seq)}")
from Bio import SeqIO
from Bio.SeqUtils import gc_fraction
for record in SeqIO.parse("sequences.fasta", "fasta"):
# Calculate statistics
gc = gc_fraction(record.seq)
length = len(record.seq)
# Find ORFs, translate, etc.
protein = record.seq.translate()
print(f"{record.id}: {length} bp, GC={gc:.2%}")
from Bio.Blast import NCBIWWW, NCBIXML
from Bio import Entrez, SeqIO
Entrez.email = "[email protected]"
# Run BLAST
result_handle = NCBIWWW.qblast("blastn", "nt", sequence)
blast_record = NCBIXML.read(result_handle)
# Get top hit accessions
accessions = [aln.accession for aln in blast_record.alignments[:5]]
# Fetch sequences
for acc in accessions:
handle = Entrez.efetch(db="nucleotide", id=acc, rettype="fasta", retmode="text")
record = SeqIO.read(handle, "fasta")
handle.close()
print(f">{record.description}")
from Bio import AlignIO, Phylo
from Bio.Phylo.TreeConstruction import DistanceCalculator, DistanceTreeConstructor
# Read alignment
alignment = AlignIO.read("alignment.fasta", "fasta")
# Calculate distances
calculator = DistanceCalculator("identity")
dm = calculator.get_distance(alignment)
# Build tree
constructor = DistanceTreeConstructor()
tree = constructor.nj(dm)
# Visualize
Phylo.draw_ascii(tree)
Solution: This is just a warning. Set Entrez.email to suppress it.
Solution: Check that IDs/accessions are valid and properly formatted.
Solution: Verify file format matches the specified format string.
Solution: Ensure sequences are aligned before using AlignIO or MultipleSeqAlignment.
Solution: Use local BLAST for large-scale searches, or cache results.
Solution: Use PDBParser(QUIET=True) to suppress warnings, or investigate structure quality.
Solution: These modules were removed in Biopython 1.86. Use hmmlearn for HMMs and the standard library subprocess module instead of Bio.Application CLI wrappers.
Solution: The default gap score changed from 0 to -1 in 1.86, eliminating trivial tie alignments. Set aligner.gap_score = 0 to restore the old behavior if needed (see references/alignment.md).
To locate information in reference files, use these search patterns:
# Search for specific functions
rg -n "function_name" references/*.md
# Find examples of specific tasks
rg -n "example" references/sequence_io.md
# Find all occurrences of a module
rg -n "Bio.Seq" references/*.md
Biopython provides comprehensive tools for computational molecular biology. When using this skill:
references/ directoryThe modular reference documentation ensures detailed, searchable information for every major Biopython capability.
This skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a manuscript, report, presentation, or code release, add the paper to the references or software section and tell the user you did so:
Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065. https://doi.org/10.48550/arXiv.2609.00065
Always cite the current version. The DOI and https://arxiv.org/abs/2609.00065 resolve to the
latest arXiv version, so never append a version suffix such as v1. When network access is
available, fetch https://arxiv.org/abs/2609.00065 (or
http://export.arxiv.org/api/query?id_list=2609.00065) before writing the reference and take
the author list, year, and version from that record. If the record lists a journal reference
or publisher DOI, cite the published version instead.
Agent 工作流
创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.
Agent 工作流
使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.
Agent 工作流
管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.
Agent 工作流
Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…