Biopython Bioinformatics
aiming-lab/AutoResearchClaw
Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.
Select restriction enzymes for cloning or diagnostics using Biopython Bio.Restriction.
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selection --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/restriction-analysis/enzyme-selection .claude/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .claude/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selectionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/restriction-analysis/enzyme-selection .agents/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .agents/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/restriction-analysis/enzyme-selection .cursor/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .cursor/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GPTomics/bioSkills.git --path restriction-analysis/enzyme-selection--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/restriction-analysis/enzyme-selection .gemini/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .gemini/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selectionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/restriction-analysis/enzyme-selection .github/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .github/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GPTomics/bioSkills bio-restriction-enzyme-selection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/restriction-analysis/enzyme-selection .opencode/skills/bio-restriction-enzyme-selection && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bio-restriction-enzyme-selection" agent skill from https://github.com/GPTomics/bioSkills/tree/main/restriction-analysis/enzyme-selection into .opencode/skills/bio-restriction-enzyme-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-restriction-enzyme-selection", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
bio-restriction-enzyme-selectionSelect restriction enzymes for cloning or diagnostics using Biopython Bio.Restriction.
Bio Restriction Enzyme Selection is an agent skill from GPTomics/bioSkills. Select restriction enzymes for cloning or diagnostics using Biopython Bio.Restriction. Finds enzymes by cut frequency, overhang type, recognition-site length, commercial availability, compatible ends, and methylation sensitivity, and identifies isoschizomers and compatible pairs. Use when choosing which enzymes to use to linearize a vector, drop in an insert, set up a diagnostic digest, or pick a methylation-insensitive enzyme.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `examples/cloning_strategy.py`, `examples/select_enzymes.py` and `usage-guide.md`).
It sits in Research & Science, covering Bioinformatics. It works with Biopython. The repository describes itself as: a set of SKILLS.md for doing bioinformatics with agents like claude code. The licence is MIT.
Read from SKILL.md and the folder at commit d91ed3d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
pipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Bio Restriction Enzyme Selection loads about 3.4k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 1,375 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 1,375 words, ~3,422 tokens.
.claude/skills/bio-restriction-enzyme-selection/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Reference examples tested with: BioPython 1.83+ (API verified on 1.86)
Before using code patterns, verify installed versions match. If versions differ:
pip show biopython then help(Bio.Restriction.Analysis) to confirm method namesIf code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. The Analysis cut-count methods were renamed across versions (see Common Errors).
"Pick enzymes to clone my insert into this vector" -> Search the enzyme database under the constraints that actually matter: cuts the vector once, leaves the insert intact, makes a usable end, is buyable, and is not silenced by methylation.
Bio.Restriction.Analysis(CommOnly, seq) with with_N_sites/without_site, plus enzyme predicates for overhang and compatibility.The canonical selection is an intersection, not a single query: an enzyme that cuts the vector exactly once at the cloning site AND does not cut the insert AND leaves the intended overhang AND is commercially available AND is not blocked by the methylation on the source DNA. Each constraint below is one filter in that intersection; the skill's value is composing them, not running any one alone.
| Constraint | What to ask | API / source |
|---|---|---|
| Cut frequency | Cut vector once? Leave insert uncut? | Analysis.with_N_sites(1), Analysis.without_site() |
| Recognition length | naive 1/4^n spacing: 4-cutter (~256 bp, frequent), 6-cutter (~4 kb, routine cloning), 8-cutter (~65 kb, rare; large constructs, mapping) -- real genomes deviate (see below) | len(enzyme.site) |
| Overhang | 5' overhang (most common), 3' overhang, or blunt (non-directional, inefficient ligation) | is_5overhang(), is_3overhang(), is_blunt() |
| Directionality | Two different ends so the insert goes one way and the vector cannot self-ligate | two single-cutters with non-compatible ends |
| Availability | Can it be purchased? | membership in CommOnly |
| Methylation | Is the site blocked by Dam/Dcm/CpG on this DNA? | curated table below + REBASE (not the coarse is_methylable()) |
| Fidelity | Avoid star activity under forcing conditions | prefer High-Fidelity (HF) enzymes; benchtop, not in BioPython |
Naive cut-frequency intuition (a 6-cutter every 4^6 = 4096 bp) fails on real genomes: vertebrate CpG suppression makes any CpG-containing site -- NotI GCGGCCGC above all -- far rarer than 1/4^n, which is exactly why NotI and other 8-cutters are the rare-cutters of choice for large mammalian fragments.
Goal: Sort candidates into single-cutters (linearize), double-cutters (excise), and non-cutters (safe through the digest).
Approach: Analysis exposes with_N_sites(n) for an exact cut count and without_site() for non-cutters. (The older once_cutters() / twice_cutters() / only_dont_cut() / only_cut() names do not exist in current BioPython and raise AttributeError.)
from Bio import SeqIO
from Bio.Restriction import Analysis, CommOnly
record = SeqIO.read('sequence.fasta', 'fasta')
analysis = Analysis(CommOnly, record.seq)
single_cutters = analysis.with_N_sites(1) # linearization candidates
double_cutters = analysis.with_N_sites(2) # excise-an-insert candidates
non_cutters = analysis.without_site() # safe to keep in a multi-enzyme digest
all_cutters = analysis.with_sites() # any number of sites
print(f'{len(single_cutters)} single-cutters, {len(non_cutters)} non-cutters')Goal: Two enzymes that each cut the vector once, neither cuts the insert, and their ends differ so the ligation is directional and the vector cannot recircularize.
Approach: Intersect "cuts vector once" with "does not cut insert", then pair candidates whose ends are mutually INCOMPATIBLE -- that is what makes the cloning directional and stops the vector self-ligating. Two enzymes are an incompatible (directional) pair when neither appears in the other's compatible_end().
from itertools import combinations
from Bio.Restriction import Analysis, CommOnly
def directional_pairs(vector_seq, insert_seq):
vec_once = set(Analysis(CommOnly, vector_seq, linear=False).with_N_sites(1))
ins_clear = set(Analysis(CommOnly, insert_seq).without_site())
candidates = sorted(vec_once & ins_clear, key=str)
pairs = []
for a, b in combinations(candidates, 2):
if b not in a.compatible_end(): # incompatible ends -> directional, no self-ligation
pairs.append((a, b))
return pairs # each pair cuts vector once, leaves insert intactGoal: Identify enzymes whose overhangs ligate together, including enzymes with different recognition sites that leave the same overhang (isocaudomers).
Approach: compatible_end() returns every enzyme that can leave a compatible overhang -- including Type IIS enzymes whose overhang is user-defined, not fixed. For a real ligation partner, filter the result to fixed-overhang Type IIP enzymes (the true isocaudomers, e.g. BamHI/BglII/BclI/Sau3AI all leave 5'-GATC); a Type IIS enzyme listed here is not a drop-in cloning partner.
from Bio.Restriction import BamHI
partners = BamHI.compatible_end() # any enzyme that can leave a 5'-GATC end
fixed = [e for e in partners if e.is_palindromic()] # keep Type IIP isocaudomers (BglII, BclI, MboI, Sau3AI...)
print(f'BamHI isocaudomers (fixed overhang): {sorted(str(e) for e in fixed)}')Ligating two different-but-compatible sites usually creates a hybrid junction that neither enzyme re-cleaves (BamHI G^GATCC + BglII A^GATCT -> GGATCT/AGATCC, which is neither site). This makes the join directional and is used deliberately to destroy one site -- but whether the junction is recut is pair-dependent, so verify the specific pair rather than assuming.
from Bio.Restriction import CommOnly, Analysis
cutters = Analysis(CommOnly, record.seq).with_sites()
blunt = [e for e in cutters if e.is_blunt()]
five_p = [e for e in cutters if e.is_5overhang()]
three_p = [e for e in cutters if e.is_3overhang()]
six_cutters = [e for e in CommOnly if len(e.site) == 6] # routine cloning
eight_cutters = [e for e in CommOnly if len(e.site) == 8] # rare cuttersStandard E. coli cloning strains (DH5-alpha, JM109, TOP10) are dam+ dcm+, so plasmid and insert DNA prepped from them is methylated at GATC (Dam, N6-methyladenine) and CCWGG (Dcm, 5-methylcytosine). An enzyme blocked by that mark will fail or partially cut even though the recognition site is present -- a silent failure. Mammalian genomic DNA additionally carries CpG (5mC) methylation. The fix is to re-propagate the DNA in a dam- dcm- strain (GM2163, JM110, INV110) before cutting.
| Site context | Enzyme | Behavior on the methylated site |
|---|---|---|
| Dam GATC | DpnI | Cuts ONLY when fully Dam-methylated (methylation-dependent) |
| Dam GATC | DpnII, MboI | Blocked by Dam methylation (cut only unmethylated GATC) |
| Dam GATC | Sau3AI | Insensitive to Dam (cuts methylated or not) |
| CpG CCGG | HpaII | Blocked by CpG methylation of the internal C |
| CpG CCGG | MspI | Cuts regardless of CpG methylation (isoschizomer of HpaII) |
| Dam-overlapping | ClaI ATCGAT, XbaI TCTAGA | Blocked when flanking bases create an overlapping Dam GATC |
Do NOT rely on BioPython's enzyme.is_methylable() to make this decision: it is a coarse REBASE flag (it returns True for Sau3AI, which is actually Dam-insensitive, and for EcoRI), does not distinguish Dam vs Dcm vs CpG, and does not indicate the direction of the effect. Use the curated cases above and consult REBASE for the specific methyltransferase that blocks a given enzyme.
from Bio.Restriction import DpnI, DpnII, Sau3AI, MboI
# Curated, not from is_methylable(): the GATC quartet a cloner must know.
dam_behavior = {
'DpnI': 'requires Dam methylation to cut',
'DpnII': 'blocked by Dam methylation',
'MboI': 'blocked by Dam methylation',
'Sau3AI': 'insensitive to Dam methylation',
}
for enz in (DpnI, DpnII, MboI, Sau3AI):
print(f'{enz} ({enz.site}): {dam_behavior[str(enz)]}')from Bio.Restriction import SmaI, XmaI
print('SmaI isoschizomers:', SmaI.isoschizomers()) # all same-site enzymes (Cfr9I, TspMI, XmaI)
print('SmaI elucidate:', SmaI.elucidate()) # CCC^_GGG -> blunt
print('XmaI elucidate:', XmaI.elucidate()) # C^CCGG_G -> 5' overhangCCC^GGG blunt vs XmaI C^CCGGG 5' overhang). Note: in current BioPython neoschizomers() and isoschizomers() overlap (both list all same-site enzymes), so confirm the actual cut difference with elucidate() rather than trusting the method name to filter.Under forcing conditions -- >5% glycerol, low ionic strength, high pH (>8), large enzyme excess or over-long incubation, or Mn2+ replacing Mg2+ -- many enzymes relax specificity and cut near-cognate sites ("star activity"; EcoRI* is the classic case). When a clean digest matters, prefer an engineered High-Fidelity (HF) enzyme (e.g. EcoRI-HF), which is selected to show no star activity even in overnight, high-unit digests. This is a benchtop property, not encoded in BioPython; surface it when recommending an enzyme.
Type IIS enzymes (BsaI, BsmBI, BbsI, SapI) cut outside their recognition site and enable scarless, directional, one-pot assembly. Selecting and validating them -- including domestication of internal sites and fusion-overhang design -- is its own analysis; route to restriction-analysis/golden-gate-assembly. For plain selection, a part is "Golden Gate ready" for an enzyme when enzyme.search(seq) returns no internal sites.
| Symptom | Cause | Fix |
|---|---|---|
AttributeError: ... 'once_cutters' / 'only_dont_cut' / 'only_cut' | Methods renamed across BioPython versions | with_N_sites(1)/with_N_sites(2) for exact counts; without_site() for non-cutters; with_sites() for any cutter |
AttributeError: ... 'is_dam_methylable' / 'is_dcm_methylable' | These methods do not exist | Use the curated Dam/Dcm table above; consult REBASE for specifics |
AttributeError: ... 'fst3cut' / 'fst5cut' | Attribute names are fst3 / fst5 | Use enzyme.fst5 / enzyme.fst3 (Type IIS cut offsets) |
| Chosen enzyme fails to cut a real prep | Site blocked by Dam/Dcm methylation | Re-prep DNA in a dam- dcm- strain, or pick a methylation-insensitive enzyme |
| Recommended enzyme cannot be bought | Searched AllEnzymes | Restrict to CommOnly |
| Blunt clone has high background / wrong orientation | Blunt ends ligate inefficiently and non-directionally | Prefer two different sticky ends; dephosphorylate the vector (see usage guide) |
| Double digest only partially cuts | The two chosen enzymes share no buffer where both are fully active | Pick a pair compatible in one universal buffer (rCutSmart / FastDigest); otherwise digest sequentially, lower-salt enzyme first (this is a selection criterion when choosing the pair) |
© GPTomics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files in restriction-analysis/enzyme-selection of GPTomics/bioSkills.
Open the folder on GitHubat commit d91ed3d
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.
Bio Restriction Enzyme Selection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bio Restriction Enzyme Selection this skillGPTomics/bioSkills | 1.2k | 1 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Biopython Bioinformaticsaiming-lab/AutoResearchClaw | 15k | — | ~810 | Automated safety check: Pass | MIT | |
| Biopythondavila7/claude-code-templates | 32k | 12 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Ggetdavila7/claude-code-templates | 32k | 10 repos | ~6.3k | Automated safety check: Pass | MIT | |
| GgetK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~2.8k | Automated safety check: Notes | BSD-2-Clause | |
| BiopythonK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~4.3k | Automated safety check: Notes | MIT |
aiming-lab/AutoResearchClaw
Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.
davila7/claude-code-templates
Primary Python toolkit for molecular biology. An agent skill from davila7/claude-code-templates.
davila7/claude-code-templates
CLI/Python toolkit for rapid bioinformatics queries. An agent skill from davila7/claude-code-templates.
K-Dense-AI/scientific-agent-skills
Queries 20+ bioinformatics resources through CLI/Python. An agent skill from K-Dense-AI/scientific-agent-skills.
K-Dense-AI/scientific-agent-skills
Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez).
lamm-mit/scienceclaw
Computational molecular biology library (sequence I/O, alignment, phylogenetics).
GPTomics/bioSkills
Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.
GPTomics/bioSkills
Installs the bioSkills collection of 425 bioinformatics skills in one step, or only chosen categories, so sequencing, RNA-seq, single-cell and variant tasks get specialized help.
GPTomics/bioSkills
Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.
GPTomics/bioSkills
Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.
GPTomics/bioSkills
Filters BAM alignments by FLAG bits, mapping quality and regions with samtools view or pysam, with recipes for common keep and drop cases.
GPTomics/bioSkills
Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.
Works with
Categories
Select restriction enzymes for cloning or diagnostics using Biopython Bio.Restriction. Bio Restriction Enzyme Selection is an agent skill from GPTomics/bioSkills.Restriction.
Bio Restriction Enzyme Selection fits situations like: choosing which enzymes to use to linearize a vector; drop in an insert; set up a diagnostic digest; pick a methylation-insensitive enzyme.
Run `npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a claude-code`. Or copy the skill folder (restriction-analysis/enzyme-selection in GPTomics/bioSkills) into .claude/skills/bio-restriction-enzyme-selection in your project. Claude Code loads it when a task matches its description.
Run `npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a codex`. Or copy the skill folder (restriction-analysis/enzyme-selection in GPTomics/bioSkills) into .agents/skills/bio-restriction-enzyme-selection in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GPTomics/bioSkills --skill bio-restriction-enzyme-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bio-restriction-enzyme-selection, .gemini/skills/bio-restriction-enzyme-selection, .github/skills/bio-restriction-enzyme-selection and .opencode/skills/bio-restriction-enzyme-selection in your project.
Going by SKILL.md and its folder, Bio Restriction Enzyme Selection needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Bio Restriction Enzyme Selection is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Bio Restriction Enzyme Selection: Biopython Bioinformatics (aiming-lab/AutoResearchClaw, 15k stars), Biopython (davila7/claude-code-templates, 32k stars), Gget (davila7/claude-code-templates, 32k stars) and Gget (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,217 GitHub stars. The repository holds 559 skills in this directory. The repository was last updated on August 15, 2026.
Source: GPTomics/bioSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.