New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bio Restriction Sites

by GPTomics in GPTomics/bioSkills

Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction.

MITAuto-check passedResearch & Science

Install Bio Restriction Sites

skills CLI
$ npx skills add GPTomics/bioSkills --skill bio-restriction-sites -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GPTomics/bioSkills bio-restriction-sites --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/restriction-analysis/restriction-sites .claude/skills/bio-restriction-sites && rm -rf skills-src

Use ~/.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/

Facts

Skill name
bio-restriction-sites
GitHub stars
1.2k
Used in
1 other repo
Token cost
~2.5k tokens
SKILL.md length
875 words
Files
4
Skills in repo
559
Repo updated
First seen
Licence
MIT

At a glance

Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction.

  • Locating where one
  • SKILL.md covers Version Compatibility, The Decisions That Shape A…, Search With One Enzyme and Search With A Batch Of Enzymes, plus 10 more sections
  • Runs Python scripts from its folder; calls pip
  • More restriction enzymes cut a sequence

What it does

Bio Restriction Sites is an agent skill from GPTomics/bioSkills. Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction. Searches single enzymes, batches, or commercial enzyme sets and returns cut positions for linear or circular DNA. Use when locating where one or more restriction enzymes cut a sequence, screening a sequence for the presence or absence of a site, or counting how often an enzyme cuts.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `examples/circular_plasmid.py`, `examples/find_sites.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.

When your agent uses it

  • Locating where one
  • More restriction enzymes cut a sequence
  • Screening a sequence for the presence
  • Absence of a site

Example prompts

  • “/bio-restriction-sites”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit d91ed3d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    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.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bio Restriction Sites loads about 2.5k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 875 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 875 words, ~2,506 tokens.

Download SKILL.mdSave it as .claude/skills/bio-restriction-sites/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
bio-restriction-sites
description
Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction. Searches single enzymes, batches, or commercial enzyme sets and returns cut positions for linear or circular DNA. Use when locating where one or more restriction enzymes cut a sequence, screening a sequence for the presence or absence of a site, or counting how often an enzyme cuts.
tool_type
python
primary_tool
Bio.Restriction

Version Compatibility

Reference examples tested with: BioPython 1.83+ (API verified on 1.86)

Before using code patterns, verify installed versions match. If versions differ:

  • Python: pip show biopython then help(Bio.Restriction.Analysis) to check method names

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. The Analysis "cutters" methods in particular were renamed across versions (see Common Errors).

Finding Restriction Sites

"Find where this enzyme cuts my DNA" -> Return the cut positions for one or more restriction enzymes along a linear or circular sequence.

  • Python: enzyme.search(seq, linear=...) for one enzyme; Bio.Restriction.Analysis(batch, seq, linear=...).full() for many.

The one fact that governs every result: search() returns a 1-based position equal to the first base of the downstream fragment (the base immediately 3' of the cut on the top strand), not the start of the recognition site. For EcoRI G^AATTC whose site starts at position 4, search reports 5 (the base after the cut). Confusing the cut position with the recognition-site start is the single most common bug in restriction code, and it propagates silently into fragment sizes and map coordinates.

DecisionOptionsWhen to pick which
Enzyme scopeone enzyme / a curated RestrictionBatch / CommOnly / AllEnzymesA named enzyme when the assay dictates it; a small batch for a cloning panel; CommOnly (623 buyable enzymes) when the answer must be an enzyme one can purchase; AllEnzymes (1088, includes non-commercial) only for exhaustive in-silico surveys
Topologylinear=True (default) / linear=Falselinear=False for any plasmid, viral circle, or BAC. A circular molecule lets a site span the origin and changes fragment counts (see fragment-analysis)
Questiondoes it cut? / how often? / where?search() for positions; Analysis.with_N_sites(n) for exact cut counts; bool(search()) for a yes/no screen

Use CommOnly not AllEnzymes by default: proposing an enzyme nobody sells wastes a wet-lab cycle. The README's legacy "800+" figure is stale; the installed database holds 1088 enzymes total, 623 commercially available.

Search With One Enzyme

python
from Bio import SeqIO
from Bio.Restriction import EcoRI

record = SeqIO.read('sequence.fasta', 'fasta')
seq = record.seq

sites = EcoRI.search(seq)              # list of 1-based cut positions, e.g. [5, 14]
print(f'EcoRI cuts {len(sites)} time(s) at {sites}')
if not sites:
    print('EcoRI does not cut this sequence')

Search With A Batch Of Enzymes

Goal: Screen a sequence against several enzymes at once and keep only those that cut.

Approach: Build a RestrictionBatch, run Analysis.full() to get every enzyme's positions, then filter to cutters with with_sites().

python
from Bio.Restriction import RestrictionBatch, Analysis, EcoRI, BamHI, HindIII, XhoI

batch = RestrictionBatch([EcoRI, BamHI, HindIII, XhoI])
analysis = Analysis(batch, seq, linear=True)

cutters = analysis.with_sites()        # {enzyme: [positions]} only enzymes that cut
for enzyme, positions in cutters.items():
    print(f'{enzyme}: {positions}')

Filter By Cut Count

Goal: Separate single-cutters (linearize a plasmid), double-cutters (excise an insert), and non-cutters (safe to carry through a digest).

Approach: Analysis exposes with_N_sites(n) for an exact count and without_site() for enzymes with no site. (The older once_cutters()/twice_cutters()/only_dont_cut() names do not exist in current BioPython.)

python
from Bio.Restriction import Analysis, CommOnly

analysis = Analysis(CommOnly, seq, linear=False)   # circular plasmid

single_cutters = analysis.with_N_sites(1)          # {enzyme: [pos]} good for linearization
double_cutters = analysis.with_N_sites(2)          # {enzyme: [pos, pos]} good for excision
non_cutters    = analysis.without_site()           # {enzyme: []} safe in a multi-step digest
all_cutters    = analysis.with_sites()             # any number of sites

print(f'{len(single_cutters)} single-cutters, {len(non_cutters)} non-cutters')

# Pretty-print a chosen subset
analysis.print_as('map')
analysis.print_that(single_cutters)                # formats the dict you pass it

Built-In Enzyme Collections

python
from Bio.Restriction import AllEnzymes, CommOnly, Analysis

print(f'{len(AllEnzymes)} known enzymes, {len(CommOnly)} commercially available')

analysis = Analysis(CommOnly, seq)                 # default: only buyable enzymes
for enzyme, positions in analysis.with_sites().items():
    print(f'{enzyme}: {positions}')

Linear vs Circular DNA

python
from Bio.Restriction import EcoRI

sites_linear   = EcoRI.search(seq, linear=True)    # ends are free; no wrap-around
sites_circular = EcoRI.search(seq, linear=False)   # a site may span the origin

A circular search can find a site that straddles position 1, which a linear search misses. Always pass linear=False for plasmids; the fragment count and map differ (see restriction-analysis/fragment-analysis).

Read An Enzyme's Cut Geometry

Goal: Know what ends an enzyme leaves before designing a ligation.

Approach: elucidate() draws the cut unambiguously; the boolean predicates and the signed ovhg summarize it. The sign convention is the trap: negative ovhg is a 5' overhang, positive is a 3' overhang, zero is blunt.

python
from Bio.Restriction import EcoRI, KpnI, EcoRV

for enz in (EcoRI, KpnI, EcoRV):
    print(enz, enz.elucidate())        # EcoRI G^AATT_C ; KpnI G_GTAC^C ; EcoRV GAT^_ATC
    print(f'  site={enz.site} ovhg={enz.ovhg} ovhgseq={enz.ovhgseq!r}'
          f' 5prime={enz.is_5overhang()} 3prime={enz.is_3overhang()} blunt={enz.is_blunt()}')
# EcoRI.ovhg == -4  -> a 5' overhang (NOT +4). In elucidate, ^ = top-strand cut, _ = bottom-strand cut.

Access Enzymes By Name

python
from Bio.Restriction import AllEnzymes

if 'EcoRI' in AllEnzymes:
    ecori = AllEnzymes.get('EcoRI')
    sites = ecori.search(seq)
Show full SKILL.md (367 more words)Show less

Ambiguous And Interrupted Recognition Sites

Not every enzyme has a fixed 6-bp palindrome. Degenerate sites use IUPAC codes (HincII GTYRAC), and interrupted palindromes carry an unspecified N spacer (BstXI CCANNNNNNTGG, DraIII CACNNNGTG). Note what is_ambiguous() actually means in BioPython: it is True when the site or cut is ambiguous -- N-spacer / interrupted sites (BstXI, DraIII) and enzymes that cut outside their site -- but it is False for a fully IUPAC-degenerate site whose cut is fixed, such as HincII GTYRAC (BioPython reports that as is_defined()). So is_ambiguous() does not detect IUPAC degeneracy; read enzyme.site for the actual letters. Either way, the expected cut frequency for a degenerate or N-containing site is not a clean 1/4^n, so do not estimate cutter rarity from site length alone for these enzymes.

python
from Bio.Restriction import HincII, BstXI

for enz in (HincII, BstXI):
    print(enz, enz.site, 'ambiguous=', enz.is_ambiguous())

Search Many Sequences

python
from Bio import SeqIO
from Bio.Restriction import RestrictionBatch, Analysis, EcoRI, BamHI

batch = RestrictionBatch([EcoRI, BamHI])
for record in SeqIO.parse('sequences.fasta', 'fasta'):
    cutters = Analysis(batch, record.seq).with_sites()
    print(record.id, {str(e): p for e, p in cutters.items()})

Common Errors

SymptomCauseFix
AttributeError: 'Analysis' object has no attribute 'once_cutters'Method renamed across BioPython versionsUse with_N_sites(1) / with_N_sites(2); without_site() for non-cutters; with_sites() for any cutter
AttributeError: ... 'print_that_cut' / 'esite'These names do not existUse print_as(...) + print_that(dct); read the cut with elucidate()
Fragment sizes or map coordinates off by a few basesTreated search() output as the recognition-site startThe integer is the cut position = first base of the downstream fragment (1-based)
Site near the origin missed on a plasmidSearched with linear=TruePass linear=False for circular DNA
Reported a 5' overhang as 3' (or vice versa)Misread the ovhg signNegative ovhg = 5' overhang, positive = 3' overhang, zero = blunt; confirm with elucidate()
Proposed enzyme cannot be purchasedSearched AllEnzymesSearch CommOnly when the answer must be a buyable enzyme
  • restriction-mapping - Order cut sites and draw a map with inter-site distances
  • enzyme-selection - Choose enzymes by cut frequency, overhang, methylation sensitivity, or compatible ends
  • fragment-analysis - Turn cut positions into fragment sizes and gel patterns
  • golden-gate-assembly - Screen a part for internal Type IIS sites before scarless assembly
  • sequence-io/read-sequences - Load the FASTA or GenBank sequence to search

References

  • Roberts RJ, Vincze T, Posfai J, Macelis D. REBASE: a database for DNA restriction and modification: enzymes, genes and genomes. Nucleic Acids Res. 2023;51(D1):D629-D630. doi:10.1093/nar/gkac975
  • Roberts RJ, Belfort M, Bestor T, et al. A nomenclature for restriction enzymes, DNA methyltransferases, homing endonucleases and their genes. Nucleic Acids Res. 2003;31(7):1805-1812. doi:10.1093/nar/gkg274

© GPTomics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in restriction-analysis/restriction-sites of GPTomics/bioSkills.

  • SKILL.md
  • examples/circular_plasmid.py
  • examples/find_sites.py
  • usage-guide.md

Open the folder on GitHubat commit d91ed3d

Used in 1 other repository

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.

Compare with similar skills

Bio Restriction Sites 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.

Bio Restriction Sites compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bio Restriction Sites this skillGPTomics/bioSkills1.2k1 repos~2.5kAutomated safety check: PassMIT
Biopython Bioinformaticsaiming-lab/AutoResearchClaw15k—~810Automated safety check: PassMIT
Biopythondavila7/claude-code-templates33k12 repos~3.4kAutomated safety check: PassMIT
Ggetdavila7/claude-code-templates33k10 repos~6.3kAutomated safety check: PassMIT
GgetK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: NotesBSD-2-Clause
BiopythonK-Dense-AI/scientific-agent-skills48k1 repos~4.3kAutomated safety check: NotesMIT

Similar skills

  • 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.

    15k GitHub stars~810 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Biopython

    davila7/claude-code-templates

    Primary Python toolkit for molecular biology. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 12 repos~3.4k tokens
    Research & ScienceAuto-check passed

  • Gget

    davila7/claude-code-templates

    CLI/Python toolkit for rapid bioinformatics queries. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 10 repos~6.3k tokens
    Research & ScienceAuto-check passed

  • Gget

    K-Dense-AI/scientific-agent-skills

    Queries 20+ bioinformatics resources through CLI/Python. An agent skill from K-Dense-AI/scientific-agent-skills.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    Research & ScienceAuto-check: notes

  • Biopython

    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).

    48k GitHub starsUsed in 1 repo~4.3k tokens
    Research & ScienceAuto-check: notes

  • Biopython

    lamm-mit/scienceclaw

    Computational molecular biology library (sequence I/O, alignment, phylogenetics).

    246 GitHub stars~3.9k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from GPTomics/bioSkills

All 559 skills in this repo

  • Bio Alignment Io

    GPTomics/bioSkills

    Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.

    1.2k GitHub starsUsed in 3 repos~4.9k tokens
    Auto-check passed

  • bioSkills Installer

    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.

    1.2k GitHub starsUsed in 1 repo~789 tokens
    Auto-check passed

  • Bio Write Sequences

    GPTomics/bioSkills

    Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.

    1.2k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed

  • Amplicon Primer Clipping

    GPTomics/bioSkills

    Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.

    1.2k GitHub starsUsed in 2 repos~2.2k tokens
    Auto-check passed

  • Alignment Filtering with samtools and pysam

    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.

    1.2k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed

  • Bio Alignment Indexing

    GPTomics/bioSkills

    Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.

    1.2k GitHub starsUsed in 2 repos~2.4k tokens
    Auto-check passed

Works with

Categories

Questions about Bio Restriction Sites

What does Bio Restriction Sites do?

Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction. Bio Restriction Sites is an agent skill from GPTomics/bioSkills.Restriction.

When should I use Bio Restriction Sites?

Bio Restriction Sites fits situations like: locating where one; more restriction enzymes cut a sequence; screening a sequence for the presence; absence of a site.

How do I install Bio Restriction Sites in Claude Code?

Run `npx skills add GPTomics/bioSkills --skill bio-restriction-sites -a claude-code`. Or copy the skill folder (restriction-analysis/restriction-sites in GPTomics/bioSkills) into .claude/skills/bio-restriction-sites in your project. Claude Code loads it when a task matches its description.

How do I install Bio Restriction Sites in Codex?

Run `npx skills add GPTomics/bioSkills --skill bio-restriction-sites -a codex`. Or copy the skill folder (restriction-analysis/restriction-sites in GPTomics/bioSkills) into .agents/skills/bio-restriction-sites in your project. Codex loads it when a task matches its description.

Can I use Bio Restriction Sites in Cursor, Gemini CLI or GitHub Copilot?

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-sites -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-sites, .gemini/skills/bio-restriction-sites, .github/skills/bio-restriction-sites and .opencode/skills/bio-restriction-sites in your project.

What does Bio Restriction Sites need to run?

Going by SKILL.md and its folder, Bio Restriction Sites needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Bio Restriction Sites access the network?

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.

Is Bio Restriction Sites safe to install?

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.

What licence does Bio Restriction Sites use?

Bio Restriction Sites is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bio Restriction Sites use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bio Restriction Sites?

Skills that share tags, products or a category with Bio Restriction Sites: Biopython Bioinformatics (aiming-lab/AutoResearchClaw, 15k stars), Biopython (davila7/claude-code-templates, 33k stars), Gget (davila7/claude-code-templates, 33k 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.

Who maintains Bio Restriction Sites?

GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,218 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.