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 Golden Gate Assembly

by GPTomics in GPTomics/bioSkills

Design and validate Type IIS scarless DNA assembly (Golden Gate, MoClo) using Biopython Bio.Restriction.

MITAuto-check passedResearch & Science

Install Bio Restriction Golden Gate Assembly

skills CLI
$ npx skills add GPTomics/bioSkills --skill bio-restriction-golden-gate-assembly -a claude-code

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

GitHub CLI
$ gh skill install GPTomics/bioSkills bio-restriction-golden-gate-assembly --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/golden-gate-assembly .claude/skills/bio-restriction-golden-gate-assembly && 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-golden-gate-assembly
GitHub stars
1.2k
Used in
1 other repo
Token cost
~2.9k tokens
SKILL.md length
1,011 words
Files
4
Skills in repo
559
Repo updated
First seen
Licence
MIT

At a glance

Design and validate Type IIS scarless DNA assembly (Golden Gate, MoClo) using Biopython Bio.Restriction.

  • Designing a Golden Gate
  • SKILL.md covers Version Compatibility, Choosing The Assembly Enzyme, Method Context and Domesticate: Find Internal Sites, plus 6 more sections
  • Runs Python scripts from its folder; calls pip
  • Domesticating a part by removing internal Type IIS sites

What it does

Bio Restriction Golden Gate Assembly is an agent skill from GPTomics/bioSkills. Design and validate Type IIS scarless DNA assembly (Golden Gate, MoClo) using Biopython Bio.Restriction. Screens parts for internal BsaI/BsmBI/BbsI/SapI sites (domestication), previews the fusion overhangs a digest exposes, and validates a fusion-overhang set for distinctness and fidelity. Use when designing a Golden Gate or MoClo assembly, domesticating a part by removing internal Type IIS sites, or choosing and checking fusion overhangs for one-pot assembly.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `examples/domestication_check.py`, `examples/overhang_set_validate.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

  • Designing a Golden Gate
  • Domesticating a part by removing internal Type IIS sites
  • Choosing and checking fusion overhangs for one-pot assembly

Example prompts

  • “/bio-restriction-golden-gate-assembly”

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 Golden Gate Assembly loads about 2.9k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 1,011 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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). 1,011 words, ~2,880 tokens.

Download SKILL.mdSave it as .claude/skills/bio-restriction-golden-gate-assembly/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
bio-restriction-golden-gate-assembly
description
Design and validate Type IIS scarless DNA assembly (Golden Gate, MoClo) using Biopython Bio.Restriction. Screens parts for internal BsaI/BsmBI/BbsI/SapI sites (domestication), previews the fusion overhangs a digest exposes, and validates a fusion-overhang set for distinctness and fidelity. Use when designing a Golden Gate or MoClo assembly, domesticating a part by removing internal Type IIS sites, or choosing and checking fusion overhangs for one-pot assembly.
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.BsaI.search) to confirm the search API

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Golden Gate / Type IIS Assembly

"Design (or check) my Golden Gate assembly" -> Make each part free of the assembly enzyme's internal sites, and give every junction a distinct, well-behaved fusion overhang, so one tube of enzyme plus ligase builds the construct directionally and scarlessly.

  • Python: Bio.Restriction to find internal Type IIS sites and read the overhang a cut exposes; the overhang-set rules are sequence logic, not a database call.

The whole method rests on one property: a Type IIS enzyme cuts outside its recognition sequence, so the 4-nt overhang it leaves is set by the user's flanking DNA, and the recognition site is placed to be removed from the final product. Because the ligated junction no longer contains the site, the enzyme cannot re-cut it, so digestion and ligation run together in one pot. Two design obligations follow, and both are what this skill checks: (1) domestication -- no part may contain an internal copy of the assembly enzyme's site, or it will be fragmented during assembly; (2) a set of distinct, non-palindromic fusion overhangs -- one per junction -- so parts assemble in exactly one order.

Choosing The Assembly Enzyme

EnzymeRecognitionOverhangTypical role
BsaI (Eco31I)GGTCTC(1/5)4 nt 5'The default Golden Gate / MoClo Level 1 enzyme; BsaI-HFv2 for fidelity
BsmBI (Esp3I)CGTCTC(1/5)4 nt 5'MoClo Level 0 / Level 2 (alternates with BsaI between levels)
BbsI (BpiI)GAAGAC(2/6)4 nt 5'Alternative when BsaI/BsmBI sites cannot be domesticated out
SapI (LguI)GCTCTTC(1/4)3 nt 5'3-nt (codon-length) overhangs for reading-frame-preserving fusions

Hierarchical systems (MoClo, Golden Braid) alternate enzymes between levels so each assembly round removes the previous level's sites: assemble Level 0 -> 1 with one enzyme, 1 -> 2 with the other. Pick the level's enzyme first, then domesticate every part against it.

Method Context

Golden Gate (Type IIS)Classic restriction-ligation (Type IIP)Gibson assembly
Junction defined byuser-designed 4-nt overhang (3 for SapI)the enzyme's fixed overhang~20-40 bp designed homology
Scarnone (site removed from product)a restriction-site scar at each junctionnone
Reactionone-pot, one-step (37/16 C cycling)sequential digest -> purify -> ligateisothermal 50 C
Fragments per reactionmany (20-30+, more with optimized sets)fewseveral
Main constraintdomestication; distinct overhang setneeds available compatible sitesterminal homology only

Choose Golden Gate when assembling several parts repeatedly from a standardized library; classic digestion for a one-off two-piece clone with convenient sites; Gibson when parts cannot be domesticated or no site layout works.

Domesticate: Find Internal Sites

Goal: Confirm a part carries no internal copy of the assembly enzyme's site (on either strand), and locate any that must be removed.

Approach: enzyme.search(seq) finds Type IIS sites on both strands (the recognition sequence is asymmetric, so its reverse-complement is detected too). Any hit inside a part is a defect to silently mutate away.

python
from Bio import SeqIO
from Bio.Restriction import BsaI, BsmBI, BbsI, SapI

record = SeqIO.read('part.fasta', 'fasta')

for enzyme in (BsaI, BsmBI, BbsI, SapI):
    hits = enzyme.search(record.seq)            # both strands; recognition site is asymmetric
    status = 'clean' if not hits else f'{len(hits)} internal site(s) at {hits} -> domesticate'
    print(f'{enzyme} ({enzyme.site}): {status}')

Domesticate: Break A Site By A Silent Mutation

Goal: Remove an internal site from a coding part without changing the protein.

Approach: Anchor on the recognition sequence itself (on both strands), not the cut position -- a Type IIS enzyme cuts outside its site, so mutating the codon at the cut would not touch the site. Walk the codons overlapping each recognition-site occurrence, swap one for a synonymous codon that breaks the site, and assert the protein is unchanged. This needs the reading frame.

python
from Bio.Data import CodonTable
from Bio.Seq import Seq

def domesticate_cds(cds, enzyme, frame=0):
    '''Remove an enzyme's internal sites from a CDS by synonymous codon swaps (reading frame `frame`).'''
    table = CodonTable.unambiguous_dna_by_id[1]
    syn = {}
    for codon, aa in table.forward_table.items():
        syn.setdefault(aa, []).append(codon)
    s = list(str(cds).upper())
    end = frame + 3 * ((len(s) - frame) // 3)
    protein = str(Seq(''.join(s[frame:end])).translate())
    site = str(enzyme.site)
    motifs = (site, str(Seq(site).reverse_complement()))    # both strands; Type IIS sites are unambiguous
    for _ in range(len(s)):
        seqstr = ''.join(s)
        if not enzyme.search(Seq(seqstr)):
            break
        hit = max(seqstr.find(m) for m in motifs)           # a recognition-site start (either strand)
        for ci in range(((hit - frame) // 3) * 3 + frame, hit + len(site), 3):
            if ci < frame or ci + 3 > len(s):
                continue
            codon = ''.join(s[ci:ci + 3])
            alt = next((a for a in syn.get(table.forward_table.get(codon), ())
                        if a != codon and not enzyme.search(Seq(''.join(s[:ci] + list(a) + s[ci + 3:])))), None)
            if alt:
                s = s[:ci] + list(alt) + s[ci + 3:]
                break
    assert str(Seq(''.join(s[frame:end])).translate()) == protein   # protein unchanged
    return Seq(''.join(s))

# A site that overlaps only Met/Trp codons (no synonyms) is rare but cannot be silently broken;
# always confirm the result is clean: assert not enzyme.search(domesticate_cds(cds, enzyme))
Show full SKILL.md (407 more words)Show less

Preview The Fusion Overhangs A Digest Exposes

Goal: Read the actual 4-nt overhang each Type IIS cut would leave, to confirm junctions match as designed.

Approach: Anchor on the literal forward recognition sequence so only forward-oriented sites are read (a reverse-oriented site cuts on the other side and would otherwise return a misleading overhang). The 5' overhang starts fst5 bases after the recognition-site start.

python
from Bio.Restriction import BsaI

def forward_overhangs(seq, enzyme=BsaI, width=4):
    '''4-nt overhangs at FORWARD-oriented Type IIS sites, anchored on the recognition sequence.'''
    s, site, out = str(seq).upper(), str(enzyme.site), []
    i = s.find(site)
    while i >= 0:
        cut = i + enzyme.fst5                  # top-strand cut offset from the site start
        out.append(s[cut:cut + width])
        i = s.find(site, i + 1)
    return out

# Reverse-oriented sites cut on the other side; for a full construct, design the overhangs
# explicitly (below) rather than inferring every one from sequence.

Validate A Fusion-Overhang Set

Goal: Check that the overhangs chosen for all junctions assemble uniquely and ligate efficiently.

Approach: Apply the design rules: every overhang distinct; none palindromic (self-ligates); no overhang equal to the reverse complement of another (cross-ligates); avoid all-identical bases. High-throughput ligation-fidelity data (Potapov 2018) underlies curated high-fidelity sets used for large assemblies.

python
from Bio.Seq import Seq

def validate_overhang_set(overhangs):
    issues = []
    if len(set(overhangs)) != len(overhangs):
        issues.append('duplicate overhangs (parts assemble ambiguously)')
    for o in overhangs:
        if o == str(Seq(o).reverse_complement()):
            issues.append(f'{o} is palindromic (self-ligates)')
        if len(set(o)) == 1:
            issues.append(f'{o} is a homopolymer (low ligation fidelity)')
    rc = {o: str(Seq(o).reverse_complement()) for o in overhangs}
    for a in overhangs:
        for b in overhangs:
            if a != b and rc[a] == b:
                issues.append(f'{a} is the reverse complement of {b} (cross-ligates)')
    return issues or ['overhang set OK']

print(validate_overhang_set(['AATG', 'GCTT', 'TACT', 'GGGG']))

Common Errors

SymptomCauseFix
Assembly drops or scrambles a partAn internal Type IIS site fragmented itDomesticate every part against the level's enzyme before assembly
Junctions ligate in the wrong order or orientationTwo junctions share an overhang, or one is the reverse complement of anotherUse a distinct, non-self-complementary overhang per junction; check with validate_overhang_set
Empty or low-efficiency assemblyPalindromic or homopolymer overhang, or wrong enzyme/buffer cyclingAvoid palindromic/homopolymer overhangs; cycle 37/16 C with a Type IIS enzyme + T4 ligase
search() misses a reverse-oriented siteSite too close to the sequence end so the cut falls off itDomesticate on the full part in context, not a trimmed fragment
Recognition site still present in the productSite placed so the cut does not remove itOrient Type IIS sites so cleavage excises them from the assembled junction
  • enzyme-selection - Choose a classic restriction enzyme when scarless assembly is not needed
  • restriction-sites - Find any enzyme's sites in a part
  • fragment-analysis - Predict fragments to verify an assembly digest
  • genome-engineering/grna-design - Design constructs that this assembly will build
  • sequence-manipulation/transcription-translation - Confirm domestication kept the reading frame

References

  • Engler C, Kandzia R, Marillonnet S. A one pot, one step, precision cloning method with high throughput capability. PLoS One. 2008;3(11):e3647. doi:10.1371/journal.pone.0003647
  • Engler C, Gruetzner R, Kandzia R, Marillonnet S. Golden gate shuffling: a one-pot DNA shuffling method based on type IIs restriction enzymes. PLoS One. 2009;4(5):e5553. doi:10.1371/journal.pone.0005553
  • Weber E, Engler C, Gruetzner R, Werner S, Marillonnet S. A modular cloning system for standardized assembly of multigene constructs. PLoS One. 2011;6(2):e16765. doi:10.1371/journal.pone.0016765
  • Potapov V, Ong JL, Kucera RB, et al. Comprehensive profiling of four base overhang ligation fidelity by T4 DNA ligase and application to DNA assembly. ACS Synth Biol. 2018;7(11):2665-2674. doi:10.1021/acssynbio.8b00333

© 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/golden-gate-assembly of GPTomics/bioSkills.

  • SKILL.md
  • examples/domestication_check.py
  • examples/overhang_set_validate.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 Golden Gate Assembly 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 Golden Gate Assembly compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bio Restriction Golden Gate Assembly this skillGPTomics/bioSkills1.2k1 repos~2.9kAutomated 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 Golden Gate Assembly

What does Bio Restriction Golden Gate Assembly do?

Design and validate Type IIS scarless DNA assembly (Golden Gate, MoClo) using Biopython Bio.Restriction. Bio Restriction Golden Gate Assembly is an agent skill from GPTomics/bioSkills.Restriction.

When should I use Bio Restriction Golden Gate Assembly?

Bio Restriction Golden Gate Assembly fits situations like: designing a Golden Gate; domesticating a part by removing internal Type IIS sites; choosing and checking fusion overhangs for one-pot assembly.

How do I install Bio Restriction Golden Gate Assembly in Claude Code?

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

How do I install Bio Restriction Golden Gate Assembly in Codex?

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

Can I use Bio Restriction Golden Gate Assembly 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-golden-gate-assembly -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-golden-gate-assembly, .gemini/skills/bio-restriction-golden-gate-assembly, .github/skills/bio-restriction-golden-gate-assembly and .opencode/skills/bio-restriction-golden-gate-assembly in your project.

What does Bio Restriction Golden Gate Assembly need to run?

Going by SKILL.md and its folder, Bio Restriction Golden Gate Assembly 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 Golden Gate Assembly 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 Golden Gate Assembly 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 Golden Gate Assembly use?

Bio Restriction Golden Gate Assembly 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 Golden Gate Assembly use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Golden Gate Assembly?

Skills that share tags, products or a category with Bio Restriction Golden Gate Assembly: 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 Golden Gate Assembly?

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.