Skip to content
Get packs

Glycoengineering Assistant

Scans protein sequences for N-glycosylation sites and plans glycan-related engineering checks

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
5 files

What it does

This skill teaches an AI agent how to analyse protein sequences for places where sugar chains (glycans) are likely to attach, and how to plan careful engineering changes such as adding or removing those sites. It bundles a small Python helper that finds standard N-glycosylation motifs (N-X-S/T), flags serine/threonine-rich regions that may be mucin-type O-glycosylation candidates, and checks proposed mutations for lost or created sites. It also tells the agent to keep sequence motifs, predictions, experimental evidence and glycan structure clearly separate, and to point users to external prediction services and GlyTouCan lookups rather than treating a motif as proof.

Great for

  • Protein engineers or antibody scientists planning Fc or other glycosylation changes and needing a checklist of sequon effects
  • Students learning how N-glycosylation sequons and O-GalNAc candidates are identified
  • Researchers triaging a sequence before running NetNGlyc or NetOGlyc web services

Skip it if

  • Clinical or regulatory decisions about biosimilars or therapeutics: the skill explicitly says sequence motifs and predictions do not establish glycan occupancy, which needs experimental validation
  • Predicting whether a mutant protein folds, works or is safe: the helper does not model structure, function or tolerability
  • Users expecting automatic submission to prediction servers: the skill uses official web forms and provides no stable API for job submission

Try asking

  • “Find all canonical N-glycosylation sequons in this protein sequence and list their positions and context”
  • “Propose an N-to-Q mutation at site 3 and check whether it removes the sequon or creates any new overlapping one”
  • “Compare the glycosylation site patterns of these two antibody Fc sequences and list the differences”
  • “Look up the WURCS string for GlyTouCan accession G00055MO”
Step-by-step guide: how to use Glycoengineering AssistantInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 5 original files, the MIT licence and an attribution note.

    glycoengineering.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip glycoengineering.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip glycoengineering.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the full mature or construct sequence with signal peptide where possible, since prediction services and topology checks depend on context
  • Ask the agent to list every changed residue with its number when proposing mutations, and to rescan the full product sequence
  • Treat any output as a candidate list to validate experimentally, not as confirmed glycosylation

What's inside

  • references/glycan_databases.md
  • references/glycoshield.md
  • scripts/glycoengineering_tools.py
  • scripts/glytoucan_lookup.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.