glycoengineering

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/glycoengineering/SKILL.md

The canonical home for this skill is glycoengineering in K-Dense-AI/scientific-agent-skills

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is rich in executable code and genuinely useful tool-specific operational detail, but it is padded with domain concepts Claude already knows, lacks an explicit sequenced workflow, and fails to surface its existing references bundle.

Suggestions

Trim or relocate Claude-known conceptual content (the Overview, glycosylation-type primer, monosaccharide table, and complex N-glycan ASCII art) to tighten the body and improve conciseness.

Link references/glycan_databases.md from the body (e.g., a '## Glycan databases' section pointing to it) so the existing bundle is discoverable and reference material can be split out of SKILL.md.

Add an explicit numbered workflow with checkpoints (e.g., predict sites → check GlyConnect for experimental evidence → engineer mutation → suggest MS validation) to raise workflow clarity.

Replace the stub submit_netoglycv4 with a genuinely functional submission path or clearly mark it as a manual web-interface pointer rather than executable code.

Dimension	Reasoning	Score
Conciseness	The Overview paragraph, the N/O glycosylation-type explanation, the monosaccharide abbreviation table, and the complex N-glycan ASCII art restate concepts Claude already knows; the executable code and tool-specific operational details are efficient, but the conceptual padding could be trimmed.	3 / 5
Actionability	Provides mostly executable, copy-paste-ready Python (sequon scanning, site mutation, O-glyc hotspot prediction, GlyConnect query) and concrete GlycoSHIELD install/usage commands, but submit_netoglycv4 is a stub that only prints a URL and the GlycoSHIELD flags are explicitly labeled illustrative and 'not run here'.	4 / 5
Workflow Clarity	A rough sequence is implied via the Best Practices section (predict with NetNGlyc/NetOGlyc, verify with MS, characterize Fc N297, check GlyConnect) but there is no explicit numbered workflow with validation checkpoints; the skill reads as a toolkit rather than a sequenced process.	3 / 5
Progressive Disclosure	Section structure is clear, but the bundle file references/glycan_databases.md is never linked or signaled from the body, and reference-style content (notation tables, common-mutations table, additional resources) is inlined rather than split out.	3 / 5
	Total	13 / 20 Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete capabilities and use-case triggers for a well-defined niche. It would benefit only from an explicit 'Use when...' trigger clause to reach the top completeness anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Scan sequences for N-glycosylation sequons (N-X-S/T)', 'predict O-glycosylation hotspots', 'access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench)' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly states both what it does and when to use it via 'For glycoprotein engineering, therapeutic antibody optimization, and vaccine design', but lacks the 'Use when...' / 'when the user mentions...' framing of the top anchor.	4 / 5
Trigger Term Quality	Covers natural use-case phrases users would say — 'glycoprotein engineering', 'therapeutic antibody optimization', 'vaccine design' — alongside technical terms and named tools, giving comprehensive keyword coverage for the domain.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, specialized niche (protein glycosylation engineering) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/glycoengineering/SKILL.md
Commit: 4082a2e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.