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

66%

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 ./skills/glycoengineering/SKILL.md

Quality

Content

50%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 skill is rich and actionable with solid code examples and real external tools, but it is padded with concept explanations, lacks a clearly sequenced workflow with validation checkpoints, and fails to link to its own bundled reference file.

Suggestions

Trim the Overview and N/O-glycosylation-type definitions to remove biology that Claude already knows, keeping only domain-specific heuristics and tool-specific knowledge.

Replace the topical layout with an explicit ordered workflow (scan sequons -> predict O-sites -> validate against GlyConnect -> mutate with verification) including validation checkpoints for sequence-mutation operations.

Link to references/glycan_databases.md from the Additional Resources section and move the duplicated database URLs/detail there instead of inlining them.

Dimension	Reasoning	Score
Conciseness	Several sections explain biology Claude already knows (the Overview paragraph on PTM prevalence and the N/O-glycosylation type definitions), padding the body noticeably despite efficient code and tool sections.	2 / 5
Actionability	Provides executable Python functions (sequon scanning, site mutation, hotspot prediction, GlyConnect query) and real tool URLs/commands, though submit_netoglycv4 only prints a URL rather than truly submitting and GlycoWorkbench lacks code.	4 / 5
Workflow Clarity	Sections are organized topically rather than as a sequenced workflow; the loose order in Best Practices lacks explicit validation checkpoints or feedback loops for batch/destructive operations like sequence mutation.	3 / 5
Progressive Disclosure	The body inlines a large Additional Resources/database section while a bundled references/glycan_databases.md exists but is never referenced or linked from the body, leaving content that should be offloaded inline and navigation unclear.	3 / 5
	Total	12 / 20 Passed

Description

83%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 clearly conveys capabilities and use cases with named tools and natural trigger terms. Its main weakness is that the 'when' guidance is expressed as use cases rather than an explicit 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when engineering glycoproteins, optimizing antibody Fc glycosylation, or designing vaccine glycan shields') to raise completeness to 5.

Include a few more natural synonyms or specific file/notation terms users might say (e.g., 'glycan shield', 'ADCC', 'Fc glycan') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (scan for N-X-[S/T] sequons, predict O-glycosylation hotspots, access curated tools) plus named tools (NetOGlyc, GlycoShield, GlycoWorkbench), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Both the 'what' (analyze/engineer glycosylation, scan, predict, access tools) and 'when' (use cases listed via 'For glycoprotein engineering, therapeutic antibody optimization, and vaccine design') are present, but the 'when' is phrased as use cases rather than an explicit 'Use when...' trigger clause.	4 / 5
Trigger Term Quality	Includes natural user-facing terms like 'glycoprotein engineering', 'therapeutic antibody optimization', and 'vaccine design' with good keyword coverage, though a few common synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (protein glycosylation engineering) with named specialized tools and distinct trigger phrases, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/glycoengineering/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.