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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/glycoengineering/SKILL.md

Quality

Content

65%

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

Highly actionable code with clear organization, but it teaches background biology Claude already knows, lacks validation feedback loops for destructive sequence edits, and fails to link its existing reference bundle. Tightening prose, adding validation checkpoints, and signaling references would raise all three weaker dimensions.

Suggestions

Remove or condense the Overview and 'Two major glycosylation types' background to assume Claude's biology knowledge, keeping only non-obvious engineering guidance.

Add an explicit validate-fix-retry workflow for mutating glycosylation sites (e.g., re-scan after eliminate/add_glycosite to confirm the target sequon was removed/introduced).

Move detailed external-tool and notation content into references/glycan_databases.md and signal it from the body with a clear 'See [references/glycan_databases.md]' link, rather than inlining everything.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete executable code, but the Overview and 'Two major glycosylation types' sections restate textbook biology Claude already knows, and tool notes ('Results take ~1-5 min') add padding—matching the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready functions (find_n_glycosylation_sequons, eliminate_glycosite, add_glycosite, predict_o_glycosylation_hotspots, query_glyconnect) plus a runnable IgG1 Fc example and concrete CLI/strategy tables.	3 / 3
Workflow Clarity	A recommended predict-then-validate sequence appears in Best Practices, but sequence-mutating operations (eliminate/add glycosite) lack explicit validation checkpoints or validate-fix-retry feedback loops, capping workflow clarity at 2 per the destructive/batch guideline.	2 / 3
Progressive Disclosure	Sections are organized and a bundle file (references/glycan_databases.md) exists, but the body never signals it with a link, and substantial reference-grade content (5 external tools, strategy/notation tables) remains inline rather than split out—matching the 'some structure, references not clearly signaled' anchor.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, distinctive description with good natural trigger terms, weakened only by an implied rather than explicit 'Use when...' trigger clause. Adding an explicit 'Use when...' sentence targeting user phrasing would lift completeness to 3.

Suggestions

Add an explicit 'Use when the user wants to ...' clause naming natural user phrasings (e.g., 'Use when engineering antibody Fc glycosylation, predicting glycosylation sites, or designing glycan shields').

Expand trigger terms with common variations users say, such as 'glycan shield', 'Fc glycosylation', 'ADCC optimization', and 'site-specific glycosylation'.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions—scan N-X-S/T sequons, predict O-glycosylation hotspots, access named tools (NetOGlyc, GlycoShield, GlycoWorkbench)—matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does, but the 'when' is only implied via an application-domain list ('For glycoprotein engineering, therapeutic antibody optimization, and vaccine design') rather than an explicit 'Use when...' trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Uses natural domain terms a specialist would actually say—'glycoprotein engineering', 'therapeutic antibody optimization', 'vaccine design', 'N-glycosylation sequons'—giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Glycoengineering with named tools (NetOGlyc, GlycoShield, GlycoWorkbench) and specific motifs defines a clear niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 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: 757b63b

Reviewed: about 12 hours 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.