CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/glycoengineering/SKILL.md
SKILL.md
Quality
Evals
Security

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 actionable with executable code and real tool commands, but it is padded with redundant rule restatements and background explanation, lacks a sequenced workflow with validation checkpoints for destructive mutations, and fails to offload reference material to the existing bundle file.

Suggestions

De-duplicate the N-X-[S/T] rule (state it once) and trim the Overview's background on what glycosylation is, since Claude already knows it; consolidate the closing 'Additional Resources' with the per-tool URL lists to remove repetition.

Add a short sequenced workflow (e.g., predict with NetNGlyc/NetOGlyc -> verify with the local scanner -> mutate with eliminate/add_glycosite -> re-scan to confirm) with an explicit validation/re-scan checkpoint for destructive mutations.

Move the database reference blocks (GlyConnect, UniCarbKB, GlyTouCan, glycan-notation tables) into references/glycan_databases.md and link to it from the body so SKILL.md stays an overview with one-level-deep, clearly signaled references.

DimensionReasoningScore

Conciseness

The N-X-[S/T] rule is repeated across Overview, headers, and docstrings, and the Overview explains background glycosylation facts Claude already knows; closing 'Additional Resources' also re-lists URLs already given in the tool sections, so it is mostly efficient but padded in several places.

3 / 5

Actionability

Provides concrete, executable Python (find_n_glycosylation_sequons, eliminate_glycosite, predict_o_glycosylation_hotspots) and real GlycoSHIELD CLI invocations, but submit_netoglycv4 only prints a URL rather than executing and query_glyconnect uses an API shape that may not be real, leaving minor gaps.

4 / 5

Workflow Clarity

Content is organized by analysis type rather than as a sequenced pipeline, and the destructive sequence-mutation helpers (eliminate_glycosite/add_glycosite) lack validation/verify checkpoints beyond an assert, which caps workflow clarity at 3 per the destructive-operation rule.

3 / 5

Progressive Disclosure

A bundle file references/glycan_databases.md exists but is never linked or signposted from the body, while large reference-style content (database listings, glycan-notation tables, Additional Resources) is inlined in SKILL.md instead of being split into the existing reference file.

3 / 5

Total

13

/

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 with concrete named actions and a distinct glycoengineering niche. The main gap is the lack of an explicit 'Use when...' trigger clause and slightly technical rather than natural-language trigger phrasing.

DimensionReasoningScore

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 named tools, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Has a clear 'what' (scan/predict/access tools) and a 'when' ('For glycoprotein engineering, therapeutic antibody optimization, and vaccine design'), but the trigger is a terse 'For...' clause rather than an explicit 'Use when...' phrase, so it is not the level-5 anchor.

4 / 5

Trigger Term Quality

Good domain keyword coverage ('glycoprotein engineering', 'therapeutic antibody optimization', 'vaccine design', 'N-glycosylation sequons') but leans technical and lacks natural synonyms or file extensions, sitting above anchor 3 but below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (protein glycosylation) with specific named tools and domain-specific triggers, giving minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.