glycobiology

Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.

Quality

73%

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/glycobiology/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 with executable code and real examples, but token efficiency and structure suffer from duplicated function definitions and an unreferenced bundle script, and workflows lack explicit validation checkpoints.

Suggestions

Reference scripts/predict_glycosylation.py from the body and move the long function implementations there, keeping SKILL.md as a lean overview with short examples.

Remove the duplicate find_n_glycosylation_sites definition — keep one canonical implementation and point to it from Quick Start.

Reframe Typical Workflows as sequenced steps with explicit validation (e.g. predict -> cross-check against UniProt annotations -> report TP/FP/FN) rather than bare single-line calls.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but the body duplicates find_n_glycosylation_sites (a compact Quick Start version and an expanded Core Capabilities version) and inlines long code that could reference the bundled script, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python functions with real example sequences (human EPO) and concrete outputs, matching the anchor for executable code with specific examples.	3 / 3
Workflow Clarity	Typical Workflows are presented as single-line function invocations without explicit multi-step sequencing or validation checkpoints; the UniProt TP/FP/FN comparison is embedded in code rather than framed as a checkpointed workflow.	2 / 3
Progressive Disclosure	The body has clear sections but is inline-heavy (~400 lines) and never references the bundled scripts/predict_glycosylation.py, leaving that file orphaned; content that should be offloaded to the script is duplicated inline.	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, well-scoped description with strong natural trigger terms and good distinctiveness, but it omits an explicit 'Use when...' clause stating when to invoke this skill, capping completeness.

Suggestions

Add an explicit 'Use when...' clause naming user-facing triggers (e.g. 'Use when predicting glycosylation sites from protein sequences, finding N-X-S/T sequons, or surveying glycan analysis tools').

The existing routing sentences ('For protein function queries use uniprot-database...') describe other skills; pair them with a positive trigger for this skill so Claude knows when to select it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Glycosylation site prediction', 'N-glycosylation motif finding', 'O-glycosylation hotspot prediction', 'glycan structure resources' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' but lacks an explicit 'Use when...' trigger for this skill; the only when-like clause routes to other skills ('For protein function queries use uniprot-database'), so completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains natural domain terms a user would say ('glycosylation site prediction', 'N-glycosylation', 'O-glycosylation', 'glycan structure'), giving good coverage of expected phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear glycobiology niche and explicitly routes adjacent needs to uniprot-database and alphafold-database, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/glycobiology/SKILL.md
Commit: 52845c3

Reviewed: about 11 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.