CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tooluniverse-glycobiology

Glycobiology and glycomics research using GlyGen — glycan structure lookup by GlyTouCan accession, glycan search by mass/monosaccharide-count/type, glycoprotein glycosylation profiles by UniProt accession, glycosylation-site-level detail (position, flanking sequence, attached glycan, co-located SNVs). Use when someone asks about "what glycans are attached to protein X", "N-linked vs O-linked glycosylation sites", "glycan mass/composition search", "GlyTouCan accession lookup", "glycosylation site at position N", or "which proteins have reported glycosylation in human/mouse". NOT for protein sequence/structure retrieval alone (use tooluniverse-sequence-retrieval or tooluniverse-protein-structure-retrieval), NOT for general small-molecule chemistry (use tooluniverse-chemical-compound-retrieval), NOT for post-translational modifications other than glycosylation (use tooluniverse-protein-modification-analysis).

77

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A dense, well-structured operational guide: concrete tool chains with real parameter names and example accessions, explicit verification checkpoints, and a correctly wired single reference file. The only weakness is mild duplication of the description's scope and routing language inside the body.

Suggestions

Trim or compress the 'When to Use This Skill' bullet list and the 'NOT for' routing block, which largely restate the frontmatter description — keep only the body-specific additions (e.g. the UniProt-accession input requirement and the gene_name exception).

In step 4 of the first tool chain, the site_id format explanation is split between a long parenthetical and the reference file — shorten the inline note to the '<uniprot_ac>.<start_pos>.<end_pos>' pattern plus 'confirm isoform suffix from the glycoprotein response' and let the reference carry the worked example.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no concept explanations, no padding — but the 'When to Use This Skill' bullets and the 'NOT for' routing block substantially restate the frontmatter description's triggers and routing, a duplication that could be trimmed. It sits above the score-3 anchor (no unnecessary explanations of known concepts) but short of 'every token earns its place'.

4 / 5

Actionability

Exact tool-call signatures with concrete parameter names ('GlyGen_get_glycoprotein(uniprot_ac=...)', 'GlyGen_search_glycans(mass_min=..., mass_max=...)'), real example accessions ('G17689DH', 'P14210-1.294.294'), and taxonomy IDs (9606 = human, 10090 = mouse) fully cover the common question cases. For an instruction-only routing skill this is copy-paste-ready guidance, matching the score-5 anchor.

5 / 5

Workflow Clarity

Three numbered tool chains are clearly sequenced, with explicit verification checkpoints woven in: 'check status/error before reading data', 'use total_results to know whether to page further with offset', and 'confirm the exact accession format from the glycoprotein response rather than assuming'. These are read-only lookups, so the destructive/batch validation cap does not apply; the checkpoints present are explicit rather than implicit, matching the score-5 anchor.

5 / 5

Progressive Disclosure

The body is an operational overview with a single clearly signaled, one-level-deep reference ('See references/glygen_tool_reference.md for the full parameter table and captured example responses for all 5 tools') — verified to exist as the sole bundle file. The inline 'Response Shape Notes' keep only the operationally relevant deltas (status envelope, paging, when a follow-up call is unnecessary), with the bulk of per-tool detail appropriately split into the reference, matching the score-5 anchor.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary description: concrete parameter-level capabilities, quoted natural-language trigger phrases, and explicit NOT-for routing to sibling skills. Both 'what' and 'when' are fully explicit with no vague or padded language.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete, parameter-level actions — 'glycan structure lookup by GlyTouCan accession, glycan search by mass/monosaccharide-count/type, glycoprotein glycosylation profiles by UniProt accession, glycosylation-site-level detail (position, flanking sequence, attached glycan, co-located SNVs)' — with comprehensive coverage of the skill's capabilities. It matches the score-5 anchor; it is not 4 because no named capability area is missing.

5 / 5

Completeness

It explicitly answers both 'what' (four concrete capabilities) and 'when' ('Use when someone asks about...' followed by six quoted trigger phrases), exactly matching the score-5 anchor. It is not 4 because the 'when' clause is fully explicit with concrete triggers rather than merely present or general.

5 / 5

Trigger Term Quality

It includes literal user phrasings — "what glycans are attached to protein X", "N-linked vs O-linked glycosylation sites", "glycan mass/composition search", "GlyTouCan accession lookup", "which proteins have reported glycosylation in human/mouse" — plus domain keywords (glycobiology, glycomics, glycosylation, glycan, glycoprotein). Coverage of natural terms a user would say for this domain is comprehensive, matching the score-5 anchor.

5 / 5

Distinctiveness Conflict Risk

A clear niche (GlyGen glycan/glycosylation data) with explicit negative routing to each sibling skill — 'NOT for protein sequence/structure retrieval... (use tooluniverse-sequence-retrieval or tooluniverse-protein-structure-retrieval), NOT for general small-molecule chemistry... NOT for post-translational modifications other than glycosylation' — gives minimal conflict risk, matching the score-5 anchor.

5 / 5

Total

20

/

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

mims-harvard/ToolUniverse

Path

plugin/skills/tooluniverse-glycobiology/SKILL.md

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.