tooluniverse-protein-structure-retrieval

Retrieves protein structure data from RCSB PDB, PDBe, and AlphaFold with protein disambiguation, quality assessment, and comprehensive structural profiles. Creates detailed structure reports with experimental metadata, ligand information, and download links. Use when users need protein structures, 3D models, crystallography data, or mention PDB IDs (4-character codes like 1ABC) or UniProt accessions.

Quality

88%

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

Quality

Content

77%

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

A thorough, actionable skill body with strong workflow sequencing and concrete tool usage. Its main weaknesses are length/redundancy and a monolithic structure with no progressive disclosure to external reference files.

Suggestions

De-duplicate the search_structures_by_protein_name example (shown in both Phase 1.1 and 2.1) and consider removing the Tool Reference tables since the same calls appear inline in code.

Split the large report template, Quality Assessment Tiers, and Tool Reference into separate reference files (e.g. REPORT_TEMPLATE.md, TOOL_REFERENCE.md) linked one level deep from SKILL.md to improve progressive disclosure.

Tighten the report template by trimming optional sections or marking them conditional, reducing token load while preserving the completeness checklist.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable reference material, but ~415 lines with redundancy: search_structures_by_protein_name appears in both Phase 1.1 and 2.1, and the Tool Reference tables duplicate tool calls already shown in code; the large report template could be tightened.	2 / 3
Actionability	Provides concrete, executable Python using real tool calls (e.g. get_protein_metadata_by_pdb_id, pdbe_get_binding_sites) plus a copy-paste resolution filter: 'high_res = [entry for entry in result["data"] if entry.get("resolution") and entry["resolution"] < 2.5]'.	3 / 3
Workflow Clarity	Clear phased sequence (0-3) with explicit checkpoints (Identity Resolution Checklist, Completeness Checklist), fallback-chain tables, and an error-handling table that includes retry guidance ('Retry once, provide alternative link').	3 / 3
Progressive Disclosure	Well-organized into sections but monolithic (>50 lines, no references/scripts/assets bundle files) with large inline blocks (report template, quality tiers, tool reference) that could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities and provides an explicit 'Use when' trigger with natural keyword coverage. No vague fluff or over-claims; clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across named sources: 'Retrieves protein structure data from RCSB PDB, PDBe, and AlphaFold with protein disambiguation, quality assessment', 'Creates detailed structure reports with experimental metadata, ligand information, and download links'.	3 / 3
Completeness	Explicitly answers both what (retrieves/disambiguates/reports) and when via a clear 'Use when users need protein structures... or mention PDB IDs... or UniProt accessions' trigger clause.	3 / 3
Trigger Term Quality	Covers natural user terms broadly: 'protein structures, 3D models, crystallography data', 'PDB IDs (4-character codes like 1ABC)', 'UniProt accessions', plus source names RCSB PDB, PDBe, AlphaFold.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (protein structure retrieval from PDB/PDBe/AlphaFold) with distinct, specialized triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: wu-yc/LabClaw
Path: skills/bio/tooluniverse-protein-structure-retrieval/SKILL.md
Commit: df37802

Reviewed: 2 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.