tooluniverse-structural-proteomics

Structural biology plus proteomics integration for drug target validation. Combines PDB experimental structures, AlphaFold predictions, GPCRdb, SAbDab antibody structures, ProteinsPlus binding-site prediction, and BindingDB ligand-affinity data. Use for druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), and antibody-target interface analysis.

Quality

96%

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

92%

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

A lean, highly actionable reference with concrete tool signatures, correction tables, and clearly phased workflows backed by evidence-grading and interpretation tables. The main gap is progressive disclosure: a skill this size keeps all detail inline rather than splitting the tool inventory and workflows into one-level-deep reference files.

Suggestions

Move the detailed Tool Inventory (and optionally the per-workflow phase breakdowns) into a references/ file such as TOOLS.md, leaving SKILL.md as a concise overview that links to it — this would lift progressive_disclosure toward level 3.

Add a brief 'Quick start' or single worked example near the top so the most common task (e.g. find structures for a target) is runnable without scanning the full inventory.

Tighten the opening line, which restates the databases already named in the frontmatter description, to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	Dense, token-efficient content — parameter signatures in parentheses, compact tables, and no padding with concepts Claude already knows; the only slack is a mildly redundant opening line, so it does not drop to level 2's 'could be tightened'.	3 / 3
Actionability	Concrete executable guidance throughout — exact tool names with parameters, a gotchas table correcting real mistakes (e.g. use `qualifier` not `uniprot_id`), and numeric thresholds (DoGSiteScorer >0.6); not level 2 because guidance is specific and copy-ready rather than pseudocode-only.	3 / 3
Workflow Clarity	Workflows 1–3 are clearly phased with explicit decision criteria ('Resolution <2.5A for drug design', 'Holo > apo'), Evidence Grading tiers, and Interpretation thresholds serving as validation; not level 2 because checkpoints and grading are explicit rather than implicit.	3 / 3
Progressive Disclosure	Well-sectioned internally, but as a ~130-line monolithic file with no bundle files the full tool inventory and detailed workflows are inline with no one-level-deep references; not level 3 because content that could be split into reference files is not, and not level 1 because organization is clear with no nested references.	2 / 3
	Total	11 / 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 precise, third-person description that states concrete capabilities and provides an explicit 'Use for' trigger clause with distinctive, domain-specific keywords. It is well-distinguished from other skills and answers both what it does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), and antibody-target interface analysis' — matching the multiple-specific-actions anchor; not level 2 because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	Explicitly answers what ('Combines PDB experimental structures, AlphaFold predictions...') and when via the 'Use for ...' trigger clause; not level 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Covers natural domain terms a researcher would say — 'drug target validation', 'PDB', 'AlphaFold', 'GPCRdb', 'SAbDab', 'BindingDB', 'binding-site', 'druggability'; not level 2 because coverage spans both database names and analysis types rather than missing common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (structural proteomics for drug target validation) anchored by named databases (GPCRdb, SAbDab, ProteinsPlus, BindingDB) makes conflict with other skills unlikely; not level 2 because the triggers are distinctive rather than broadly overlapping.	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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-structural-proteomics/SKILL.md
Commit: 089eb8e

Reviewed: about 8 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.