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

76%

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 ./plugin/skills/tooluniverse-structural-proteomics/SKILL.md

Quality

Content

75%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 reference skill with concrete tool signatures, decision rules, and numeric thresholds rather than concept explanations. It is strong across the board but stops short of top marks because workflows are phase outlines without explicit validation loops and no bundle files are used to offload the large tool inventory.

Suggestions

Add explicit validation checkpoints to the workflows (e.g., 'Validate: confirm resolution <2.5A before trusting binding-site calls; if not, downgrade tier') to push workflow_clarity toward 5.

Move the full Tool Inventory into a references/ file (e.g., TOOL_REFERENCE.md) and keep SKILL.md as an overview, improving progressive_disclosure and conciseness.

Provide at least one copy-paste executable example (e.g., a Python snippet chaining PDBeSIFTS -> RCSBGraphQL -> PDBeValidation into a summary table) to lift actionability.

Dimension	Reasoning	Score
Conciseness	Lean, table-driven body that assumes domain competence (resolution tiers, pLDDT thresholds, artifact filtering) with no padding of basic concepts; a few long tool-inventory lines could be tightened, keeping it just below 5.	4 / 5
Actionability	Provides concrete tool names with parameter signatures, decision rules ('X-ray > Cryo-EM > NMR > AlphaFold'), artifact filters, and numeric thresholds; falls short of 5 because workflows are phase outlines rather than copy-paste executable code/commands.	4 / 5
Workflow Clarity	Three multi-phase workflows are clearly sequenced with decision gates ('IF GPCR', 'IF antibody target') and evidence grading; not 5 because validation/checkpoint steps are implicit rather than explicit validate-then-proceed loops, and not below 4 since sequencing and decisions are strong.	4 / 5
Progressive Disclosure	Well-organized into labeled sections (tool inventory, workflows, gotchas, grading, interpretation, limitations) with no nested references and no bundle files to offload; minor gaps (the long inline tool inventory could live in a reference file) keep it from 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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 specific, well-scoped description that names concrete data sources and use cases with a clear 'Use for' clause. It is slightly below top marks on completeness and trigger-term coverage because it lacks the explicit 'when the user mentions X' phrasing and broader synonyms.

Suggestions

Add an explicit 'Use when the user asks about...' clause naming natural user phrases (e.g., 'drug target druggability', 'binding pocket analysis', 'antibody-antigen interface') to lift completeness toward 5.

Include common synonyms and identifiers users say (e.g., 'PDB structures', 'AlphaFold confidence/pLDDT', 'binding affinity/Ki/Kd') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), and antibody-target interface analysis') alongside named data sources, with only minor coverage gaps; not quite the comprehensive multi-action level of 5.	4 / 5
Completeness	Clearly states 'what' (structural biology plus proteomics integration combining named sources) and 'when' ('Use for druggability assessment...'), but the 'when' trigger phrasing is a task list rather than the explicit 'Use when the user mentions...' formulation of the 5 anchor.	4 / 5
Trigger Term Quality	Includes natural domain terms ('drug target validation', 'druggability assessment', 'ligand-pocket analysis', 'antibody-target interface') and tool names users would mention, but is light on common synonyms/file extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (structural proteomics for drug target validation) with distinct, specific triggers (GPCRdb, SAbDab, pLDDT, druggability) unlikely to collide with other skills.	5 / 5
	Total	17 / 20 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: 1b02920

Reviewed: 1 day 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.