tooluniverse-protein-therapeutic-design

AI-guided de novo protein design — RFdiffusion backbone generation, ProteinMPNN sequence design, structure validation (pLDDT, pTM, MPNN scores). Use for designing therapeutic protein binders, novel scaffolds, enzyme variants, and miniprotein/protein-interface design before experimental validation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured, actionable skill body with a clear phased workflow, specific tool/parameter guidance, and validation checkpoints. Its main weaknesses are some generic boilerplate sections and five referenced detail files that are not present in the bundle.

Suggestions

Remove or tighten the generic 'LOOK UP, DON'T GUESS' and 'COMPUTE, DON'T DESCRIBE' sections, which are not specific to protein design and add token overhead.

Create the five referenced files (DESIGN_PROCEDURES.md, TOOLS_REFERENCE.md, EXAMPLES.md, CHECKLIST.md, design_templates.md) under references/, or drop the references list if the detail is not provided.

Collapse the repeated '*(requires NVIDIA_API_KEY env var; free key at build.nvidia.com)*' note per tool into a single statement in the NVIDIA NIM Requirements section to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and table-driven, but the 'LOOK UP, DON'T GUESS' and 'COMPUTE, DON'T DESCRIBE' sections are generic meta-instructions not specific to this skill, and the opening prose paragraph restates ideas already in the KEY PRINCIPLES list.	2 / 3
Actionability	Concrete and executable in spirit: exact tool names, exact parameter names ('diffusion_steps', 'pdb_string', 'sequence'), a wrong-vs-correct parameter table, numeric thresholds (pLDDT >85, pTM >0.8), and minimum counts (>=5 backbones, >=8 sequences).	3 / 3
Workflow Clarity	A clearly sequenced 6-phase workflow with explicit validation in Phase 4 (predict structure, compare, assess pLDDT/pTM) and a completeness checklist with pass/fail gating ('>= 3 passing').	3 / 3
Progressive Disclosure	The body signals one-level-deep references (DESIGN_PROCEDURES.md, TOOLS_REFERENCE.md, EXAMPLES.md, CHECKLIST.md, design_templates.md) with descriptions, but none of these files actually exist in references/, so the navigation is broken.	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 pairs concrete named-tool actions with an explicit 'Use for' trigger clause and natural domain terms. It clearly answers what the skill does and when to invoke it with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'RFdiffusion backbone generation, ProteinMPNN sequence design, structure validation (pLDDT, pTM, MPNN scores)' — naming specific tools and metrics rather than vague capabilities.	3 / 3
Completeness	Explicitly answers both 'what' (de novo protein design via RFdiffusion/ProteinMPNN/validation) and 'when' via an explicit 'Use for ...' trigger clause.	3 / 3
Trigger Term Quality	Natural use-case terms a domain user would say ('therapeutic protein binders, novel scaffolds, enzyme variants, miniprotein/protein-interface design') appear alongside the technical tool names, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The therapeutic de novo protein design niche with named tools (RFdiffusion, ProteinMPNN) is clearly distinct and unlikely to trigger 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-protein-therapeutic-design/SKILL.md
Commit: 089eb8e

Reviewed: about 7 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.