tooluniverse-protein-lof-mechanism

Propose the mechanism by which a missense variant causes loss-of-function (LoF), synthesizing evidence from 5 independent layers: AlphaMissense pathogenicity, AlphaFold structural context, ESMC sequence likelihood, SAE feature disruption, and DynaMut2 stability ΔΔG. Distinguishes 'structural stability LoF' (mis-folding) from 'direct functional disruption' (catalytic / binding / PTM site damage). Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score.

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 highly actionable, well-sequenced workflow with executable tool calls and explicit validation, but the monolithic layout and a verbose optional ThermoMPNN section leave room on conciseness and progressive disclosure.

Suggestions

Move the 'Optional: ThermoMPNN instead of DynaMut2' section (local install, the five commercial SaaS platforms, and the citation) into a separate reference file and link to it from a one-line pointer, reducing inline tokens and improving progressive disclosure.

Tighten the ThermoMPNN SaaS list to the single most relevant option plus a 'see reference for others' note, keeping only what bears on the LoF ddG>1 vs ≈0 decision.

Consider extracting the reporting-format template block into a reference file so the main workflow stays a lean overview with a signaled one-level-deep pointer.

Dimension	Reasoning	Score
Conciseness	The core Steps 0–7 are lean and code-driven, but the 'Optional: ThermoMPNN' section (~45 lines listing five commercial SaaS platforms with URLs plus a full citation) is tangential and could be tightened, so it is 'mostly efficient but includes some unnecessary explanation' rather than fully lean (3).	2 / 3
Actionability	Fully executable Python tool calls with real parameters, concrete thresholds, decision tables, and a copy-paste reporting template — meeting the 'fully executable code/commands; copy-paste ready' anchor, not just partial guidance (2).	3 / 3
Workflow Clarity	Steps 0–7 are clearly sequenced with explicit validation checkpoints (assert on the reference residue, pLDDT bands, and a confidence-grading table), matching the 'clear sequence with explicit validation steps' anchor rather than steps-with-gaps (2).	3 / 3
Progressive Disclosure	No bundle files exist and the ~290-line body is monolithic, with content that could be split out (the ThermoMPNN advanced section, the report template) kept inline — 'some structure but content that should be separate is inline' rather than an overview pointing to one-level-deep references (3).	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 names concrete capabilities, a clear 'Use for' trigger, and a well-scoped niche. It answers both what and when without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'synthesizing evidence from 5 independent layers' naming each tool, plus 'Distinguishes structural stability LoF from direct functional disruption' — so it sits at the most specific anchor rather than naming only a domain and some actions (2).	3 / 3
Completeness	Explicitly answers both what ('Propose the mechanism...') and when ('Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score'), matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Includes natural domain terms a genomics user would say — 'missense variant', 'loss-of-function (LoF)', 'pathogenicity score', 'mechanistic causal model' — giving good coverage rather than only jargon or a single keyword.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow (5-layer protein LoF mechanism synthesis for coding missense variants) and clearly separated from sibling skills named in the body, making wrong-skill triggering unlikely rather than merely 'somewhat specific'.	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-lof-mechanism/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.