CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-protein-lof-mechanism/SKILL.md

The canonical home for this skill is tooluniverse-protein-lof-mechanism in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable, well-sequenced analysis workflow with concrete tool calls and explicit gating checkpoints. Its main weaknesses are the inlined advanced ThermoMPNN/SaaS material that should be split into a reference file and the absence of any progressive-disclosure references.

Suggestions

Move the optional 'ThermoMPNN instead of DynaMut2' section (including the five-vendor SaaS list) into a separate references file (e.g. references/THERMOMPNN.md) and replace it with a one-line pointer, improving both conciseness and progressive_disclosure.

Add explicit validate→fix→retry feedback loops for the fragile steps (e.g., Step 0 reference-residue mismatch and Step 5 PDB coverage checks) to lift workflow_clarity from 4 to 5.

Tighten Step 4's two parallel code paths into a single recommended path with the lower-level alternative as a brief note, reducing token cost without losing actionability.

DimensionReasoningScore

Conciseness

Mostly efficient and free of beginner-concept padding, but the ~45-line optional ThermoMPNN section with a five-vendor SaaS list is substantial tangential material inlined in the main skill that could be tightened or moved to a reference; not the level-4 'minor trim' case.

3 / 5

Actionability

Fully executable, copy-paste-ready tool calls with real parameters, tool names, and numeric thresholds (≥0.564, ΔlogP < −1, ddG > +1 kcal/mol) covering the common cases across all five signal types.

5 / 5

Workflow Clarity

Seven clearly sequenced steps (Step 0–7) with explicit checkpoints (reference-residue assert, AlphaMissense benign branch, pLDDT gating, Step 7 confidence grading); just below 5 because error-recovery feedback loops in later steps are mostly implicit rather than explicit validate→fix→retry loops.

4 / 5

Progressive Disclosure

Well-organized with clear section headers but no bundle files exist and there are no one-level-deep references, while the inlined optional ThermoMPNN/SaaS vendor content is material that clearly belongs in a separate reference file.

3 / 5

Total

15

/

20

Passed

Description

87%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 strong, specific description that states a concrete capability and an explicit use-when clause with natural trigger terms. Its only weakness is a slightly dense single-sentence framing rather than a clean enumerated action list.

DimensionReasoningScore

Specificity

Names the domain plus multiple concrete evidence layers ("AlphaMissense pathogenicity, AlphaFold structural context, ESMC sequence likelihood, SAE feature disruption, and DynaMut2 stability ΔΔG") and two specific mechanism categories; slightly below 5 because it frames one synthesized action rather than a list of discrete operations.

4 / 5

Completeness

Explicitly answers both what ("Propose the mechanism by which a missense variant causes loss-of-function") and when ("Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score") with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural terms a genomics user would say ("missense variant", "loss-of-function", "LoF", "coding missense variants", "pathogenicity score"); a few common synonyms (e.g. "amino acid substitution") are missing, keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (mechanistic LoF synthesis for coding missense variants) explicitly contrasted against plain pathogenicity scoring, with third-person voice and minimal overlap risk with adjacent skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.