torchdrug

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

Quality

89%

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

86%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 well-structured, actionable skill body that splits detail into verified reference files and leads with a version-guard checkpoint. Minor tightening of prose and explicit validation in a few sub-workflows would push it to the top anchor.

Dimension	Reasoning	Score
Conciseness	Lean, code-and-list driven body that assumes Claude's competence and avoids explaining generic concepts; only minor stretches of explanatory prose could be trimmed, keeping it just below the fully-lean anchor.	4 / 5
Actionability	Provides copy-paste-ready, executable commands (version guard, uv install, torch-scatter wheel pins) and a complete ClinTox→GIN→PropertyPrediction→Engine code block covering the canonical case.	5 / 5
Workflow Clarity	Clear sequenced workflow (version guard → install → canonical workflow → per-task recipes) with an explicit version-check checkpoint and troubleshooting feedback, but a few sub-workflows lack explicit validation checkpoints.	4 / 5
Progressive Disclosure	SKILL.md is an overview with well-signaled, one-level-deep links to 8 real reference files (verified present in ./references/), each referenced inline and aggregated in a Reference index — clean navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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 high-quality description that is specific, third-person, and clearly states both what it does and when to use it, anchored to a concrete library/version. Minor additional synonym coverage in triggers is the only marginal improvement.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities (build/troubleshoot workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, knowledge graph reasoning), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (build and troubleshoot TorchDrug 0.2.1 workflows for the listed tasks) and 'when' ('Use when code imports torchdrug or needs its datasets, models, tasks, or Engine') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger coverage ('code imports torchdrug', 'datasets, models, tasks, or Engine', plus the sub-domain names a user would name), though a few synonymous phrasings are absent — sits just below the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	Pinned to a specific named library and version with import/API-based triggers, giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	19 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/torchdrug/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.