Tessl • The package manager for agent skills

SkillPublic

rowan

Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.

Quality

86%

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

72%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.

Well-structured, actionable content with strong progressive disclosure that splits detailed API docs into verified reference files. Its main weakness is workflow clarity: batch and screening workflows submit and poll without validation checkpoints or status verification before data access.

Suggestions

Add a status-verification checkpoint to the core workflow pattern (check workflow.status == 'completed' before accessing workflow.data) and integrate it into the five core examples rather than isolating it in the Error Handling section.

Add a feedback loop to the batch/virtual-screening pattern: after batch_poll_status, handle failed workflows explicitly (retry or report) before consuming results.

Replace placeholders in the Common Patterns section ([x, y, z], compound_library, 'complex_molecule_smiles') with concrete sample values so the examples are copy-paste ready, or explicitly mark them as placeholders requiring user input.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, code-driven content with little explanation of concepts Claude already knows, but the repeated submit/wait_for_result/fetch_latest boilerplate across five examples and the promotional 'Why Rowan' / 'Key Capabilities' bullets are minor instances that could be trimmed.	4 / 5
Actionability	The five core workflow examples and the RDKit-native, batch, folder, and error-handling sections are concrete and copy-paste ready, but the 'Common Patterns' section uses undefined placeholders like 'center': [x, y, z], compound_library, and 'complex_molecule_smiles', leaving minor gaps.	4 / 5
Workflow Clarity	A clear submit -> wait_for_result -> fetch_latest -> access-data sequence is shown throughout, but batch operations (Pattern 2 virtual screening, batch_submit_workflow) lack validation checkpoints, and the main examples access workflow.data without first verifying status — the missing-verification cap for batch operations applies.	3 / 5
Progressive Disclosure	SKILL.md acts as an overview with core examples inline and a clearly signaled 'Reference Documentation' section listing all six one-level-deep reference files (api_reference, workflow_types, rdkit_native, molecule_handling, proteins_and_organization, results_interpretation), each verified to exist, with an inline pointer ('See references/rdkit_native.md').	5 / 5
	Total	16 / 20 Passed

Description

96%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 clearly states capabilities and provides an explicit 'Use when' trigger clause with concrete, natural keywords. Its only weakness is that some trigger terms are broad chemistry tasks shared with non-Rowan skills, slightly raising overlap risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools — 'pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2)' — comprehensive rather than just several with minor gaps.	5 / 5
Completeness	Explicitly answers both what ('Cloud-based quantum chemistry platform with Python API... Preferred for computational chemistry workflows including...') and when ('Use when tasks involve quantum chemistry calculations...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when...' clause covers natural user phrases and synonyms — 'quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions' — comprehensive coverage including specific model names.	5 / 5
Distinctiveness Conflict Risk	Rowan is a clearly named cloud platform with a distinct quantum-chemistry niche, but several triggers ('pKa prediction', 'protein-ligand docking', 'conformer searching') are generic chemistry terms that overlap with RDKit and other chemistry skills, creating minor conflict risk.	4 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/rowan/SKILL.md
Revision: 5ce2258

Reviewed: 28 days ago

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.

rowan

Table of Contents

Is this your skill?