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

80%

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

68%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, largely executable skill body with excellent reference signaling. Its main weakness is workflow clarity around batch operations, which lack the per-item validation/verification the rubric requires, capping that dimension at 3.

Suggestions

Add a per-item validation loop to the Batch Operations section and Pattern 1: after batch_poll_status, check each workflow's status and branch on 'failed' (e.g., log workflow.error_message) before accessing results, with a retry/re-submit feedback step.

Replace placeholders in the Common Patterns examples ('[x, y, z]', 'compound_library', 'complex_molecule_smiles') with concrete sample values or a clearly labeled 'replace with your values' comment so the examples are copy-paste executable.

Trim the 'Why Rowan' and 'Key Capabilities' blocks (which restate the frontmatter description) or fold them into Overview to reduce redundancy and lift conciseness toward the 5 anchor.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and lean per section without explaining concepts Claude already knows, but the Overview/'Key Capabilities'/'Why Rowan' blocks restate the frontmatter's value proposition, adding minor padding that keeps it just below the 5 anchor.	4 / 5
Actionability	Core workflows 1–5 are copy-paste ready with real SMILES and values, but the 'Common Patterns' section uses placeholders like '[x, y, z]', 'compound_library', and 'complex_molecule_smiles', leaving minor execution gaps.	4 / 5
Workflow Clarity	Each workflow has a clear submit→wait→fetch→access sequence and Error Handling shows a status-check feedback loop, but the 'Batch Operations' section and Pattern 1 run batch workflows with no per-item validation, triggering the rubric's hard cap at 3 for batch operations lacking verification.	3 / 5
Progressive Disclosure	Clear section structure plus a dedicated 'Reference Documentation' block that maps all six real reference files one level deep, with inline signals like 'See references/rdkit_native.md'; docked one point because the 'Common Patterns' section duplicates concepts already shown in the core workflows.	4 / 5
	Total	15 / 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 strong, third-person description that pairs a comprehensive capability list with an explicit 'Use when' trigger clause and a well-defined niche. Its only gap is trigger-term breadth — it relies on technical jargon without synonyms or file-format tokens.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions — 'pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2)' — giving comprehensive, specific coverage rather than vague abstractions.	5 / 5
Completeness	Explicitly answers 'what' (cloud-based quantum chemistry platform with Python API and capabilities) and 'when' via the 'Use when tasks involve...' clause with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Strong domain-natural terms ('quantum chemistry calculations', 'DFT or semiempirical methods', 'protein-ligand binding predictions') that practitioners would say, but it omits common synonyms and file extensions, stopping short of the 5 anchor's comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (quantum/computational chemistry) with highly specific triggers, making overlap with other skills minimal; written in third person with no voice penalty.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/rowan/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.