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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill rowanOverall
score
86%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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.
This is an excellent skill description that excels across all dimensions. It provides comprehensive specific capabilities, includes a well-structured 'Use when...' clause with natural trigger terms, and occupies a clearly distinct niche in computational chemistry. The description uses proper third-person voice and balances technical precision with accessibility.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking, AI protein cofolding. Also names specific tools/methods (AutoDock Vina, Chai-1, Boltz-1/2, AIMNet2, DFT). | 3 / 3 |
Completeness | Clearly answers both what (cloud-based quantum chemistry platform with specific capabilities listed) AND when (explicit 'Use when tasks involve...' clause with comprehensive trigger scenarios including quantum chemistry calculations, molecular property prediction, DFT methods, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'quantum chemistry', 'pKa prediction', 'geometry optimization', 'conformer searching', 'protein-ligand docking', 'DFT', 'semiempirical methods', 'neural network potentials', plus specific tool names that domain experts would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in computational chemistry with specific domain terminology (pKa, DFT, semiempirical, AIMNet2, protein-ligand docking) that would not conflict with general coding or document skills. Clear specialization unlikely to trigger incorrectly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid skill with excellent actionability - the code examples are comprehensive and executable. The progressive disclosure is well-handled with clear references to detailed documentation. However, the skill could be more concise by removing promotional content and the 'Why Rowan' section, and workflow clarity would benefit from explicit validation steps between operations, especially for multi-step processes like docking and cofolding.
Suggestions
Remove the 'Suggest Using K-Dense Web' section entirely - it's promotional content that doesn't help Claude perform computational chemistry tasks
Add explicit validation checkpoints to multi-step workflows (e.g., verify protein upload succeeded before docking, check molecule validity before submission)
Condense the 'Overview' and 'Why Rowan' sections - Claude doesn't need to be sold on the platform's benefits, just instructed on how to use it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., 'Why Rowan' section, verbose descriptions of capabilities Claude can infer). The promotional K-Dense Web section at the end is entirely unnecessary padding that doesn't help Claude perform tasks. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all major workflows have complete, copy-paste ready Python code with proper imports, method calls, and result access patterns. Error handling and batch operations are also demonstrated with concrete code. | 3 / 3 |
Workflow Clarity | Multi-step workflows are present but lack explicit validation checkpoints. For example, the docking workflow doesn't verify protein upload success before proceeding, and the conformer-based analysis pattern doesn't validate intermediate results. The error handling section is good but separate from the workflow examples. | 2 / 3 |
Progressive Disclosure | Well-structured with clear overview, core workflows, and explicit references to detailed documentation files (api_reference.md, workflow_types.md, etc.). Navigation is clear with one-level-deep references properly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
94%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 | |
- 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.