rowan
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.
79
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/rowan/SKILL.mdQuality
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 clearly identifies the platform (Rowan), lists extensive specific capabilities in computational chemistry, and provides explicit trigger guidance via 'Use for' and 'Ideal for' clauses. The domain-specific terminology ensures high distinctiveness and strong trigger term coverage for the target user base. The description is comprehensive yet well-organized without unnecessary padding.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists numerous specific concrete actions: pKa prediction, macropKa prediction, conformer ensembles, tautomer ensembles, docking, analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows. This is highly specific and comprehensive. | 3 / 3 |
Completeness | Clearly answers 'what' (cloud-native molecular modeling platform with Python API, listing specific capabilities) and 'when' ('Use for pKa and macropKa prediction...', 'Ideal for programmatic batch screening, multi-step chemistry pipelines'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes many natural domain-specific keywords users would actually say: pKa, docking, conformer, tautomer, molecular dynamics, permeability, cofolding, MSA, medicinal chemistry, small-molecule, protein modeling, batch screening, HPC/GPU. These are terms a computational chemist would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — molecular modeling, medicinal chemistry, and computational chemistry workflows via a specific platform (Rowan). The domain-specific terminology (pKa, docking, cofolding, MSA) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with comprehensive, executable code examples covering the full Rowan API surface, and workflow clarity is strong with well-sequenced multi-step processes and decision trees. However, it is severely undermined by its length—it's a monolithic document that tries to be both a quick-start guide and a complete API reference, with no content split into separate files. Significant trimming and restructuring into a concise overview with linked reference materials would dramatically improve its effectiveness as a skill.
Suggestions
Split the monolithic content: move the full workflow type tables, webhook setup/handler code, pricing/credit details, and protein utilities into separate linked reference files (e.g., WORKFLOWS.md, WEBHOOKS.md, PRICING.md, PROTEINS.md), keeping SKILL.md as a concise overview with quick-start and core patterns.
Remove or drastically shorten sections that explain concepts Claude already knows (e.g., what SMILES/InChI are, what webhooks are, what HMAC signatures do) and trim the 'When to use Rowan' section which restates the overview.
Consolidate the 'Quick start' and 'Installation' sections (they're redundant) and remove the 'Summary' section which restates earlier content.
Move the end-to-end lead optimization example and the detailed decision trees to a separate EXAMPLES.md or PATTERNS.md file, linked from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~700+ lines. It includes extensive pricing tables, credit estimates, decision trees, and exhaustive workflow catalogs that could be in separate reference files. Sections like 'Access and pricing model', 'Molecule input formats', and the full workflow type tables add significant bulk. The summary section restates what was already covered. Much content explains concepts Claude can infer (e.g., what webhooks are, what SMILES is). | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready code examples for every workflow type. API calls include specific parameter names, return value access patterns, and realistic SMILES inputs. The end-to-end lead optimization example is particularly thorough with real function signatures and result handling. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit steps (submit → wait → retrieve). The end-to-end example demonstrates chaining workflows with error handling at each step. Decision trees for choosing between workflow types (pKa vs macropKa, docking vs analogue docking) provide clear guidance. Batch workflows include status polling and error recovery patterns. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The complete workflow catalog tables, webhook handler examples, pricing details, and end-to-end campaign code are all inline. Content like the full workflow type tables, webhook setup, and protein utilities should be in separate reference files linked from a concise overview. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1088 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 8 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
1420470
- 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.