CtrlK
BlogDocsLog inGet started
Tessl Logo

rowan

Cloud-based quantum chemistry platform providing a Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformational search, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Suitable for tasks involving quantum chemistry calculations, molecular property prediction, DFT or semi-empirical methods, neural network potentials (AIMNet2), protein-ligand binding prediction, or automated computational chemistry pipelines. Provides cloud computing resources without local installation.

64

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/rowan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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.

The body is strong on actionability with concrete, executable code across the major workflows and well-organized one-level-deep references, but it is weighed down by generic templated boilerplate and lacks validation checkpoints around its batch operations.

Suggestions

Remove or collapse the generic boilerplate sections (When to Use, Implementation Details, Output Contract, Validation and Safety Rules, Failure Handling, Quick Validation, Required Inputs) that restate process truisms and duplicate the description, keeping only domain-specific guidance.

Add explicit validation/verification checkpoints to the batch-operation and virtual-screening patterns (e.g., check every workflow status, retry failures, report incomplete results) so the batch workflow has a clear feedback loop.

Trim the inlined full code examples and Common Patterns into the reference files, leaving a lean overview in SKILL.md that points to them, to reduce token cost while preserving actionability.

DimensionReasoningScore

Conciseness

The technical sections (code examples, methods, references) are efficient, but the body carries substantial generic boilerplate—'When to Use', 'Implementation Details', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation'—that states process truisms Claude already knows and re-states the description verbatim in 'Key Features'.

3 / 5

Actionability

Provides multiple concrete, largely copy-paste-ready code blocks (pKa, conformer search, optimization, docking, cofolding, RDKit-native, batch ops, error handling), with only minor gaps such as a missing stjames import in the docking block and placeholder variables (mol1, compound_library, [x, y, z]).

4 / 5

Workflow Clarity

The submit → wait_for_result → fetch_latest → access pattern is clearly sequenced with status checking, but the batch operations (batch_submit_workflow, virtual screening) lack explicit validation/verification checkpoints, which caps workflow clarity per the batch-operation rule.

3 / 5

Progressive Disclosure

Six reference files exist and are clearly signaled one level deep with one-line descriptions in the 'Reference Documentation' section, and content is appropriately split; however the body itself inlines a large volume of full workflow examples and generic sections rather than trimming to a lean overview.

4 / 5

Total

14

/

20

Passed

Description

100%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.

The description is specific, trigger-rich, and clearly demarcates a distinct niche; it answers both what the skill does and when to use it with concrete, domain-natural language and no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'pKa prediction, geometry optimization, conformational search, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2)'—with comprehensive coverage of the platform's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (cloud-based quantum chemistry platform with a Python API and a concrete capability list) and 'when' via equivalent explicit trigger guidance ('Preferred for... workflows including', 'Suitable for tasks involving...').

5 / 5

Trigger Term Quality

Covers the natural domain vocabulary a computational chemist would actually say—pKa prediction, docking, geometry optimization, DFT, semi-empirical, neural network potentials, protein-ligand binding—including synonyms and named methods (AIMNet2, AutoDock Vina).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (cloud quantum chemistry / computational chemistry pipelines) with distinct technical triggers, making overlap with unrelated skills minimal.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (527 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

13

/

16

Passed

Repository
aipoch/medical-research-skills
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.