CtrlK
BlogDocsLog inGet started
Tessl Logo

chemistry-rdkit

Computational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search. Use when working with SMILES, drug discovery, or cheminformatics tasks.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable RDKit reference with executable snippets and useful domain heuristics, well organized into clear sections. Its main weakness is workflow clarity: batch and risky operations are mentioned without explicit validation checkpoints or error-recovery feedback loops.

Suggestions

Add an explicit batch-processing workflow with a validation checkpoint, e.g. iterate SDMolSupplier, skip/flag None entries, then verify the kept count before downstream analysis.

For 3D coordinate generation, sequence the steps as a checked workflow: AddHs -> EmbedMolecule -> MMFFOptimizeMolecule -> verify convergence/energy, so failure modes are caught.

Turn the Common Pitfalls into explicit if/then recovery guidance (e.g. on kekulization error: recheck SMILES stereochemistry/valence then retry) rather than just listing the pitfalls.

DimensionReasoningScore

Conciseness

The body is a lean reference of code snippets and brief heuristic notes (e.g. "Tanimoto > 0.7 suggests structural similarity", Lipinski thresholds) with no padding explaining what RDKit or SMILES is, so every token earns its place.

3 / 3

Actionability

It provides concrete, executable RDKit calls with parameters throughout — `Chem.MolFromSmiles('CCO')`, `AllChem.GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)`, `DataStructs.TanimotoSimilarity(fp1, fp2)` — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Numbered lists within each section provide light sequencing, but there is no end-to-end workflow with validation checkpoints, and the batch-processing guidance ("iterate over SDMolSupplier, skip None entries") lacks the verify/feedback steps the rubric requires for batch operations, capping the score.

2 / 3

Progressive Disclosure

At under 50 lines with no external references needed, the well-organized section headers (Molecular I/O, Descriptors, Fingerprints, Substructure Search, etc.) satisfy the simple-skill allowance for a top score without bundle files.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, concise description that names concrete capabilities, includes an explicit Use-when trigger clause with natural domain terms, and occupies a clear distinct niche. Third-person voice is used throughout with no over-claims or fluff.

DimensionReasoningScore

Specificity

The description lists multiple concrete capability areas — "molecular analysis, descriptors, fingerprints, and substructure search" — matching the anchor that lists several specific actions rather than vague domain naming.

3 / 3

Completeness

It explicitly answers both what ("Computational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search") and when via an explicit "Use when working with..." clause.

3 / 3

Trigger Term Quality

It surfaces natural domain terms a user would actually say — "SMILES, drug discovery, or cheminformatics tasks" — giving good coverage rather than only technical jargon.

3 / 3

Distinctiveness Conflict Risk

The RDKit/cheminformatics niche with SMILES and drug-discovery triggers is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
aiming-lab/AutoResearchClaw
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.