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.

72

Quality

90%

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

The canonical home for this skill is chemistry-rdkit in aiming-lab/AutoResearchClaw

SKILL.md
Quality
Evals
Security

Quality

Content

87%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.

An efficient, highly actionable RDKit reference with lean code patterns and good organization. The main weakness is the absence of explicit validation/feedback loops for batch operations, which caps workflow clarity.

Suggestions

Add an explicit validate-then-fix-retry loop for batch SDF/SMILES processing (e.g. check mol is not None, log skipped entries, report counts at the end) to lift workflow clarity above the batch-operation cap.

Consider framing the 'Common Pitfalls' section as ordered checkpoints within the batch-processing pattern so the validation sequence is explicit rather than scattered.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — no padding, no explanations of what RDKit/SMILES/descriptors are; every line is a concrete code pattern or terse rule that assumes Claude's competence.

5 / 5

Actionability

Fully executable, copy-paste-ready snippets (e.g. Chem.MolFromSmiles('CCO'), Descriptors.MolWt(mol), AllChem.GetMorganFingerprintAsBitVect(...)) covering the common cheminformatics cases.

5 / 5

Workflow Clarity

Content is organized as topical reference sections rather than a sequenced workflow, and batch operations (iterating SDMolSupplier) lack an explicit validate/verify feedback loop, which caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

A compact (under 50 lines), single-purpose reference with no need for external files, organized into clear well-labeled sections; per the simple-skill scoring note this earns a 5.

5 / 5

Total

18

/

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, concise description that clearly states capabilities and provides explicit trigger guidance with natural keywords. The only minor gap is the absence of additional synonyms/file extensions that would round out trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions — 'molecular analysis, descriptors, fingerprints, and substructure search' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (analysis, descriptors, fingerprints, substructure search) and 'when' via a concrete 'Use when working with SMILES, drug discovery, or cheminformatics tasks' trigger clause.

5 / 5

Trigger Term Quality

'SMILES, drug discovery, or cheminformatics tasks' gives good natural keyword coverage, but misses some common synonyms and file extensions (e.g. .sdf, 'molecules', 'compounds') that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

RDKit cheminformatics is a clear niche with distinct triggers (SMILES, drug discovery, cheminformatics) and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

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.