datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/datamol/SKILL.md

Quality

Content

65%

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

The content is highly actionable with extensive executable code across ten well-organized workflows. It is weakened by verbosity and repetition, missing explicit validation checkpoints in batch pipelines, and references to a references/ directory that does not exist.

Suggestions

Create the referenced files under references/ (io_module.md, core_api.md, conformers_module.md, descriptors_viz.md, fragments_scaffolds.md, reactions_data.md) or remove the broken 'Refer to' pointers so navigation is not misleading.

Add explicit validation feedback loops to batch/destructive workflows (e.g. after standardization, gate downstream descriptor computation on a verified valid-molecule set before proceeding).

Tighten redundant sections such as the repeated scaffold-grouping code and remove background explanations of concepts Claude already knows to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is ~700 lines with mostly executable code that assumes competence, but it is padded by repeated patterns (scaffold grouping recurs several times) and explanatory comments on concepts Claude already knows, so it could be tightened rather than reaching fully lean token efficiency.	2 / 3
Actionability	Provides numerous complete, copy-paste-ready, executable code blocks (e.g. dm.to_mol, dm.read_sdf, dm.descriptors.compute_many_descriptors) with concrete parameters, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Multi-step pipelines like the loading→filtering→analysis flow are numbered and sequenced, but validation/checkpoint feedback loops for batch and destructive operations are mostly implicit rather than explicit 'validate then proceed' gates, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Reference files are signaled one level deep (e.g. 'Refer to references/io_module.md'), but the actual references/ directory does not exist so the links are broken, and a large amount of content that could live in those files remains inline in the overview.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 and well-differentiated, naming concrete cheminformatics capabilities and clarifying its relationship to RDKit. Its main weakness is the absence of an explicit 'Use when...' trigger, which weakens both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when working with molecules, SMILES, SDF files, or standard drug-discovery workflows like descriptors, fingerprints, and clustering.'

Include common natural user phrasings such as 'molecules', 'SDF files', 'drug-likeness', or 'chemical structures' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names many concrete actions including 'SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing', matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly states what datamol does but only implies when to use it ('Preferred for standard drug discovery'); per the guidelines a missing explicit 'Use when...' trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain keywords (SMILES, descriptors, fingerprints, clustering, drug discovery) but lacks an explicit 'Use when...' clause and is missing several natural phrasings a user would actually say, so it does not reach full coverage.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Pythonic RDKit cheminformatics wrapper) and explicitly distinguishes itself from rdkit ('For advanced control or custom parameters, use rdkit directly'), making conflict unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

75%

Warnings & errors only

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

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (706 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	12 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/datamol/SKILL.md
Commit: df37802

Reviewed: 4 minutes ago

Table of Contents

Discovery Implementation Validation

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.