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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/chemistry/datamol/SKILL.md

Quality

Content

80%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.

A highly actionable, well-structured skill with excellent progressive disclosure and copy-paste code; its main weakness is batch/destructive workflows that lack explicit validation checkpoints.

Suggestions

Add explicit validation checkpoints to batch workflows—e.g. after read_sdf, verify `df['mol'].notna().all()` or report the count of failed parses before proceeding.

Add a validate→fix→retry feedback loop to the batch reaction example (check product is not None / expected atom count before collecting).

Trim the recap-style 'Common Workflows' sections or cross-link them to the per-feature sections to reduce redundancy and save tokens.

Dimension	Reasoning	Score
Conciseness	Dense, mostly executable content with little padding and no over-explanation of known concepts, but the Common Workflows section partially recapitulates the per-feature sections and could be tightened.	4 / 5
Actionability	Copy-paste ready, executable code throughout with concrete function names, parameter values, and expected return shapes covering the common cheminformatics cases.	5 / 5
Workflow Clarity	Numbered pipelines (load→filter→analyze, SAR, virtual screening) are sequenced, but batch/destructive operations like clustering, batch reactions, and descriptor computation lack explicit validation checkpoints; per the rubric this caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Clear overview body with one-level-deep, clearly signaled references to real files (references/io_module.md, core_api.md, conformers_module.md, descriptors_viz.md, fragments_scaffolds.md, reactions_data.md); bulk API docs are appropriately split out.	5 / 5
	Total	17 / 20 Passed

Description

71%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 and well-scoped to the datamol/RDKit niche with strong trigger terms, but it lacks an explicit 'Use when...' trigger clause, leaving the 'when' only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with molecules, SMILES, .sdf/.smi files, or standard cheminformatics/drug-discovery tasks.'

Include file extensions and format synonyms (.sdf, .smi, SELFIES, InChI) to improve natural trigger-term coverage.

State the boundary with raw rdkit as a 'Use rdkit directly when...' sentence to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing'—with comprehensive coverage of the library's scope.	5 / 5
Completeness	Has a clear 'what' but only a weakly implied 'when' ('Preferred for standard drug discovery'); per the rubric, a missing explicit 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms (SMILES, descriptors, fingerprints, clustering, drug discovery, 3D conformers) but missing common synonyms and file extensions like SELFIES, InChI, .sdf, .smi that users would say.	4 / 5
Distinctiveness Conflict Risk	Clear RDKit-wrapper niche with an explicit boundary ('For advanced control or custom parameters, use rdkit directly'); minor overlap risk with a raw rdkit skill.	4 / 5
	Total	16 / 20 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 (710 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	12 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/datamol/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.