CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

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/datamol/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 reference body: executable code throughout, clearly sequenced pipelines with error-handling guidance, and a clean one-level reference bundle. Its weaknesses are verbosity (duplicated patterns, generic ML/sklearn filler, a promotional footer section) and a body length that inlines much of what the reference files already cover.

Suggestions

Deduplicate repeated patterns — the scaffold-to-molecules dict building appears twice and the Lipinski filter twice; keep one canonical version and reference it.

Trim or move the generic sklearn 'Integration with Machine Learning' snippet and the promotional 'K-Dense Web' footer; neither adds skill-specific capability.

Fold error handling into the pipelines themselves as inline validate-then-proceed checkpoints (as the Complete Pipeline does with notna filtering) rather than a separate section, and verify borderline API calls (dm.viz.conformers, dm.open_df, dm.reactions.apply_reaction signature) against the actual datamol API.

DimensionReasoningScore

Conciseness

The bulk is dense, datamol-specific code that earns its tokens, but there is real tightening opportunity: the Overview repeats the frontmatter description, the scaffold-to-molecules dict-building pattern appears twice (Scaffold-based analysis and train/test splitting), the Lipinski filter is written twice (is_druglike then again in the pipeline), and the sklearn 'Integration with Machine Learning' section plus the promotional K-Dense Web section explain things Claude already knows or doesn't need. This fits anchor 3 ('Mostly efficient but includes some unnecessary explanation or could be tightened') better than 2, since no section is pure concept-explanation padding.

3 / 5

Actionability

Nearly every section is copy-paste-ready executable Python with real arguments, covering the common cases end-to-end (parse, standardize, descriptors, fingerprints, clustering, conformers, viz, reactions, full pipelines). Minor gaps keep it from 5: a few calls may not match the real API as written (e.g. dm.viz.conformers vs. the conformers image helper, dm.open_df, the reactions signature), and one snippet mixes pseudo-flow ('# Handle invalid SMILES') without a concrete handler. Better than anchor 3's pseudocode/incomplete level.

4 / 5

Workflow Clarity

Multi-step workflows are explicitly numbered and sequenced (the Complete Pipeline: load → standardize → drop failures → descriptors → filter → diverse selection → visualize; Virtual Screening is numbered 1-5), and validation is addressed for batch operations (None checks after parsing, try/except in batch reactions, notna filtering), so the destructive/batch cap at 3 does not apply. It falls short of anchor 5 because validation lives in a separate 'Error Handling' section rather than being inline validate-then-proceed checkpoints with feedback loops inside the pipelines.

4 / 5

Progressive Disclosure

Structure is good: six real reference files exist, each is signaled at its point of use ('Refer to references/io_module.md for comprehensive I/O documentation') and summarized in a Reference Documentation section, and a grep confirms the references are one level deep with no further nesting. It sits at anchor 4 rather than 5 because the ~700-line SKILL.md inlines substantial per-module code that substantially overlaps the dedicated reference files for the same topics — a leaner overview would push it to 5, but a monolithic wall or buried references would drop it to 3.

4 / 5

Total

15

/

20

Passed

Description

83%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 description: specific, action-oriented, third person, with a clear what/when structure and an explicit boundary against using RDKit directly. The main gap is trigger-term breadth — it lacks the file extensions and everyday synonyms (.sdf, molecules, cheminformatics, similarity) that would make natural-language triggering more reliable.

Suggestions

Add natural trigger synonyms and file extensions, e.g. 'Use when working with molecules, SMILES/SDF/MOL files, cheminformatics, similarity analysis, or molecular data in Python'.

Make the trigger clause more explicit and second-mention friendly: 'Use for standard drug discovery tasks such as SMILES parsing...' rather than the fragment 'Preferred for standard drug discovery including...'.

Consider mentioning reading/writing molecular file formats (SDF, CSV, Excel) in the description, since I/O is a headline capability of the skill body but is absent from the description.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — "SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing" — comprehensively covering the library's scope, and adds a concrete return-type commitment ("Returns native rdkit.Chem.Mol objects"). This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage'; nothing is generic filler, so the level-4 anchor ('minor gaps in coverage') understates it.

5 / 5

Completeness

The 'what' is clear (Pythonic wrapper over RDKit with sensible defaults returning Mol objects) and the 'when' is present via "Preferred for standard drug discovery including..." plus the explicit boundary "For advanced control or custom parameters, use rdkit directly". This is equivalent explicit trigger guidance, so it clears the 3-cap; but the trigger phrasing is less direct and user-facing than "Use when...", matching anchor 4 ('Has both what and when; when could be more explicit or specific') rather than 5's concrete trigger phrasing.

4 / 5

Trigger Term Quality

Strong domain keywords users would naturally say are present: "RDKit", "SMILES", "drug discovery", "descriptors", "fingerprints", "clustering", "3D conformers". However, common natural variations are missing — file extensions (.sdf, .mol, .smi), "molecules"/"molecular", "cheminformatics", "similarity" — so it falls at anchor 4 ('Good keyword coverage; a few natural terms missing') rather than 5's 'comprehensive coverage of natural terms including synonyms and file extensions'.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche ("Pythonic wrapper around RDKit") and explicitly disambiguates against the closest competing skill — "For advanced control or custom parameters, use rdkit directly" — which is exactly the kind of boundary guidance that minimizes conflict. Cheminformatics-specific terms mean it would not trigger for unrelated skills; anchor 5 ('Clear niche with distinct triggers; minimal conflict risk') is the best fit, with no real overlap risk to justify 4.

5 / 5

Total

18

/

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.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Total

13

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/datamol/SKILL.md

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.