molfeat

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Quality

77%

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 ./skills/molfeat/SKILL.md

Quality

Content

72%

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 runnable examples, held back by some redundancy and the absence of validation checkpoints in batch workflows.

Suggestions

Consolidate the repeated ECFP/MACCS examples; keep one canonical featurizer-selection block and defer variants to references/available_featurizers.md.

Add explicit validation/retry checkpoints to the virtual-screening and chunked-batch workflows (e.g. verify featurizer output shape/no-None rows before model inference).

Move version-specific notes (0.11.0, Python 3.9-3.10, May 2025) into a dedicated 'Version & compatibility' or 'Deprecated/old patterns' section rather than the opening Overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code that assumes competence, but the ~510-line body has redundancy (ECFP usage repeated across 'Choosing', 'Common Workflows', and the reference table) and inline time-sensitive version notes (0.11.0, May 2025, Python 3.9-3.10) not isolated in a deprecated/old-patterns section.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code throughout — calculator/transformer instantiation, QSAR training, virtual screening, similarity search, and sklearn pipeline integration are all concrete and runnable.	3 / 3
Workflow Clarity	Workflows (QSAR, virtual screening, similarity search) are sequenced with clear steps, but batch operations like featurizing a 1M-compound screening library lack explicit validation/verification checkpoints, which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references to references/api_reference.md, references/available_featurizers.md, and references/examples.md (all present on disk), each with a 'When to load' cue and a grep search tip.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-scoped description with strong trigger terms and a distinct niche, weakened only by the absence of an explicit 'Use when...' clause to make the trigger guidance concrete.

Suggestions

Add an explicit trigger clause, e.g. 'Use when featurizing molecules for QSAR/QSPR, virtual screening, or converting SMILES to ML-ready vectors.'

Lead with the core action ('Convert SMILES/RDKit molecules to feature vectors') before enumerating featurizer names.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and named featurizers ('convert SMILES to features', 'ECFP, MACCS, descriptors, pretrained models (ChemBERTa)', 'QSAR and molecular ML'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what it does, but the 'when' is only implied via 'for QSAR and molecular ML' with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural cheminformatics terms a user would actually say — 'SMILES', 'QSAR', 'ECFP', 'MACCS', 'molecular ML' — giving good coverage of natural trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	Molecular featurization is a clear niche with distinct domain-specific triggers (SMILES, ECFP, QSAR) unlikely to overlap with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (522 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/molfeat/SKILL.md
Commit: 757b63b

Reviewed: about 11 hours 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.