molfeat

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

Quality

69%

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/molfeat/SKILL.md

Quality

Content

68%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 body with comprehensive executable examples and clearly signaled one-level-deep references. Its main weaknesses are redundancy that hurts conciseness and missing validation checkpoints in batch workflows that cap workflow_clarity at 3.

Suggestions

Consolidate redundancy: merge the duplicate invalid-molecule error-handling guidance between 'Quick Start' and 'Troubleshooting', and de-duplicate the ECFP/MACCS/MAP4 lists repeated across featurizer-selection subsections.

Add explicit validation checkpoints to batch workflows — e.g. after featurizing the screening library, check for None/failed entries and verify the output shape before ranking top hits.

Move extended workflow examples and detailed featurizer selection into references/examples.md and references/available_featurizers.md so the SKILL.md overview stays leaner.

Dimension	Reasoning	Score
Conciseness	The body is mostly code and actionable guidance and assumes Claude's competence, but it carries noticeable redundancy — invalid-molecule error handling appears in both 'Quick Start' and 'Troubleshooting', and ECFP/MACCS/MAP4 featurizers are re-listed across the 'Traditional ML', 'Similarity Searching', and reference-table subsections — so it could be tightened.	3 / 5
Actionability	It provides abundant copy-paste-ready, executable code covering the common cases (basic featurization, save/load config, error handling, QSAR, virtual screening, similarity search, sklearn pipeline integration, caching), with only trivial gaps such as omitted imports and a placeholder evaluate_model in the comparison example.	5 / 5
Workflow Clarity	Multi-step workflows (QSAR, virtual screening, similarity search) have clear linear sequences, but they lack explicit validation checkpoints or fix-retry feedback loops, and the 1M-compound batch screening workflow runs no validation, capping workflow_clarity at 3 per the batch-operations guideline.	3 / 5
Progressive Disclosure	Bundle files (references/api_reference.md, available_featurizers.md, examples.md) are real, one level deep, and well-signaled with 'When to load' guidance, but the overview itself inlines heavy workflow code and featurizer-selection detail that could live in the references, leaving minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

70%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 specific, domain-rich description with strong natural trigger terms and clear distinctiveness, but it lacks an explicit 'Use when...' clause, leaving the trigger guidance only weakly implied and capping completeness at 3. Action coverage is good but narrow in verbs.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when converting SMILES to ML-ready features for QSAR, virtual screening, similarity search, or molecular ML.'

Broaden trigger coverage with common synonyms a user might say, such as 'fingerprints', 'molecular descriptors', and 'RDKit'.

Consider one or two more concrete action verbs (e.g. 'compute', 'encode', 'embed') beyond 'featurization' and 'convert' to round out specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Molecular featurization for ML') and several specific concrete featurizers ('ECFP, MACCS, descriptors, pretrained models (ChemBERTa)') plus a concrete action ('convert SMILES to features'), but the action verbs are narrow (mainly featurize/convert), leaving minor coverage gaps rather than comprehensive coverage.	4 / 5
Completeness	The 'what' is clear ('Molecular featurization... convert SMILES to features'), but the 'when' is only weakly implied via 'for QSAR and molecular ML' with no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	It includes strong natural domain terms a practitioner would actually say — 'SMILES', 'QSAR', 'ECFP', 'MACCS', 'ChemBERTa', 'molecular ML' — but is missing some common variations/synonyms such as 'fingerprints', 'RDKit', or 'molecular descriptors' as a phrase, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The chemistry/cheminformatics niche ('SMILES', 'QSAR', 'ECFP', 'ChemBERTa', 'molecular featurization') is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (511 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

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/molfeat/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.