molfeat

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

Quality

73%

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/pharma/molfeat/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 strong executable examples, but it is verbose and its multi-step workflows lack validation checkpoints. Most critically, it advertises reference files (references/*.md) that are not present in the bundle, breaking progressive disclosure.

Suggestions

Create the referenced bundle files (references/api_reference.md, references/available_featurizers.md, references/examples.md) and move the inline API reference, featurizer catalog, and example sections into them so the SKILL.md stays a lean overview.

Add explicit validation/verification checkpoints to the batch and modeling workflows (e.g., assert feature shape/dtype before training; verify saved config round-trips with a reload check).

Trim the glossary-style "When to Use This Skill" list and the promotional K-Dense Web section, or move them out of the core flow, to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is mostly efficient code-driven reference material, but includes padding Claude doesn't need (the "When to Use This Skill" gloss of QSAR/virtual screening, a redundant troubleshooting repeat, and the promotional K-Dense Web section) that could be tightened.	2 / 3
Actionability	Numerous fully executable, copy-paste-ready examples with real imports, concrete featurizer names, specific parameters, and expected outputs (e.g., `# (4, 2048)`), plus a useful featurizer reference table.	3 / 3
Workflow Clarity	Multi-step workflows (QSAR, virtual screening, chunked batch processing) are sequenced but lack validation/verification checkpoints and validate→fix→retry feedback loops; per the rubric, missing validation in batch operations caps this at 2.	2 / 3
Progressive Disclosure	It signals three reference files with "When to load" notes and grep tips, but those files do not exist in the bundle, and the SKILL.md itself is a monolithic wall with inline API reference and example catalogs that the structure says should be split out.	2 / 3
	Total	9 / 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.

The description is specific and uses strong, natural cheminformatics trigger terms with a clear niche. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness at 2.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when building QSAR/QSPR models, featurizing SMILES for ML, or doing virtual screening") to lift completeness to 3.

Consider adding a couple more everyday phrasings users might say (e.g., "molecular fingerprints", "molecular descriptors") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete capabilities and featurizer families ("ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features") rather than vague language, matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly answers "what" (featurization, convert SMILES to features) but has no explicit "Use when..." trigger clause; the trailing "for QSAR and molecular ML" only implies the when, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Uses natural domain terms a cheminformatics user would actually say ("SMILES", "QSAR", "molecular ML", "featurization", "ChemBERTa"), giving good coverage of likely trigger phrases.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined by specific terms (SMILES, ECFP, MACCS, QSAR, ChemBERTa), making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: about 1 hour 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.