📦
venue-templates
85Prepare Academic Venue Submissions
Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.
Research & Learning View
Skills molfeat
📦
molfeat
Content revision r1 Medium Risk 📁 Filesystem access⚙️ External commands🌐 Network access
Build Molecular Features for ML
Molecular ML projects need consistent features from SMILES and RDKit molecules. This skill guides molfeat choices, batch featurization, pretrained embeddings, caching, and QSAR workflows.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "molfeat" from https://skillstore.io/skills/k-dense-ai-molfeat.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-molfeat/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "molfeat". I have 100,000 SMILES and need features for a property model.
Expected outcome:
- Recommended starting with ECFP for speed and a strong baseline.
- Suggested chunked batch processing with parallel workers to control memory use.
- Outlined validation steps for invalid SMILES and reproducible featurizer settings.
Using "molfeat". I want to compare ChemBERTa embeddings with classical descriptors.
Expected outcome:
- Identified dependency and runtime differences for pretrained embeddings.
- Proposed a comparison plan using the same train and validation splits.
- Recommended tracking feature dimensions, runtime, and model metrics together.
Using "molfeat". I need a similarity search workflow for a compound library.
Expected outcome:
- Recommended ECFP or MAP4 depending on library size and similarity goals.
- Explained how to compute query and library features consistently.
- Suggested ranking top compounds after similarity scoring and review.
Security Audit
Medium Riskv7 • 7/5/2026 Open versioned report
Most static findings are false positives caused by Markdown code fences, inline API names, local cache examples, and documentation links. No prompt injection attempt, data exfiltration intent, or automatic command execution was found. The only semantic concern is unsafe pickle cache loading guidance without a trust warning.
4
Files scanned
1,998
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (1)
Medium
Unsafe Pickle Cache Loading in Examples
The caching examples load embeddings from pickle files without warning that pickle files must be trusted. Copying this pattern for attacker-controlled cache files can enable code execution.
Both examples use pickle.load on a local cache file. Exploitability depends on attacker control of that file, so the guidance risk is clear but contextual.
Risk Factors
📁 Filesystem access (2)
⚙️ External commands (75)
SKILL.md:28-33 SKILL.md:33-36 SKILL.md:36-37 SKILL.md:37-38 SKILL.md:38-39 SKILL.md:39-40 SKILL.md:40-46 SKILL.md:46-48 SKILL.md:48-56 SKILL.md:56-61 SKILL.md:61-63 SKILL.md:63-73 SKILL.md:73-79 SKILL.md:79-81 SKILL.md:81-91 SKILL.md:91-96 SKILL.md:96-102 SKILL.md:102-117 SKILL.md:117-121 SKILL.md:121-127 SKILL.md:127-131 SKILL.md:131-142 SKILL.md:142-149 SKILL.md:149-158 SKILL.md:158-161 SKILL.md:161-169 SKILL.md:169-172 SKILL.md:172-179 SKILL.md:179-184 SKILL.md:184-190 SKILL.md:190-193 SKILL.md:193-200 SKILL.md:200-204 SKILL.md:204-217 SKILL.md:217-221 SKILL.md:221-231 SKILL.md:231-237 SKILL.md:237-254 SKILL.md:254-258 SKILL.md:258-274 SKILL.md:274-278 SKILL.md:278-292 SKILL.md:292-296 SKILL.md:296-309 SKILL.md:309-313 SKILL.md:313-328 SKILL.md:328-334 SKILL.md:334-354 SKILL.md:354-360 SKILL.md:360-371 SKILL.md:371-375 SKILL.md:375-384 SKILL.md:384-388 SKILL.md:388-401 SKILL.md:401-405 SKILL.md:405-409 SKILL.md:409-410 SKILL.md:410-418 SKILL.md:418-419 SKILL.md:419-420 SKILL.md:420-421 SKILL.md:421-422 SKILL.md:422-423 SKILL.md:423-424 SKILL.md:424-434 SKILL.md:434-435 SKILL.md:435-436 SKILL.md:436-455 SKILL.md:455-458 SKILL.md:458-477 SKILL.md:477-483 SKILL.md:483-490 SKILL.md:490-493 SKILL.md:493-497 SKILL.md:497-501
🌐 Network access (4)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/k-dense-ai-molfeat/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-molfeat?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-molfeat?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-molfeat/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-molfeat.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
K-Dense-AI. (2026). molfeat security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-molfeat/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-molfeat-2026,
author = {K-Dense-AI},
title = {molfeat security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-molfeat/audits/7},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "molfeat security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-molfeat/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-molfeat:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
k-dense-ai-molfeat
Skillstore Score 68
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
davila7-molfeat
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 45
Architecture
85
Maintainability
87
Content
70
Community
87
Spec Compliance
What You Can Build
Prepare QSAR Features
Select fingerprints or descriptors and build reproducible inputs for property prediction models.
Build Screening Pipelines
Convert large compound libraries into features for ranking, classification, and hit selection.
Compare Molecular Embeddings
Evaluate traditional fingerprints against pretrained embeddings for chemical similarity and model performance.
Try These Prompts
Choose a Featurizer
Help me choose a molfeat featurizer for my SMILES dataset and explain the tradeoffs for QSAR modeling.
Plan Batch Featurization
Design a molfeat workflow for a large SMILES list with invalid molecule handling, parallel processing, and reproducible settings.
Compare Model Inputs
Compare ECFP, MACCS, RDKit descriptors, Mordred, and ChemBERTa features for my molecular prediction task.
Design Screening Pipeline
Create a virtual screening plan using molfeat features, scikit-learn evaluation, ranking logic, and memory-conscious batch processing.
Best Practices
- Start with fast fingerprints before testing larger pretrained embeddings.
- Save featurizer configuration and package versions for reproducible experiments.
- Use chunking and parallel processing for large molecule collections.
Avoid
- Do not compare featurizers using different train and validation splits.
- Do not ignore invalid SMILES without tracking which molecules failed.
- Do not use pretrained model caches from untrusted sources.
Frequently Asked Questions
What is molfeat used for?
Molfeat converts molecular structures into numerical features for machine learning, similarity search, and virtual screening.
Can it work with SMILES strings?
Yes. The examples show SMILES inputs and RDKit molecule inputs for calculators and transformers.
Does it include deep learning embeddings?
Yes. The skill covers pretrained transformers such as ChemBERTa, ChemGPT, GIN, and Graphormer models.
Can I use it with scikit-learn?
Yes. The skill describes scikit-learn compatible transformers, pipelines, cross-validation, and grid search workflows.
Does the skill install dependencies automatically?
No. It documents install commands and optional extras, but users must manage their environment.
Is it safe for production workflows?
It is guidance for implementation. Review dependencies, cache handling, and scientific validation before production use.
Developer Details
Author
K-Dense-AILicense
Apache-2.0 license
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/molfeatRef
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
5 downloads · 227 views
File structure
More from K-Dense-AI
View all📦
iso-13485-certification
85Prepare ISO 13485 Certification Docs
Medical device teams must create complete QMS documentation before certification audits. This skill provides templates, checklists, and gap analysis guidance for ISO 13485 readiness.
Documentation View
📦
pytdc
82Analyze therapeutic ML datasets with PyTDC
Drug discovery teams need reliable datasets and fair evaluation protocols. This skill helps Claude use PyTDC for curated therapeutic ML data, benchmark splits, metrics, and molecular oracles.
Data & Analytics View
📦
diffdock
81Run DiffDock Molecular Docking
Protein-ligand docking requires careful setup, parameter choices, and result interpretation. This skill guides DiffDock workflows for poses, confidence scores, and screening.
Research & Learning View
📦
statistical-analysis
80Analyze Research Data with Statistical Guidance
Choosing tests and reporting results can be slow and error-prone. This skill guides test selection, assumptions, effect sizes, power analysis, Bayesian options, and APA reporting.
Data & Analytics View
📦
scanpy
80Analyze Single-Cell RNA-seq with Scanpy
Single-cell RNA-seq analysis requires many linked decisions across QC, normalization, clustering, and plotting. This skill gives Claude, Codex, and Claude Code structured Scanpy workflows, reference guidance, and reusable analysis scripts.
Data & Analytics View
Related Skills
View all📦
senior-data-scientist
81Design Data Science Experiments and Models
by alirezarezvani
Data science projects often fail when experiments, features, and models lack clear statistical structure. This skill gives Claude, Codex, and Claude Code guided workflows for experimentation, feature engineering, and model review.
Data & Analytics View
📦
ml-antipattern-validator
81Validate ML Workflows for Hidden Antipatterns
by Doyajin174
ML projects can look accurate while data leakage or weak evaluation hides serious flaws. This skill guides structured checks for splits, metrics, training, and deployment readiness.
Data & Analytics View
📦
senior-ml-engineer
81Deploy Production ML Systems
by davila7
Production ML systems are hard to design, deploy, monitor, and improve reliably. This skill gives Claude, Codex, and Claude Code structured ML engineering guidance.
Data & Analytics View
📦
torch-geometric
80Build Graph Neural Networks with PyTorch Geometric
by davila7
Graph learning projects require specialized data structures, layers, sampling, and evaluation workflows. This skill provides PyTorch Geometric guidance, references, templates, visualization, and benchmarking utilities.
Data & Analytics View
📦
scikit-learn
80Build Scikit-Learn Machine Learning Workflows
by davila7
Classical machine learning projects require careful preprocessing, model selection, and evaluation. This skill provides scikit-learn guidance, reusable pipeline patterns, and complete examples.
Data & Analytics View
📦
when-debugging-ml-training-use-ml-training-debugger
80Debug ML Training Failures
by DNYoussef
ML training can fail through NaN loss, overfitting, slow convergence, or unstable gradients. This skill guides diagnosis, targeted fixes, validation, and reporting.
Data & Analytics View