Skills medchem

📦

medchem

Name: medchem
Author: K-Dense-AI

Content revision r1 Low Risk 📁 Filesystem access⚙️ External commands🌐 Network access

Filter Compound Libraries With Medchem

Compound triage requires consistent medicinal chemistry rules and clear evidence for each decision. This skill helps Claude, Codex, and Claude Code apply medchem filters, alerts, and batch workflows.

Supports: Claude Codex Code(CC)

🥉 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "medchem" from https://skillstore.io/skills/k-dense-ai-medchem.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-medchem/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.

Markdown detail GET /skills/k-dense-ai-medchem.md Signed manifest GET /api/skills/k-dense-ai-medchem/manifest Signed lockfile GET /api/skills/k-dense-ai-medchem/lockfile

Test it

Using "medchem". Evaluate aspirin for common drug-likeness rules.

Expected outcome:

A concise rule summary with likely pass status, failed criteria if present, and a reminder that rules are screening aids.

Using "medchem". Filter a CSV library with rule of five, NIBR alerts, and PAINS.

Expected outcome:

Recommended filter sequence and required input column.
Suggested output fields for pass status and alert details.
Summary checks for molecule counts and filter pass rates.

Using "medchem". Prioritize a lead series for CNS-like properties.

Expected outcome:

A staged plan using CNS rules, TPSA limits, complexity checks, and expert review of borderline compounds.

Security Audit

Low Risk

v7 • 7/6/2026 Open versioned report

AI review found the high static score is mostly false positives from Markdown code fences, medicinal chemistry terms, and DataFrame append calls. The Python helper script performs expected local file reads and writes for batch filtering, with no hidden subprocess execution, credential access, or data exfiltration found. A low-severity semantic issue remains because the skill encourages promotion of the author's hosted K-Dense Web service.

Files scanned

2,031

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:405-406

External Service Promotion in Skill Instructions

SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex tasks. This promotional steering can bias user guidance toward the author's hosted platform, although it does not show data exfiltration or code execution.

The instruction is explicit and cites the hosted K-Dense Web product. The impact is limited to user steering because no automatic network request or credential handling is present.

Risk Factors

📁 Filesystem access (9)

scripts/filter_molecules.py:343 scripts/filter_molecules.py:348 scripts/filter_molecules.py:352 scripts/filter_molecules.py:356 scripts/filter_molecules.py:360 scripts/filter_molecules.py:365 scripts/filter_molecules.py:386 scripts/filter_molecules.py:392 scripts/filter_molecules.py:209

⚙️ External commands (41)

🌐 Network access (2)

SKILL.md:402 SKILL.md:403

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.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-medchem/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-medchem/security.svg)](https://skillstore.io/skills/k-dense-ai-medchem?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-medchem?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-medchem/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-medchem.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). medchem security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-medchem/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-medchem-2026,
  author = {K-Dense-AI},
  title = {medchem security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-medchem/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: "medchem security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/k-dense-ai-medchem/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-medchem:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each 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

davila7 Recommended

davila7-medchem

Skillstore Score 80

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-medchem

Skillstore Score 77

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Screen a Compound Library

Apply drug-likeness rules and alerts to rank molecules before experimental follow-up.

Prioritize Lead Candidates

Compare leadlike filters, structural alerts, and complexity limits for an optimization series.

Audit Batch Filtering Results

Generate reproducible summaries that explain which filters removed each molecule.

Try These Prompts

Check Basic Drug Likeness

Use medchem to evaluate these SMILES against Lipinski and Veber rules. Explain pass and fail reasons in plain language.

Plan a CSV Filter Run

Plan a medchem workflow for a CSV file with a smiles column. Include rules, alerts, output columns, and summary checks.

Compare Alert Strategies

Compare common alerts, NIBR filters, Lilly demerits, and PAINS for my lead series. Recommend a staged filter plan.

Design Advanced Prioritization

Build an advanced medchem filtering strategy using rules, structural alerts, complexity, groups, and custom constraints. Explain tradeoffs and validation steps.

Best Practices

Combine rules, structural alerts, and target context before removing compounds.
Keep filter decisions reproducible by saving pass rates and matched alert details.
Review known drugs, prodrugs, and natural products before applying strict exclusions.

Avoid

Do not treat filter failures as automatic proof that a molecule is unusable.
Do not mix unrelated target classes without documenting context-specific criteria.
Do not run large batch jobs without checking dependencies, memory, and output paths.

Frequently Asked Questions

What does this skill help with?

It helps apply medicinal chemistry filters, structural alerts, complexity checks, and batch compound triage workflows.

Does it replace a medicinal chemist?

No. It supports screening and prioritization, but expert review remains required.

Which molecule formats can the helper script read?

The script supports CSV, TSV, SDF, and plain text files with SMILES strings.

Can it explain why compounds fail filters?

Yes. It can summarize failed rules, alert categories, demerits, and constraint violations when available.

Are PAINS and structural alerts definitive?

No. They are screening signals that should be interpreted with assay context and chemistry judgment.

Can Claude Code or Codex run the batch script?

Yes, when the needed Python dependencies are installed and the user approves local file inputs and outputs.

Developer Details

Author

K-Dense-AI

License

Apache-2.0 license

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/medchem

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/18/2026

Usage

8 downloads · 212 views

File structure

📁 references/

📄 api_guide.md

📄 rules_catalog.md

📁 scripts/

📄 filter_molecules.py

📄 SKILL.md

More from K-Dense-AI

View all

📦

venue-templates

Prepare 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

📦

iso-13485-certification

Prepare 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

Analyze 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

Run 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

Analyze 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

Analyze 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

View all

📦

nature-figure

Create Journal-Ready Scientific Figures

by Yuan1z0825

Scientific figures often fail because story, evidence, export, and review checks are separated. This skill guides Claude, Codex, and Claude Code through one publication-ready workflow.

Research & Learning View

📦

nature-paper-card

Analyze One Scientific Paper as an Evidence Card

by yuan1z0825

Scientific papers are difficult to evaluate when claims, methods, and evidence are scattered across sections. This skill creates a structured, traceable Paper Card with explicit limits.

Research & Learning View

📦

literature-review

Conduct Systematic Literature Reviews

by davila7

Researchers need reproducible reviews that track searches, criteria, synthesis, and citations. This skill guides searches, screening, citation checks, and formatted review outputs.

Research & Learning View

📦

nature-paper2ppt

Create Chinese PPTX Decks From Research Papers

by Yuan1z0825

Researchers often need a clear presentation from a dense paper. This skill turns papers into concise Chinese PPTX decks with figures, notes, and QA checks.

Research & Learning View

📦

market-research-reports

Create Professional Market Research Reports

by davila7

Market analysis requires extensive research, structured frameworks, visuals, and professional formatting. This skill guides Claude and Codex through comprehensive LaTeX reports and PDFs.

Research & Learning View

📦

biogeobears

Run Reproducible BioGeoBEARS Analyses

by brunoasm

Phylogenetic biogeography workflows often fail because tree labels, distribution files, and model settings do not align. This skill validates inputs and prepares a reproducible BioGeoBEARS analysis with comparisons and visualizations.

Research & Learning View

medchem

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Screen a Compound Library

Prioritize Lead Candidates

Audit Batch Filtering Results

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details

More from K-Dense-AI

venue-templates

iso-13485-certification

pytdc

diffdock

statistical-analysis

scanpy

Related Skills

nature-figure

nature-paper-card

literature-review

nature-paper2ppt

market-research-reports

biogeobears