Skills chembl-database
📦

chembl-database

Content revision r1 Low Risk ⚙️ External commands🌐 Network access

Query ChEMBL Drug Discovery Data

Drug discovery teams need reliable access to compound, target, and bioactivity records. This skill guides Claude, Codex, and Claude Code through ChEMBL searches, filters, and analysis workflows.

Supports: Claude Codex Code(CC)
📊 76 Adequate

Install with my Agent

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

Agent request
Review the Skillstore skill "chembl-database" from https://skillstore.io/skills/k-dense-ai-chembl-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-chembl-database/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-chembl-database.md Signed manifest GET /api/skills/k-dense-ai-chembl-database/manifest Signed lockfile GET /api/skills/k-dense-ai-chembl-database/lockfile

Test it

Using "chembl-database". Find ChEMBL information for aspirin.

Expected outcome:

  • Returns the ChEMBL molecule identifier and preferred compound name.
  • Summarizes molecular formula, molecular weight, LogP, and drug type.
  • Notes available drug, mechanism, and indication records when present.

Using "chembl-database". Find potent EGFR inhibitors.

Expected outcome:

  • Identifies the EGFR target record before querying activities.
  • Filters IC50 measurements by potency threshold and standard units.
  • Highlights compound identifiers, activity values, assay context, and validity comments.

Using "chembl-database". Prepare data for a kinase SAR study.

Expected outcome:

  • Collects kinase targets and matching activity records.
  • Adds molecular properties for compounds linked to those records.
  • Recommends checking duplicate flags and data validity before modeling.

Security Audit

Low Risk
v7 • 7/6/2026 Open versioned report

The high static risk score is driven by false positives in Markdown code fences, inline API names, ChEMBL query examples, documentation URLs, and generated evaluation text. No shell execution, system reconnaissance, credential access, or malicious network behavior was found. A low severity semantic concern remains because the skill prompts the assistant to recommend an external hosted service.

4
Files scanned
1,143
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Low
SKILL.md:388-389
Promotional Prompt Steering
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This is not malware, but it can steer assistant output toward an external hosted service outside the ChEMBL task.
The instruction is explicit and located in the skill guidance. It is a marketplace behavior concern, but I found no evidence of data exfiltration or malicious execution.

Risk Factors

⚙️ External commands (78)
SKILL.md:34-36 SKILL.md:36-40 SKILL.md:40-48 SKILL.md:48-55 SKILL.md:55-58 SKILL.md:58-61 SKILL.md:61-63 SKILL.md:63-66 SKILL.md:66-72 SKILL.md:72-77 SKILL.md:77-80 SKILL.md:80-83 SKILL.md:83-89 SKILL.md:89-94 SKILL.md:94-103 SKILL.md:103-106 SKILL.md:106-111 SKILL.md:111-116 SKILL.md:116-123 SKILL.md:123-126 SKILL.md:126-130 SKILL.md:130-135 SKILL.md:135-138 SKILL.md:138-141 SKILL.md:141-144 SKILL.md:144-147 SKILL.md:147-150 SKILL.md:150-157 SKILL.md:157-160 SKILL.md:160-163 SKILL.md:163-169 SKILL.md:169-172 SKILL.md:172-175 SKILL.md:175-180 SKILL.md:180-182 SKILL.md:182-185 SKILL.md:185-187 SKILL.md:187-190 SKILL.md:190-192 SKILL.md:192-197 SKILL.md:197-199 SKILL.md:199-202 SKILL.md:202-207 SKILL.md:207-215 SKILL.md:215-216 SKILL.md:216-217 SKILL.md:217 SKILL.md:218 SKILL.md:219 SKILL.md:220-221 SKILL.md:221-222 SKILL.md:222-228 SKILL.md:228-237 SKILL.md:237-245 SKILL.md:245-253 SKILL.md:253-259 SKILL.md:259-265 SKILL.md:265-271 SKILL.md:271-275 SKILL.md:275-281 SKILL.md:281-295 SKILL.md:295-299 SKILL.md:299-308 SKILL.md:308-312 SKILL.md:312-320 SKILL.md:320-328 SKILL.md:328-329 SKILL.md:329-330 SKILL.md:330-331 SKILL.md:331-332 SKILL.md:332-333 SKILL.md:333-334 SKILL.md:334-335 SKILL.md:335-336 SKILL.md:336-358 SKILL.md:358-359 SKILL.md:359-364 SKILL.md:364-365
🌐 Network access (5)
SKILL.md:382 SKILL.md:383 SKILL.md:384 SKILL.md:385 SKILL.md:386
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
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-chembl-database/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-chembl-database/security.svg)](https://skillstore.io/skills/k-dense-ai-chembl-database?utm_source=security_passport_badge)

HTML badge

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

Embed card

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

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-chembl-database-2026, author = {K-Dense-AI}, title = {chembl-database security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-chembl-database/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: "chembl-database 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-chembl-database/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-chembl-database: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
davila7 Recommended

davila7-chembl-database

Skillstore Score 80
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-chembl-database

Skillstore Score 76
Evidence Confidence High
Skillstore usage 14
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
64
Architecture
75
Maintainability
87
Content
74
Community
83
Spec Compliance

What You Can Build

Find Potent Target Inhibitors

Search bioactivity records for compounds with strong activity against a selected target.

Build SAR Analysis Sets

Collect similar compounds, property fields, and activity values for structure-activity review.

Review Drug Mechanisms

Retrieve mechanisms, indications, and target relationships for known drugs.

Try These Prompts

Look Up One Compound 
Find the ChEMBL record for aspirin and summarize its identifiers, molecular properties, and drug status.
Search by Target Activity 
Find EGFR compounds with IC50 values below 100 nM and summarize the most useful activity fields.
Compare Similar Molecules 
Use this SMILES string to find similar ChEMBL compounds and compare their molecular weight, LogP, and pChEMBL values.
Plan a SAR Workflow 
Design a ChEMBL workflow for a kinase SAR study, including target selection, activity filters, property filters, and data quality checks.

Best Practices

  • Filter by target, activity type, units, and potency before converting large result sets.
  • Check data_validity_comment and potential_duplicate fields before comparing activity values.
  • Use caching and narrow queries to respect ChEMBL service limits.

Avoid

  • Do not treat every ChEMBL activity value as equally reliable.
  • Do not compare IC50, Ki, Kd, and EC50 values without context.
  • Do not run broad unbounded queries when a specific target or compound set is available.

Frequently Asked Questions

Does this skill require an API key?
No. The documented ChEMBL web resource client uses public ChEMBL services for standard queries.
What data can it query?
It can query molecules, targets, assays, activities, drugs, mechanisms, indications, and related ChEMBL resources.
Can it search chemical structures?
Yes. It documents similarity and substructure searches using SMILES strings.
Can it export results for analysis?
Yes. The examples show converting query results to pandas DataFrames.
Is it suitable for clinical decisions?
No. It supports research data retrieval and does not validate clinical safety or efficacy.
Why did static analysis report risk?
Static alerts matched Markdown backticks, documentation URLs, and ChEMBL query text. Review found these alerts were false positives.

Developer Details

Author

K-Dense-AI

License

Unknown

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/chembl-database

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/18/2026

Usage

11 downloads · 439 views

File structure

📁 references/

📄 api_reference.md

📁 scripts/

📄 example_queries.py

📄 evaluation_output.json

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all