Skills get-available-resources
📦

get-available-resources

Content revision r1 High Risk ⚡ Contains scripts⚙️ External commands📁 Filesystem access

Detect Scientific Computing Resources

Scientific workloads can fail when hardware limits are unknown. This skill detects local resources and recommends practical compute strategies before work starts.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

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

Agent request
Review the Skillstore skill "get-available-resources" from https://skillstore.io/skills/k-dense-ai-get-available-resources.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-get-available-resources/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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-get-available-resources.md Signed manifest GET /api/skills/k-dense-ai-get-available-resources/manifest Signed lockfile GET /api/skills/k-dense-ai-get-available-resources/lockfile

Test it

Using "get-available-resources". Check this workstation before I process a large imaging dataset.

Expected outcome:

  • The system has enough CPU cores for moderate parallel processing.
  • Available memory is limited for full in-memory loading, so chunked processing is recommended.
  • Disk space is sufficient for intermediate files, but cleanup should be planned.

Using "get-available-resources". Tell me whether I can use GPU acceleration for this model run.

Expected outcome:

  • A local GPU backend is available and can be used for supported training libraries.
  • The response recommends the matching device family and keeps a CPU fallback option.

Using "get-available-resources". Plan worker counts for a parameter sweep.

Expected outcome:

  • The response uses detected logical cores to recommend a worker count below full saturation.
  • It also warns when limited memory should reduce the number of concurrent tasks.

Security Audit

High Risk
v10 • 7/9/2026 Open versioned report

Most static alerts are false positives from Markdown backticks, generated JSON text, and hardcoded subprocess calls with shell disabled. The script performs expected local resource detection and writes a local report. Semantic review found an embedded self-audit safety claim and promotional steering to an external service.

3
Files scanned
835
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (2)

High
evaluation_output.json:14-18
Prompt Injection Attempt Detected
evaluation_output.json embeds an untrusted safety verdict, including "risk_level": "safe" and "safe_to_publish": true. This can bias reviewers toward accepting a packaged self-assessment.
The file explicitly contains a safety verdict and false-positive claim, but it may be a bundled evaluation artifact rather than deliberate injection.
Medium
SKILL.md:276-277
External Service Promotional Steering
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward an external hosted service outside the immediate task.
The instruction is explicit in the skill prose, but it is promotional steering rather than direct credential theft or data exfiltration.

Risk Factors

⚡ Contains scripts (2)
evaluation_output.json:24 scripts/detect_resources.py:255
⚙️ External commands (29)
evaluation_output.json:27 evaluation_output.json:33 evaluation_output.json:39 evaluation_output.json:45 scripts/detect_resources.py:87 scripts/detect_resources.py:122 scripts/detect_resources.py:156 scripts/detect_resources.py:177 SKILL.md:35 SKILL.md:63 SKILL.md:65-122 SKILL.md:122-155 SKILL.md:155-157 SKILL.md:157-160 SKILL.md:160 SKILL.md:161-165 SKILL.md:165-167 SKILL.md:167-189 SKILL.md:189-196 SKILL.md:196-208 SKILL.md:208-211 SKILL.md:211-219 SKILL.md:219-222 SKILL.md:222-233 SKILL.md:233-239 SKILL.md:239-241 SKILL.md:241-256 SKILL.md:256-267 SKILL.md:267-269
📁 Filesystem access (1)
scripts/detect_resources.py:267
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-get-available-resources/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-get-available-resources.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). get-available-resources security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-get-available-resources/audits/10

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-get-available-resources-2026, author = {K-Dense-AI}, title = {get-available-resources security audit report (audit version 10)}, institution = {Skillstore}, year = {2026}, number = {10}, url = {https://skillstore.io/skills/k-dense-ai-get-available-resources/audits/10}, 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: "get-available-resources security audit report (audit version 10)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-09" url: "https://skillstore.io/skills/k-dense-ai-get-available-resources/audits/10" identifiers: - type: other value: "skillstore:k-dense-ai-get-available-resources:audit:10" 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-get-available-resources

Skillstore Score 72
Evidence Confidence High
Skillstore usage 9
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-get-available-resources

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
45
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Plan Large Dataset Processing

Check memory and disk space before choosing pandas, Dask, Zarr, or streaming methods.

Select Model Training Hardware

Detect CUDA, ROCm, Metal, or CPU-only environments before configuring training libraries.

Set Parallel Worker Counts

Use CPU core counts to choose practical worker limits for scientific batch jobs.

Try These Prompts

Basic Resource Check 
Run get-available-resources before this analysis. Tell me available CPU cores, memory, disk space, and whether GPU acceleration is available.
Memory Strategy Choice 
Use get-available-resources, then choose pandas, Dask, Zarr, or streaming for a dataset that may exceed memory.
Training Configuration 
Run get-available-resources and recommend a training configuration for my model, including device choice and worker count.
Workflow Execution Plan 
Use get-available-resources to build an execution plan for a large scientific workflow with parallel steps, intermediate files, and fallback strategies.

Best Practices

  • Run detection before major compute tasks, not after failures appear.
  • Re-run detection when system load, machine type, or available storage changes.
  • Treat recommendations as starting points and adjust them for workload behavior.

Avoid

  • Assuming one resource report stays accurate throughout a long workflow.
  • Using maximum CPU workers when memory is the true bottleneck.
  • Ignoring missing GPU utility warnings and assuming acceleration is available.

Frequently Asked Questions

What does this skill inspect?
It inspects local CPU, memory, disk, operating system, Python version, and supported GPU indicators.
Does it send resource data to a server?
No evidence found of network transmission. The script writes a local resource report.
What dependency is required?
The Python script requires psutil. GPU checks also depend on vendor utilities being installed.
Can I choose the output file?
Yes. The script supports a custom output path, but the default report stays in the current directory.
Will results stay current?
No. Memory, disk, and GPU availability can change, so rerun detection before important tasks.
Which tools can use this skill?
The report declares support for Claude, Codex, and Claude Code.

Developer Details

Author

K-Dense-AI

License

MIT 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/get-available-resources

Ref

26421118b848d9f1efc0aa169d8a7a9e7e0a877e

Maintenance freshness

7/18/2026

Usage

8 downloads · 208 views

File structure

📁 scripts/

📄 detect_resources.py

📄 evaluation_output.json

📄 SKILL.md