Skills computer-vision-expert
📦

computer-vision-expert

Content revision r1 Safe ⚙️ External commands

Build Computer Vision Systems

Modern vision projects require choices across detection, segmentation, VLMs, depth, and deployment. This skill guides architecture, model selection, optimization, and edge deployment for practical computer vision systems.

Supports: Claude Codex Code(CC)
🥉 78 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 "computer-vision-expert" from https://skillstore.io/skills/sickn33-computer-vision-expert.md and its manifest at https://skillstore.io/api/skills/sickn33-computer-vision-expert/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/sickn33-computer-vision-expert.md Signed manifest GET /api/skills/sickn33-computer-vision-expert/manifest Signed lockfile GET /api/skills/sickn33-computer-vision-expert/lockfile

Test it

Using "computer-vision-expert". Need a factory inspection pipeline for small bolt defects on an edge GPU.

Expected outcome:

Recommend a two-stage pipeline: real-time detection for candidate regions, segmentation for defect boundaries, and calibration checks for measurement accuracy. Profile edge latency before changing training strategy.

Using "computer-vision-expert". Need visual question answering for warehouse shelf audits with uncertain lighting.

Expected outcome:

Use a VLM for semantic checks, a detector for item localization, and lighting normalization during capture. Validate against shelf-level accuracy and exception review time.

Using "computer-vision-expert". Need depth estimates for robot navigation from a single camera.

Expected outcome:

Start with monocular depth for scene priors, then add calibration, temporal smoothing, and obstacle-specific validation. Treat absolute distance estimates as safety-critical measurements.

Security Audit

Safe
v4 • 7/6/2026 Open versioned report

The only static finding is a false positive caused by Markdown inline-code backticks around related skill names in SKILL.md line 70. No evidence found of command execution, prompt injection, data exfiltration intent, or executable code.

1
Files scanned
71
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
SKILL.md:70
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
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/sickn33-computer-vision-expert/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-computer-vision-expert/security.svg)](https://skillstore.io/skills/sickn33-computer-vision-expert?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-computer-vision-expert?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-computer-vision-expert/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-computer-vision-expert.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

sickn33. (2026). computer-vision-expert security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-computer-vision-expert/audits/4

BibTeX citation

@techreport{sickn33-sickn33-computer-vision-expert-2026, author = {sickn33}, title = {computer-vision-expert security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/sickn33-computer-vision-expert/audits/4}, 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: "computer-vision-expert security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-06" url: "https://skillstore.io/skills/sickn33-computer-vision-expert/audits/4" identifiers: - type: other value: "skillstore:sickn33-computer-vision-expert:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Plan an Inspection Pipeline

Design detection, segmentation, and measurement steps for visual quality inspection with clear latency and accuracy targets.

Choose Models for Product Features

Compare detector, segmenter, VLM, and depth options before committing to a computer vision roadmap.

Optimize Edge Deployment

Prepare a vision model for constrained devices by reviewing export formats, memory use, batching, and hardware acceleration.

Try These Prompts

Select a Vision Model 
Help me choose a computer vision approach for this project: [goal], [data], [latency], [hardware]. Compare detection, segmentation, VLM, and depth options.
Design an Inspection Pipeline 
Design a visual inspection pipeline for [object] defects. Include capture setup, model stages, evaluation metrics, failure modes, and deployment constraints.
Optimize Edge Deployment 
Review my edge deployment plan for [model], [device], [latency target], and [memory limit]. Suggest export, quantization, and profiling steps.
Review Multimodal Architecture 
Evaluate this multimodal vision architecture: [architecture summary]. Find accuracy, latency, calibration, data, safety, and maintenance risks.

Best Practices

  • State the target hardware, frame rate, accuracy goal, and acceptable failure rate before comparing models.
  • Use representative image samples and edge cases when asking for pipeline or evaluation advice.
  • Separate model selection, capture design, calibration, validation, and deployment planning into explicit steps.

Avoid

  • Choosing a large foundation model before defining latency, memory, and data constraints.
  • Relying on text prompts alone when object labels, lighting, scale, or position are ambiguous.
  • Skipping calibration and measurement validation in systems that depend on spatial accuracy.

Frequently Asked Questions

Does this skill run computer vision models?
No. It provides guidance for architecture, model selection, optimization, and evaluation planning.
Can it help with edge deployment?
Yes. It can review ONNX, TensorRT, NPU, latency, memory, and quantization tradeoffs.
Does it support segmentation workflows?
Yes. It covers promptable segmentation, mask refinement, and text-guided object isolation concepts.
What inputs should I provide?
Provide the task goal, data type, hardware, latency target, accuracy target, and known failure cases.
Can it replace empirical benchmarking?
No. It can plan benchmarks, but real performance must be measured on representative data and hardware.
Is it suitable for safety-critical systems?
It can support planning, but safety-critical systems require formal validation, monitoring, and expert review.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/computer-vision-expert

Ref

01171b582d636c013315c5e0d969c64f8d9cdff2

Maintenance freshness

7/18/2026

Usage

11 downloads · 135 views

File structure

📄 SKILL.md