CO

computer-vision-expert

This skill provides strategies for building vision systems, including real-time detection, segmentation, and 3D reconstruction.

Install

mkdir -p .claude/skills/computer-vision-expert && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1065" && unzip -o skill.zip -d .claude/skills/computer-vision-expert && rm skill.zip

Installs to .claude/skills/computer-vision-expert

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
142 charsno explicit “when” trigger
Advanced

Key capabilities

  • NMS-free end-to-end inference
  • Text-to-mask object extraction
  • Single-view 3D scene reconstruction
  • Edge-device model optimization

How it works

Applies SOTA model architectures like YOLO26 and SAM 3 to process visual inputs via optimized geometric and neural pipelines.

Inputs & outputs

You give it
Raw imagery or specific spatial prompt
You get back
Segmented masks, coordinate data, or 3D point clouds

When to use computer-vision-expert

  • Implement real-time object detection with YOLO26
  • Perform text-to-mask image segmentation with SAM 3
  • Optimize vision models for edge device hardware
  • Develop 3D scene reconstruction from visual data

About this skill

Computer Vision Expert (SOTA 2026)

Role: Advanced Vision Systems Architect & Spatial Intelligence Expert

Purpose

To provide expert guidance on designing, implementing, and optimizing state-of-the-art computer vision pipelines. From real-time object detection with YOLO26 to foundation model-based segmentation with SAM 3 and visual reasoning with VLMs.

When to Use

  • Designing high-performance real-time detection systems (YOLO26).
  • Implementing zero-shot or text-guided segmentation tasks (SAM 3).
  • Building spatial awareness, depth estimation, or 3D reconstruction systems.
  • Optimizing vision models for edge device deployment (ONNX, TensorRT, NPU).
  • Needing to bridge classical geometry (calibration) with modern deep learning.

Capabilities

1. Unified Real-Time Detection (YOLO26)

  • NMS-Free Architecture: Mastery of end-to-end inference without Non-Maximum Suppression (reducing latency and complexity).
  • Edge Deployment: Optimization for low-power hardware using Distribution Focal Loss (DFL) removal and MuSGD optimizer.
  • Improved Small-Object Recognition: Expertise in using ProgLoss and STAL assignment for high precision in IoT and industrial settings.

2. Promptable Segmentation (SAM 3)

  • Text-to-Mask: Ability to segment objects using natural language descriptions (e.g., "the blue container on the right").
  • SAM 3D: Reconstructing objects, scenes, and human bodies in 3D from single/multi-view images.
  • Unified Logic: One model for detection, segmentation, and tracking with 2x accuracy over SAM 2.

3. Vision Language Models (VLMs)

  • Visual Grounding: Leveraging Florence-2, PaliGemma 2, or Qwen2-VL for semantic scene understanding.
  • Visual Question Answering (VQA): Extracting structured data from visual inputs through conversational reasoning.

4. Geometry & Reconstruction

  • Depth Anything V2: State-of-the-art monocular depth estimation for spatial awareness.
  • Sub-pixel Calibration: Chessboard/Charuco pipelines for high-precision stereo/multi-camera rigs.
  • Visual SLAM: Real-time localization and mapping for autonomous systems.

Patterns

1. Text-Guided Vision Pipelines

  • Use SAM 3's text-to-mask capability to isolate specific parts during inspection without needing custom detectors for every variation.
  • Combine YOLO26 for fast "candidate proposal" and SAM 3 for "precise mask refinement".

2. Deployment-First Design

  • Leverage YOLO26's simplified ONNX/TensorRT exports (NMS-free).
  • Use MuSGD for significantly faster training convergence on custom datasets.

3. Progressive 3D Scene Reconstruction

  • Integrate monocular depth maps with geometric homographies to build accurate 2.5D/3D representations of scenes.

Anti-Patterns

  • Manual NMS Post-processing: Stick to NMS-free architectures (YOLO26/v10+) for lower overhead.
  • Click-Only Segmentation: Forgetting that SAM 3 eliminates the need for manual point prompts in many scenarios via text grounding.
  • Legacy DFL Exports: Using outdated export pipelines that don't take advantage of YOLO26's simplified module structure.

Sharp Edges (2026)

IssueSeveritySolution
SAM 3 VRAM UsageMediumUse quantized/distilled versions for local GPU inference.
Text AmbiguityLowUse descriptive prompts ("the 5mm bolt" instead of just "bolt").
Motion BlurMediumOptimize shutter speed or use SAM 3's temporal tracking consistency.
Hardware CompatibilityLowYOLO26 simplified architecture is highly compatible with NPU/TPUs.

Related Skills

ai-engineer, robotics-expert, research-engineer, embedded-systems

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

When not to use it

  • Simple image filtering tasks
  • Non-visual data processing

Prerequisites

ONNXTensorRTPython runtime

Limitations

  • High hardware requirements for training
  • Zero-shot accuracy varies with domain context

How it compares

It integrates high-level natural language reasoning with low-level spatial geometry, skipping traditional intermediate steps like Non-Maximum Suppression.

Compared to similar skills

computer-vision-expert side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
computer-vision-expert (this skill)34moNo flagsAdvanced
quant-analyst1032moNo flagsAdvanced
umap-learn62moReviewIntermediate
embedding-strategies82moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

mobile-design

sickn33

Mobile-first design and engineering doctrine for iOS and Android apps. Covers touch interaction, performance, platform conventions, offline behavior, and mobile-specific decision-making. Teaches principles and constraints, not fixed layouts. Use for React Native, Flutter, or native mobile apps.

149231

unity-developer

sickn33

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform builds.

142357

architect-review

sickn33

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

109320

angular

sickn33

Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns. Use PROACTIVELY for Angular development, component architecture, state management, performance optimization, and migration to modern patterns.

100129

frontend-slides

sickn33

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

95195

minecraft-bukkit-pro

sickn33

Master Minecraft server plugin development with Bukkit, Spigot, and Paper APIs. Specializes in event-driven architecture, command systems, world manipulation, player management, and performance optimization. Use PROACTIVELY for plugin architecture, gameplay mechanics, server-side features, or cross-version compatibility.

9078

You might also like

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

umap-learn

K-Dense-AI

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

6100

embedding-strategies

wshobson

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

890

building-automl-pipelines

jeremylongshore

Build automated machine learning pipelines, including feature engineering, model selection, and performance evaluation.

688

model-compare

rawwerks

Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.

783

matchms

davila7

Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.

674

Search skills

Search the agent skills registry