Agent skill

ML Cv Specialist

by alirezarezvani in alirezarezvani/claude-cto-team

Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

MITAuto-check passedAI & LLM Engineering

Install ML Cv Specialist

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ml-cv-specialist .claude/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .claude/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ml-cv-specialist .agents/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .agents/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ml-cv-specialist .cursor/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .cursor/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/alirezarezvani/claude-cto-team.git --path skills/ml-cv-specialist

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ml-cv-specialist .gemini/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .gemini/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ml-cv-specialist .github/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .github/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install alirezarezvani/claude-cto-team ml-cv-specialist --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ml-cv-specialist .opencode/skills/ml-cv-specialist && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ml-cv-specialist" agent skill from https://github.com/alirezarezvani/claude-cto-team/tree/main/skills/ml-cv-specialist into .opencode/skills/ml-cv-specialist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-cv-specialist", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: ml-cv-specialist
GitHub stars: 117
Token cost: ~3.1k tokens
SKILL.md length: 558 words
Files: 2
Skills in repo: 12
Repo updated: Dec 18, 2025
First seen: Oct 7, 2026
Licence: MIT

At a glance

Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

Designing machine learning systems
SKILL.md covers When to Use, ML System Design Framework, API vs. Self-Hosted Decision and Training Pipeline Architecture, plus 7 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Computer vision pipelines

What it does

ML Cv Specialist is an agent skill from alirezarezvani/claude-cto-team. Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `model-catalog.md`).

It sits in AI & LLM Engineering, covering Computer vision and Machine learning. It works with Amazon SageMaker and MLflow. The repository describes itself as: Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute. The licence is MIT.

When your agent uses it

Designing machine learning systems
Computer vision pipelines
AI-powered features

Example prompts

“/ml-cv-specialist”

What it can do on your machine

Read from SKILL.md and the folder at commit a5bbb78. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ML Cv Specialist loads about 3.1k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 558 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~50
When it runs · the whole SKILL.md, loaded when a task matches: ~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alirezarezvani/claude-cto-team at commit a5bbb78, republished under its MIT licence (© alirezarezvani). 558 words, ~3,080 tokens.

Download SKILL.mdSave it as .claude/skills/ml-cv-specialist/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: ml-cv-specialist
description: Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.

ML/CV Specialist

Provides specialized guidance for machine learning and computer vision system design, model selection, and production deployment.

When to Use

Selecting ML models for specific use cases
Designing training and inference pipelines
Optimizing ML system performance and cost
Evaluating build vs. API for ML capabilities
Planning data pipelines for ML workloads

ML System Design Framework

Model Selection Decision Tree

Use Case Identified
    │
    ├─► Text/Language Tasks
    │   ├─► Classification → BERT, DistilBERT, or API (OpenAI, Claude)
    │   ├─► Generation → GPT-4, Claude, Llama (self-hosted)
    │   ├─► Embeddings → OpenAI Ada, sentence-transformers
    │   └─► Search/RAG → Vector DB + Embeddings + LLM
    │
    ├─► Computer Vision Tasks
    │   ├─► Classification → ResNet, EfficientNet, ViT
    │   ├─► Object Detection → YOLOv8, DETR, Faster R-CNN
    │   ├─► Segmentation → SAM, Mask R-CNN, U-Net
    │   ├─► OCR → Tesseract, PaddleOCR, Cloud Vision API
    │   └─► Face Recognition → InsightFace, DeepFace
    │
    ├─► Audio Tasks
    │   ├─► Speech-to-Text → Whisper, DeepSpeech, Cloud APIs
    │   ├─► Text-to-Speech → ElevenLabs, Coqui TTS
    │   └─► Audio Classification → PANNs, AudioSet models
    │
    └─► Structured Data
        ├─► Tabular → XGBoost, LightGBM, CatBoost
        ├─► Time Series → Prophet, ARIMA, Transformer-based
        └─► Recommendations → Two-tower, matrix factorization

API vs. Self-Hosted Decision

When to Use APIs

Factor	API Preferred	Self-Hosted Preferred
Volume	< 10K requests/month	> 100K requests/month
Latency	> 500ms acceptable	< 100ms required
Customization	General use case	Domain-specific fine-tuning
Data Privacy	Non-sensitive data	PII, HIPAA, financial
Team Expertise	No ML engineers	ML team available
Budget	Predictable per-call costs	High volume justifies infra

Cost Comparison Framework

markdown

## API Costs (Example: OpenAI GPT-4)
- Input: $0.03/1K tokens
- Output: $0.06/1K tokens
- Average request: 500 input + 200 output tokens
- Cost per request: $0.027
- 100K requests/month: $2,700

## Self-Hosted Costs (Example: Llama 70B)
- GPU instance: $3/hour (A100 40GB)
- Throughput: ~50 requests/minute = 3K/hour
- Cost per request: $0.001
- 100K requests/month: $100 + $500 engineering time

## Break-even Analysis
- < 50K requests: API likely cheaper
- > 50K requests: Self-hosted may be cheaper
- Factor in: engineering time, ops burden, model quality

Training Pipeline Architecture

Standard ML Pipeline

┌─────────────────────────────────────────────────────────────┐
│                    DATA LAYER                                │
├─────────────────────────────────────────────────────────────┤
│  Data Sources → ETL → Feature Store → Training Data         │
│  (S3, DBs)     (Airflow)  (Feast)     (Versioned)          │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                  TRAINING LAYER                              │
├─────────────────────────────────────────────────────────────┤
│  Experiment Tracking → Training Jobs → Model Registry       │
│  (MLflow, W&B)         (SageMaker)    (MLflow, S3)         │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                  SERVING LAYER                               │
├─────────────────────────────────────────────────────────────┤
│  Model Server → Load Balancer → Monitoring                  │
│  (TorchServe)   (K8s/ELB)      (Prometheus)                │
└─────────────────────────────────────────────────────────────┘

Component Selection Guide

Component	Options	Recommendation
Feature Store	Feast, Tecton, SageMaker	Feast (open source), Tecton (enterprise)
Experiment Tracking	MLflow, Weights & Biases, Neptune	MLflow (free), W&B (best UX)
Training Orchestration	Kubeflow, SageMaker, Vertex AI	SageMaker (AWS), Vertex (GCP)
Model Registry	MLflow, SageMaker, custom S3	MLflow (standard)
Model Serving	TorchServe, TFServing, Triton	Triton (multi-framework)

Inference Architecture Patterns

Pattern 1: Synchronous API

Best for: Low-latency requirements, simple integration

Client → API Gateway → Model Server → Response
                           │
                      Load Balancer
                           │
                    ┌──────┴──────┐
                    │             │
                Model Pod    Model Pod

Latency targets:

P50: < 100ms
P95: < 300ms
P99: < 500ms

Pattern 2: Asynchronous Processing

Best for: Long-running inference, batch processing

Client → API → Queue (SQS) → Worker → Result Store → Webhook/Poll
                                          │
                                     S3/Redis

Use when:

Inference > 5 seconds
Batch processing required
Variable load patterns

Pattern 3: Edge Inference

Best for: Privacy, offline capability, ultra-low latency

┌─────────────────────────────────────────┐
│              EDGE DEVICE                 │
│  ┌─────────┐    ┌─────────────────────┐ │
│  │ Camera  │───▶│ Optimized Model     │ │
│  └─────────┘    │ (ONNX, TFLite)      │ │
│                 └─────────────────────┘ │
│                          │              │
│                     Local Result        │
└─────────────────────────────────────────┘
                           │
                    Sync to Cloud
                    (non-blocking)

Model optimization for edge:

Quantization (INT8): 4x smaller, 2-3x faster
Pruning: 50-90% sparsity possible
Distillation: Smaller model, similar accuracy
ONNX/TFLite: Optimized runtime

Computer Vision Pipeline Design

Real-Time Video Processing

Camera Stream → Frame Extraction → Preprocessing → Model → Postprocessing → Output
     │              │                   │            │           │
   RTSP/         1-30 FPS           Resize,      Batch or    NMS, tracking,
   WebRTC                           normalize    single       annotation

Performance optimization:

Process every Nth frame (skip frames)
Resize to model input size early
Batch frames when latency allows
Use GPU preprocessing (NVIDIA DALI)

Object Detection System

markdown

## Pipeline Components

1. **Input Processing**
   - Video decode: FFmpeg, OpenCV
   - Frame buffer: Ring buffer for temporal context
   - Preprocessing: NVIDIA DALI (GPU), OpenCV (CPU)

2. **Detection**
   - Model: YOLOv8 (speed), DETR (accuracy)
   - Batch size: 1-8 depending on latency requirements
   - Confidence threshold: 0.5-0.7 typical

3. **Post-processing**
   - NMS (Non-Maximum Suppression)
   - Tracking: SORT, DeepSORT, ByteTrack
   - Smoothing: Kalman filter for stable boxes

4. **Output**
   - Annotations: Bounding boxes, labels, confidence
   - Events: Trigger on detection (webhook, queue)
   - Storage: Frame + metadata to S3/DB

LLM Integration Patterns

RAG (Retrieval-Augmented Generation)

User Query → Embedding → Vector Search → Context Retrieval → LLM → Response
                              │
                         Vector DB
                       (Pinecone, Weaviate,
                        Chroma, pgvector)

Vector DB Selection:

Database	Best For	Limitations
Pinecone	Managed, scale	Cost at scale
Weaviate	Self-hosted, features	Operational overhead
Chroma	Simple, local dev	Not for production scale
pgvector	PostgreSQL users	Performance at >1M vectors
Qdrant	Performance	Newer, smaller community

Show full SKILL.md (232 more words)Show less

LLM Serving Architecture

┌─────────────────────────────────────────────────────────────┐
│                    API GATEWAY                               │
│  Rate limiting, auth, request routing                       │
└─────────────────────────────────────────────────────────────┘
                            │
              ┌─────────────┼─────────────┐
              │             │             │
              ▼             ▼             ▼
         ┌────────┐   ┌────────┐   ┌────────┐
         │ GPT-4  │   │ Claude │   │ Local  │
         │  API   │   │  API   │   │ Llama  │
         └────────┘   └────────┘   └────────┘
                            │
                    Model Router
              (cost/latency/capability)

Multi-model strategy:

Simple queries → Cheaper model (GPT-3.5, Haiku)
Complex reasoning → Expensive model (GPT-4, Opus)
Sensitive data → Self-hosted (Llama, Mistral)

Performance Optimization

GPU Memory Optimization

Technique	Memory Reduction	Speed Impact
FP16 (Half Precision)	50%	Neutral to faster
INT8 Quantization	75%	10-20% slower
INT4 Quantization	87.5%	20-40% slower
Gradient Checkpointing	60-80%	20-30% slower
Model Sharding	Distributed	Communication overhead

Batching Strategies

python

# Dynamic batching pseudocode
class DynamicBatcher:
    def __init__(self, max_batch=32, max_wait_ms=50):
        self.queue = []
        self.max_batch = max_batch
        self.max_wait = max_wait_ms

    async def add_request(self, request):
        self.queue.append(request)

        # Batch when full or timeout
        if len(self.queue) >= self.max_batch:
            return await self.process_batch()

        await asyncio.sleep(self.max_wait / 1000)
        return await self.process_batch()

    async def process_batch(self):
        batch = self.queue[:self.max_batch]
        self.queue = self.queue[self.max_batch:]
        return await self.model.predict_batch(batch)

Model Monitoring

Key Metrics to Track

Metric	What It Measures	Alert Threshold
Latency (P95)	Response time	> 2x baseline
Throughput	Requests/second	< 80% capacity
Error Rate	Failed predictions	> 1%
Model Drift	Distribution shift	PSI > 0.2
Data Quality	Input anomalies	> 5% anomalies

Drift Detection

Training Distribution ──┐
                        ├──► Statistical Test ──► Alert
Production Distribution ─┘
                         (PSI, KS test, JS divergence)

Population Stability Index (PSI):

PSI < 0.1: No significant change
0.1 < PSI < 0.2: Moderate change, monitor
PSI > 0.2: Significant change, investigate

Quick Reference Tables

Model Selection by Use Case

Use Case	Recommended Model	Latency	Cost
Text Classification	DistilBERT	10ms	Low
Text Generation	GPT-4 / Claude	1-5s	Medium
Image Classification	EfficientNet-B0	5ms	Low
Object Detection	YOLOv8-n	10ms	Low
Object Detection (Accurate)	YOLOv8-x	50ms	Medium
Semantic Segmentation	SAM	100ms	Medium
Speech-to-Text	Whisper-base	Real-time	Low
Embeddings	text-embedding-ada-002	50ms	Low

Infrastructure Sizing

Scale	GPU	Model Size	Throughput
Development	T4 (16GB)	< 7B params	10-50 req/s
Production Small	A10G (24GB)	< 13B params	50-100 req/s
Production Medium	A100 (40GB)	< 70B params	100-500 req/s
Production Large	A100 (80GB) x 2+	> 70B params	500+ req/s

References

Model Catalog - Detailed model comparison and benchmarks
Inference Patterns - Architecture patterns for different use cases

Files

SKILL.md and 1 other file in skills/ml-cv-specialist of alirezarezvani/claude-cto-team.

SKILL.md
model-catalog.md

Open the folder on GitHubat commit a5bbb78

Compare with similar skills

ML Cv Specialist next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ML Cv Specialist compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
ML Cv Specialist this skillalirezarezvani/claude-cto-team	117	—	~3.1k	Automated safety check: Pass	MIT	9 mo ago
Databricks ML Trainingdatabricks/databricks-agent-skills	345	—	~4.6k	Automated safety check: Pass	Custom licence	today
RuView Model Trainingruvnet/RuView	97k	—	~1.3k	Automated safety check: Notes	MIT	today
Adapting Transfer Learning Modelsjeremylongshore/tons-of-skills-marketplace	2.8k	—	~1.1k	Automated safety check: Pass	MIT	today
Hz Unity Passthrough Camera Accessmeta-quest/agentic-tools	215	—	~1.6k	Automated safety check: Pass	Apache-2.0	15 days ago
Ieee Transactions On Pattern Analysis And Machine Intelligencefranklee16/academic-research-skills	223	1 repos	~2k	Automated safety check: Pass	None	22 days ago

Similar skills

Databricks ML Training
databricks/databricks-agent-skills
Official
Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.
345 GitHub stars~4.6k tokensUpdated today
AI & LLM EngineeringAuto-check passed
RuView Model Training
ruvnet/RuView
Trains and evaluates several WiFi-signal-based pose and sensing models, from unsupervised pose estimation to domain adaptation and publishing.
97k GitHub stars~1.3k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Adapting Transfer Learning Models
jeremylongshore/tons-of-skills-marketplace
Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.
2.8k GitHub stars~1.1k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Hz Unity Passthrough Camera Access
meta-quest/agentic-tools
Meta Quest Passthrough Camera Access (PCA) for Unity — access the forward-facing RGB cameras on Quest 3 / Quest 3S to feed Computer Vision and Machine Learning pipelines.
215 GitHub stars~1.6k tokensUpdated 15 days ago
Game DevelopmentAuto-check passed
Ieee Transactions On Pattern Analysis And Machine Intelligence
franklee16/academic-research-skills
A skill your agent uses when targeting IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) or deciding whether a computer vision or machine learning manuscript fits this archival…
223 GitHub starsUsed in 1 repo~2k tokens
AI & LLM EngineeringAuto-check passed
Transformers.js
huggingface/skills
Official
Runs pre-trained Hugging Face models in JavaScript or TypeScript with Transformers.js, in browsers or Node.js, Bun and Deno, for text, vision, audio and multimodal tasks.
11k GitHub starsUsed in 1 repo~6.2k tokens
AI & LLM EngineeringAuto-check passed

Questions about ML Cv Specialist

What does ML Cv Specialist do?

Deep expertise in ML/CV model selection, training pipelines, and inference architecture. ML Cv Specialist is an agent skill from alirezarezvani/claude-cto-team. Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

When should I use ML Cv Specialist?

ML Cv Specialist fits situations like: designing machine learning systems; computer vision pipelines; AI-powered features.

How do I install ML Cv Specialist in Claude Code?

Run `npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a claude-code`. Or copy the skill folder (skills/ml-cv-specialist in alirezarezvani/claude-cto-team) into .claude/skills/ml-cv-specialist in your project. Claude Code loads it when a task matches its description.

How do I install ML Cv Specialist in Codex?

Run `npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a codex`. Or copy the skill folder (skills/ml-cv-specialist in alirezarezvani/claude-cto-team) into .agents/skills/ml-cv-specialist in your project. Codex loads it when a task matches its description.

Can I use ML Cv Specialist in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alirezarezvani/claude-cto-team --skill ml-cv-specialist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ml-cv-specialist, .gemini/skills/ml-cv-specialist, .github/skills/ml-cv-specialist and .opencode/skills/ml-cv-specialist in your project.

What does ML Cv Specialist need to run?

SKILL.md names no scripts, command-line tools or credentials: ML Cv Specialist is instructions for the agent only.

Does ML Cv Specialist access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is ML Cv Specialist safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ML Cv Specialist use?

ML Cv Specialist is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ML Cv Specialist use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to ML Cv Specialist?

Skills that share tags, products or a category with ML Cv Specialist: Databricks ML Training (databricks/databricks-agent-skills, 345 stars), RuView Model Training (ruvnet/RuView, 97k stars), Adapting Transfer Learning Models (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Hz Unity Passthrough Camera Access (meta-quest/agentic-tools, 215 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ML Cv Specialist?

alirezarezvani (a GitHub user) maintains it in alirezarezvani/claude-cto-team, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on December 18, 2025.

Source: alirezarezvani/claude-cto-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install ML Cv Specialist

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ML/CV Specialist

When to Use

ML System Design Framework

Model Selection Decision Tree

API vs. Self-Hosted Decision

When to Use APIs

Cost Comparison Framework

Training Pipeline Architecture

Standard ML Pipeline

Component Selection Guide

Inference Architecture Patterns

Pattern 1: Synchronous API

Pattern 2: Asynchronous Processing

Pattern 3: Edge Inference

Computer Vision Pipeline Design

Real-Time Video Processing

Object Detection System

LLM Integration Patterns

RAG (Retrieval-Augmented Generation)

LLM Serving Architecture

Performance Optimization

GPU Memory Optimization

Batching Strategies

Model Monitoring

Key Metrics to Track

Drift Detection

Quick Reference Tables

Model Selection by Use Case

Infrastructure Sizing

References

Files

Compare with similar skills

Similar skills

More from alirezarezvani/claude-cto-team

Related

Questions about ML Cv Specialist