New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Model Training

by SharpAI in SharpAI/DeepCamera

Agent-driven YOLO fine-tuning — annotate, train, export, deploy

MITAuto-check passedAI & LLM Engineering

Install Model Training

skills CLI
$ npx skills add SharpAI/DeepCamera --skill model-training -a claude-code

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

GitHub CLI
$ gh skill install SharpAI/DeepCamera model-training --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/SharpAI/DeepCamera.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/training/model-training .claude/skills/model-training && 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/

Facts

Skill name
model-training
GitHub stars
3.1k
Token cost
~985 tokens
SKILL.md length
116 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Agent-driven YOLO fine-tuning — annotate, train, export, deploy

  • Tasks that involve Fine-tuning
  • SKILL.md covers What You Get, Training Loop (Aegis Training…, Protocol and Setup
  • Calls python3 and pip
  • Tasks that involve Computer vision

What it does

Model Training is an agent skill from SharpAI/DeepCamera. Agent-driven YOLO fine-tuning — annotate, train, export, deploy

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in AI & LLM Engineering, covering Fine-tuning and Computer vision. The repository describes itself as: Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent… The licence is MIT.

When your agent uses it

  • Tasks that involve Fine-tuning
  • Tasks that involve Computer vision

Example prompts

  • “/model-training”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 933dcc7. 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

    Shell commands in SKILL.md call:

    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Model Training loads about 985 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 116 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~985

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 SharpAI/DeepCamera at commit 933dcc7, republished under its MIT licence (© SharpAI). 116 words, ~985 tokens.

Download SKILL.mdSave it as .claude/skills/model-training/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
model-training
description
Agent-driven YOLO fine-tuning — annotate, train, export, deploy
version
1.0.0

Model Training

Agent-driven custom model training powered by Aegis's Training Agent. Closes the annotation-to-deployment loop: take a COCO dataset from dataset-annotation, fine-tune a YOLO model, auto-export to the optimal format for your hardware, and optionally deploy it as your active detection skill.

What You Get

  • Fine-tune YOLO26 — start from nano/small/medium/large pre-trained weights
  • COCO dataset input — uses standard format from dataset-annotation skill
  • Hardware-aware training — auto-detects CUDA, MPS, ROCm, or CPU
  • Auto-export — converts trained model to TensorRT / CoreML / OpenVINO / ONNX via env_config.py
  • One-click deploy — replace the active detection model with your fine-tuned version
  • Training telemetry — real-time loss, mAP, and epoch progress streamed to Aegis UI

Training Loop (Aegis Training Agent)

dataset-annotation          model-training              yolo-detection-2026
┌─────────────┐        ┌──────────────────┐        ┌──────────────────┐
│ Annotate    │───────▶│ Fine-tune YOLO   │───────▶│ Deploy custom    │
│ Review      │  COCO  │ Auto-export      │ .pt    │ model as active  │
│ Export      │  JSON  │ Validate mAP     │ .engine│ detection skill  │
└─────────────┘        └──────────────────┘        └──────────────────┘
       ▲                                                    │
       └────────────────────────────────────────────────────┘
                    Feedback loop: better detection → better annotation

Protocol

Aegis → Skill (stdin)
jsonl
{"event": "train", "dataset_path": "~/datasets/front_door_people/", "base_model": "yolo26n", "epochs": 50, "batch_size": 16}
{"event": "export", "model_path": "runs/train/best.pt", "formats": ["coreml", "tensorrt"]}
{"event": "validate", "model_path": "runs/train/best.pt", "dataset_path": "~/datasets/front_door_people/"}
Skill → Aegis (stdout)
jsonl
{"event": "ready", "gpu": "mps", "base_models": ["yolo26n", "yolo26s", "yolo26m", "yolo26l"]}
{"event": "progress", "epoch": 12, "total_epochs": 50, "loss": 0.043, "mAP50": 0.87, "mAP50_95": 0.72}
{"event": "training_complete", "model_path": "runs/train/best.pt", "metrics": {"mAP50": 0.91, "mAP50_95": 0.78, "params": "2.6M"}}
{"event": "export_complete", "format": "coreml", "path": "runs/train/best.mlpackage", "speedup": "2.1x vs PyTorch"}
{"event": "validation", "mAP50": 0.91, "per_class": [{"class": "person", "ap": 0.95}, {"class": "car", "ap": 0.88}]}

Setup

bash
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

© SharpAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/training/model-training of SharpAI/DeepCamera.

  • SKILL.md
  • requirements.txt

Open the folder on GitHubat commit 933dcc7

Compare with similar skills

Model Training 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.

Model Training compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Model Training this skillSharpAI/DeepCamera3.1k—~985Automated safety check: PassMIT
Hugging Face Vision Trainerhuggingface/skills11k1 repos~7.5kAutomated safety check: PassApache-2.0
Huggingface Vision Trainerwaybarrios/opencode-power-pack533—~2.7kAutomated safety check: PassApache-2.0
Hugging Face Transformers Usagedavila7/claude-code-templates32k12 repos~1.2kAutomated safety check: PassMIT
Defect Image Generation with Cosmos AnomalyGenNVIDIA/skills3.5k—~5kAutomated safety check: NotesApache-2.0
Vision Sftwshobson/agents40k—~2kAutomated safety check: PassMIT

Similar skills

  • Hugging Face Vision Trainer

    huggingface/skills

    Official

    Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

    11k GitHub starsUsed in 1 repo~7.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Huggingface Vision Trainer

    waybarrios/opencode-power-pack

    Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs.

    533 GitHub stars~2.7k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Transformers Usage

    davila7/claude-code-templates

    Loads pre-trained Hugging Face Transformers models for text, vision and audio tasks, runs inference with pipelines and fine-tunes on custom datasets.

    32k GitHub starsUsed in 12 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Defect Image Generation with Cosmos AnomalyGen

    NVIDIA/skills

    Official

    Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.5k GitHub stars~5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Vision Sft

    wshobson/agents

    Fine-tune vision-language models (VLMs) with supervised learning on image+text data.

    40k GitHub stars~2k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • 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

More from SharpAI/DeepCamera

All 15 skills in this repo

  • Dataset Annotation

    SharpAI/DeepCamera

    AI-assisted dataset annotation with COCO export — bbox, SAM2, DINOv3 methods

    3.1k GitHub stars~705 tokensUpdated 21 days ago
    Auto-check passed

  • Depth Estimation

    SharpAI/DeepCamera

    Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)

    3.1k GitHub stars~945 tokensUpdated 21 days ago
    Auto-check passed

  • Segmentation Sam2

    SharpAI/DeepCamera

    Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

    3.1k GitHub stars~594 tokensUpdated 21 days ago
    Auto-check passed

  • Yolo Detection 2026

    SharpAI/DeepCamera

    YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

    3.1k GitHub stars~1.5k tokensUpdated 21 days ago
    Auto-check passed

  • Yolo Detection 2026 Coral Tpu macOS

    SharpAI/DeepCamera

    Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

    3.1k GitHub stars~1.2k tokensUpdated 21 days ago
    Auto-check passed

  • Yolo Detection 2026 Coral Tpu Win Wsl

    SharpAI/DeepCamera

    Google Coral Edge TPU — real-time object detection natively via Windows WSL

    3.1k GitHub stars~1.1k tokensUpdated 21 days ago
    Auto-check passed

Categories

Questions about Model Training

What does Model Training do?

Agent-driven YOLO fine-tuning — annotate, train, export, deploy. Model Training is an agent skill from SharpAI/DeepCamera.

When should I use Model Training?

Model Training fits situations like: tasks that involve Fine-tuning; tasks that involve Computer vision.

How do I install Model Training in Claude Code?

Run `npx skills add SharpAI/DeepCamera --skill model-training -a claude-code`. Or copy the skill folder (skills/training/model-training in SharpAI/DeepCamera) into .claude/skills/model-training in your project. Claude Code loads it when a task matches its description.

How do I install Model Training in Codex?

Run `npx skills add SharpAI/DeepCamera --skill model-training -a codex`. Or copy the skill folder (skills/training/model-training in SharpAI/DeepCamera) into .agents/skills/model-training in your project. Codex loads it when a task matches its description.

Can I use Model Training 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 SharpAI/DeepCamera --skill model-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-training, .gemini/skills/model-training, .github/skills/model-training and .opencode/skills/model-training in your project.

What does Model Training need to run?

Going by SKILL.md and its folder, Model Training needs the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3.

Does Model Training access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Model Training 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 Model Training use?

Model Training 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 Model Training use?

About 985 tokens (SKILL.md is roughly 3.9k 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 Model Training?

Skills that share tags, products or a category with Model Training: Hugging Face Vision Trainer (huggingface/skills, 11k stars), Huggingface Vision Trainer (waybarrios/opencode-power-pack, 533 stars), Hugging Face Transformers Usage (davila7/claude-code-templates, 32k stars) and Defect Image Generation with Cosmos AnomalyGen (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Training?

SharpAI (a GitHub organization) maintains it in SharpAI/DeepCamera, which has 3,089 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 17, 2026.

Source: SharpAI/DeepCamera on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.