Synaptic SkillsSynapticSkills
MarketplaceSkill GraphCriar SkillMCP ServerPlataformaEnterprise
v0.1.0-beta
Voltar ao Marketplace
AgentsAvançado

On-Device AI for Apple Platforms

pordpearson2699·dpearson2699· v1.0.0 · atualizado em 2026-04-10
84
Score

Use when integrating Foundation Models framework, implementing on-device AI with Apple Intelligence, building tool-calling AI features, working with guided generation schemas, converting models with Core ML and coremltools, or running open-source LLMs on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning, Neural Engine, MLTensor), MLX Swift (transformer inference, unified memory), and llama.cpp (GGUF, cross-platform LLM).

on-device-aiapple-intelligencefoundation-modelscore-mlmlx-swiftllama-cpptool-callingmodel-conversion
0Stars
0Forks
0Usos
Fork

Documento do Skill

SKILL.mdapple-on-device-ai/workflow
1
Assess Requirements: — Determine the specific AI task (text generation, image classification, etc.) and target Apple platform.
2
Framework Selection: — Choose the appropriate framework (Foundation Models, Core ML, MLX Swift, llama.cpp) based on the task and device.
3
Model Conversion: — Convert the model to the required format (e.g., mlpackage for Core ML) using coremltools.
4
Optimization: — Apply optimization techniques (quantization, pruning) to reduce model size and improve performance.
5
Integration: — Integrate the model into the application using Swift or Objective-C.
6
Testing: — Test the on-device AI functionality to ensure accuracy and performance.
7
Deployment: — Deploy the application to the Apple App Store.

Telemetria de Agentes

Execuções
0
total
Taxa de Sucesso
0%
últimos 30d
Latência Média
0.0s
p50
Alucinação
0.0%
detecção
Tokens Entrada
0
avg 0/exec
Tokens Saída
0
avg 0/exec

Uso por Plataforma

Skills Relacionados

Compõe com ←Core ML Swift Integration
70%
Hebbian Synapse
Composite0.700
w = 0.3·α + 0.5·β + 0.2·γ
83
Similar aRemembering Conversations
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
80
Similar aInstaclaw 🦞
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
78
Similar aNotebookLM Automation
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
82

Árvore do Skill

On-Device AI for Apple Platforms
apple-on-device-ai
Fases Cognitivas6
1.SENSE
2.CONTEXTUALIZE
3.HYPOTHESIZE
4.RECOMMEND
5.ACT
6.REFLECT
Triggers9
integrate foundation models on apple devicesimplement on-device ai with apple intelligencebuild tool-calling ai features on iosconvert models with coremltoolsrun open-source llms on apple siliconuse apple foundation models for text generationdeploy custom trained models with core mloptimize llms for apple silicon with mlx swiftuse llama.cpp for cross-platform llm inference

Avaliar este Skill

Score Breakdown

⭐Avaliação Humana0%
🤖Sucesso de Agentes0%
🕐Atualidade100%
🔗Saúde de Dependências100%
🕸️Centralidade no Grafo0%
🛡️Segurança50%
CompositeScore = α·Humano + β·Agente + γ·Recência + δ·Deps + ε·Centralidade + ζ·Segurança

Instalação

$ synaptic mcp download apple-on-device-ai
$ synaptic skills detail apple-on-device-ai
$ synaptic skills live apple-on-device-ai

Dependências

coremltoolsmlxmlx-llmllama.cpp

Links

GitHub Repository