ai-safety

Estrelas0

Forks0

Atualizado2 de março de 2026 às 08:21

Implement and review child-safe AI behavior, moderation gates, parent controls, and auditability for Ollama tool-calling features.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

jakubkrzysztofsikora

jakubkrzysztofsikora/choyce-engine

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de segurança da informaçãoInformática e Matemática·SOC 15-1212

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	ai-safety
description	Implement and review child-safe AI behavior, moderation gates, parent controls, and auditability for Ollama tool-calling features.

AI Safety Skill

Required controls

Input moderation before LLM call.
Output moderation before user rendering/apply.
Parent approval for high-impact changes.
Structured audit event for each AI action.
Revert path for each AI mutation.

See references/policy-matrix.md for mode-specific restrictions.

Mais deste repositório

mesmo repositório

dev-review

jakubkrzysztofsikora/choyce-engine

Perform cross-agent code and design reviews with explicit findings, severity, and decision outputs.

2026-03-020

gameplay-loop

jakubkrzysztofsikora/choyce-engine

Design simple, age-appropriate sandbox/tycoon gameplay loops and progression with hint scaffolding for ages 6-8.

2026-03-020

hex-architecture

jakubkrzysztofsikora/choyce-engine

Apply hexagonal architecture boundaries for game engine domain, ports, and adapters in the Godot+Ollama stack.

2026-03-020

orchestrator

jakubkrzysztofsikora/choyce-engine

Delegate work into small specialized tasks, assign to agent CLIs, and enforce cross-agent review for this repository's Godot+Ollama kid-safe architecture.

2026-03-020