Bdi Mental States

muratcankoylan/agent-skills-for-context-engineering

If you're building agents that need to explain their reasoning or coordinate mental states across a multi-agent system, this gives you formal BDI ontology patterns to transform RDF context into beliefs, desires, and intentions. It's built around the T2B2T paradigm (triples to beliefs to triples) with bidirectional properties like motivates/isMotivatedBy so you can trace forward (what should the agent do?) and backward (why did it act?). The skill enforces world state grounding, temporal validity intervals, and justification chains. Think JADE or JADEX frameworks but with semantic interoperability baked in. It won't help with general memory persistence or multi-agent topology decisions, but if you need traceable deliberative reasoning with Logic Augmented Generation patterns, it's the right abstraction layer.

skills.sh installs: 160
GitHub stars: 18.3K
last updated: May 26, 2026

View on GitHub

Install

$ npx -y skills add muratcankoylan/agent-skills-for-context-engineering --skill bdi-mental-states --agent claude-code

Installs into .claude/skills of the current project.

Files

BDI Mental State Modeling

Transform external RDF context into agent mental states (beliefs, desires, intentions) using formal BDI ontology patterns. This skill enables agents to reason about context through cognitive architecture, supporting deliberative reasoning, explainability, and semantic interoperability within multi-agent systems.