domains / families / agent-tooling / bdi-mental-states

bdi-mental-states

combined

This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration. This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.

When to use

• Processing external RDF context into agent beliefs about world states
• Modeling rational agency with perception, deliberation, and action cycles
• Enabling explainability through traceable reasoning chains
• Implementing BDI frameworks (SEMAS, JADE, JADEX)
• Augmenting LLMs with formal cognitive structures (Logic Augmented Generation)
• Coordinating mental states across multi-agent platforms
• Tracking temporal evolution of beliefs, desires, and intentions
• Linking motivational states to action plans

When not to use

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Skill page

Conflict

Both copies describe the same BDI mental-state modeling procedure (endurants/perdurants, cognitive chains, world-state grounding, goal-directed planning, T2B2T, C4 notation, justification, temporal validity, compositional entities, LAG integration). The muratcankoylan copy is the more complete, curated procedure: it adds explicit activation boundaries (when not to use), stronger grounding constraints, and a fuller T2B2T pipeline. The sickn33 copy adds material steps the first lacks or truncates: a full C4 notation table, a Justification/Explainability section, Temporal Dimensions with SPARQL queries, Compositional Mental Entities, and an Integration Patterns section (LAG). Because each has material steps the other lacks, crowning one would hide a real alternative.