skills.rest
gtbauke
gtbaukeCOMMUNITY
Explore all skills by this author →
GitHub

bdi-mental-states

Transform RDF context into BDI agent mental states using formal ontology patterns.

Updated Feb 20, 2026
Search Tags:#ontology#multi-agent systems#neuro-symbolic#sparql#rdf#bdi#mental states
One-click install
npx skills add https://github.com/gtbauke/bj-utils --skill bdi-mental-states-gtbauke
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bdi-mental-states
Source: https://github.com/gtbauke/bj-utils/tree/main/.agent/skills/bdi-mental-states
Command: npx skills add https://github.com/gtbauke/bj-utils --skill bdi-mental-states-gtbauke

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdflib, and includes references (resource) components.

What problem does it solve? Modeling agent cognition with beliefs, desires, and intentions requires a formal ontology to keep reasoning traceable and interoperable. This Skill provides the patterns to convert external RDF context into structured BDI mental states and back, enabling explainable deliberative reasoning in multi-agent and neuro-symbolic systems. ## Core Features & Use Cases - T2B2T Pipeline: Translate incoming RDF triples into beliefs, run BDI deliberation, and project results back into RDF for downstream linked-data consumers. - Cognitive Chain Modeling: Wire beliefs, desires, and intentions with bidirectional properties (motivates/isMotivatedBy, fulfils/isFulfilledBy) for forward reasoning and backward explainability tracing. - Framework Integration: Deploy mental state models to SEMAS production rules, JADE/JADEX agents, or Logic Augmented Generation pipelines that constrain LLM outputs with ontology validation. - Use Case: A payment-notification agent receives an RDF world state, forms a justified belief, derives a desire and intention with a task-ordered plan, executes it, and emits the resulting world state as new triples. ## Quick Start Model the agent's beliefs, desires, and intentions from this RDF context using the BDI ontology patterns, including justifications and temporal validity intervals.

Frequently Asked Questions about bdi-mental-states

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I model BDI agent mental states in RDF?▼

Model beliefs, desires, and intentions as endurant classes linked by motivates and fulfils properties, grounded in WorldState references via refersTo. Add Justification instances and TimeInterval validity bounds to each mental entity for traceability and temporal reasoning.

What is the T2B2T paradigm in BDI modeling?▼

T2B2T (Triples-to-Beliefs-to-Triples) is a bidirectional pipeline where incoming RDF triples are translated into belief instances via BeliefProcess entities, BDI deliberation selects intentions and plans, and execution results are projected back into RDF using bringsAbout.

Can BDI ontology models integrate with JADE or JADEX agents?▼

Yes, mental states stored as RDF can be mapped to JADE agent belief sets and JADEX goal structures, with SPARQL ASK queries driving goal target and drop conditions. The ontology also exports to SEMAS production rules for rule-based platforms.

How does Logic Augmented Generation constrain LLM outputs?▼

LAG serializes the BDI ontology into the LLM prompt context, then validates generated triples against ontological restrictions such as intentions fulfilling desires and beliefs referencing world states. Invalid output triggers retry with error feedback.

Why do BDI beliefs need temporal validity intervals?▼

Without hasValidity intervals, stale beliefs persist indefinitely and conflict detection becomes impossible. Temporal bounds enable SPARQL queries filtering mental states active at a specific moment and support garbage collection of expired beliefs.

What are common mistakes when implementing a BDI ontology?▼

Common pitfalls include conflating mental states with world states, omitting justifications, mapping intentions directly to actions without a plan layer, and building belief chains deeper than three levels, which inflates LLM inference cost without improving decisions.

Related Skills

Explore More Software Engineering Skills→
danbridanbri
1

tna-legislation

Retrieve UK legislation as Linked Data via content negotiation and RDF serialization.

Community
Advanced
khrorekhrore

bdi-mental-states

Transform RDF context into BDI mental states with Turtle triples and SPARQL validation.

Community
Advanced
muratcankoylanmuratcankoylan
17.7k

bdi-mental-states

Translate agent cognition prompts into RDF-based BDI mental states linked to world states.

Community
Advanced
christhz666christhz666

bdi-mental-states

Model agent beliefs, desires, and intentions from RDF context using BDI ontology patterns.

Community
Advanced