bdi-mental-states

Name: bdi-mental-states
Author: muratcankoylan

43installs1.4kforks

How to install bdi-mental-states?

muratcankoylan/agent-skills-for-context-engineering/bdi-mental-states

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill bdi-mental-states

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# BDI Mental State Modeling
2
3	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.
4
5	## When to Activate
6
7	Activate this skill when:
8	- Processing external RDF context into agent beliefs about world states
9	- Modeling rational agency with perception, deliberation, and action cycles
10	- Enabling explainability through traceable reasoning chains
11	- Implementing BDI frameworks (SEMAS, JADE, JADEX)
12	- Augmenting LLMs with formal cognitive structures (Logic Augmented Generation)
13	- Coordinating mental states across multi-agent platforms
14	- Tracking temporal evolution of beliefs, desires, and intentions
15	- Linking motivational states to action plans
16
17	Do not activate this skill for adjacent work owned by other skills:
18	- General context-window explanations or attention mechanics: `context-fundamentals`.
19	- Persistent user, entity, or conversation memory without formal BDI state: `memory-systems`.
20	- Supervisor, swarm, or handoff topology decisions: `multi-agent-patterns`.
21	- General agent evaluation rubrics or quality gates: `evaluation`.
22
23	## Core Concepts
24
25	### Mental Reality Architecture
26
27	Separate mental states into two ontological categories because BDI reasoning requires distinguishing what persists from what happens:
28
29	Mental States (Endurants) -- model these as persistent cognitive attributes that hold over time intervals:
30	- `Belief`: Represent what the agent holds true about the world. Ground every belief in a world state reference.
31	- `Desire`: Represent what the agent wishes to bring about. Link each desire back to the beliefs that motivate it.
32	- `Intention`: Represent what the agent commits to achieving. An intention must fulfil a desire and specify a plan.
33
34	Mental Processes (Perdurants) -- model these as events that create or modify mental states, because tracking causal transitions enables explainability:
35	- `BeliefProcess`: Triggers belief formation/update from perception. Always connect to a generating world state.
36	- `DesireProcess`: Generates desires from existing beliefs. Preserves the motivational chain.
37	- `IntentionProcess`: Commits to selected desires as actionable intentions.
38
39	### Cognitive Chain Pattern
40
41	Wire beliefs, desires, and intentions into directed chains using bidirectional properties (`motivates`/`isMotivatedBy`, `fulfils`/`isFulfilledBy`) because this enables both forward reasoning (what should the agent do?) and backward tracing (why did the agent act?):
42
43	```turtle
44	:Belief_store_open a bdi:Belief ;
45	rdfs:comment "Store is open" ;
46	bdi:motivates :Desire_buy_groceries .
47
48	:Desire_buy_groceries a bdi:Desire ;
49	rdfs:comment "I desire to buy groceries" ;
50	bdi:isMotivatedBy :Belief_store_open .
51
52	:Intention_go_shopping a bdi:Intention ;
53	rdfs:comment "I will buy groceries" ;
54	bdi:fulfils :Desire_buy_groceries ;
55	bdi:isSupportedBy :Belief_store_open ;
56	bdi:specifies :Plan_shopping .
57	```
58
59	### World State Grounding
60
61	Always ground mental states in world state references rather than free-text descriptions, because ungrounded beliefs break semantic querying and cross-agent interoperability:
62
63	```turtle
64	:Agent_A a bdi:Agent ;
65	bdi:perceives :WorldState_WS1 ;
66	bdi:hasMentalState :Belief_B1 .
67
68	:WorldState_WS1 a bdi:WorldState ;
69	rdfs:comment "Meeting scheduled at 10am in Room 5" ;
70	bdi:atTime :TimeInstant_10am .
71
72	:Belief_B1 a bdi:Belief ;
73	bdi:refersTo :WorldState_WS1 .
74	```
75
76	### Goal-Directed Planning
77
78	Connect intentions to plans via `bdi:specifies`, and decompose plans into ordered task sequences using `bdi:precedes`, because this separation allows plan reuse across different intentions while keeping execution order explicit:
79
80	```turtle
81	:Intention_I1 bdi:specifies :Plan_P1 .
82
83	:Plan_P1 a bdi:Plan ;
84	bdi:addresses :Goal_G1 ;
85	bdi:beginsWith :Task_T1 ;
86	bdi:endsWith :Task_T3 .
87
88	:Task_T1 bdi:precedes :Task_T2 .
89	:Task_T2 bdi:precedes :Task_T3 .
90	```
91
92	### T2B2T Paradigm
93
94	Implement Triples-to-Beliefs-to-Triples as a bidirectional pipeline because agents must both consume external RDF context and produce new RDF assertions. Structure every T2B2T implementation in two explicit phases:
95
96	Phase 1: Triples-to-Beliefs -- Translate incoming RDF triples into belief instances. Use `bdi:triggers` to connect the external world state to a `BeliefProcess`, and `bdi:generates` to produce the resulting belief. This preserves provenance from source data through to internal cognition:
97	```turtle
98	:WorldState_notification a bdi:WorldState ;
99	rdfs:comment

People who liked this also viewed

6 picks

Type

bdi-mental-states

43installs1.4kforks

View on GitHub

How to install bdi-mental-states?

muratcankoylan/agent-skills-for-context-engineering/bdi-mental-states

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill bdi-mental-states

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# BDI Mental State Modeling
2
3	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.
4
5	## When to Activate
6
7	Activate this skill when:
8	- Processing external RDF context into agent beliefs about world states
9	- Modeling rational agency with perception, deliberation, and action cycles
10	- Enabling explainability through traceable reasoning chains
11	- Implementing BDI frameworks (SEMAS, JADE, JADEX)
12	- Augmenting LLMs with formal cognitive structures (Logic Augmented Generation)
13	- Coordinating mental states across multi-agent platforms
14	- Tracking temporal evolution of beliefs, desires, and intentions
15	- Linking motivational states to action plans
16
17	Do not activate this skill for adjacent work owned by other skills:
18	- General context-window explanations or attention mechanics: `context-fundamentals`.
19	- Persistent user, entity, or conversation memory without formal BDI state: `memory-systems`.
20	- Supervisor, swarm, or handoff topology decisions: `multi-agent-patterns`.
21	- General agent evaluation rubrics or quality gates: `evaluation`.
22
23	## Core Concepts
24
25	### Mental Reality Architecture
26
27	Separate mental states into two ontological categories because BDI reasoning requires distinguishing what persists from what happens:
28
29	Mental States (Endurants) -- model these as persistent cognitive attributes that hold over time intervals:
30	- `Belief`: Represent what the agent holds true about the world. Ground every belief in a world state reference.
31	- `Desire`: Represent what the agent wishes to bring about. Link each desire back to the beliefs that motivate it.
32	- `Intention`: Represent what the agent commits to achieving. An intention must fulfil a desire and specify a plan.
33
34	Mental Processes (Perdurants) -- model these as events that create or modify mental states, because tracking causal transitions enables explainability:
35	- `BeliefProcess`: Triggers belief formation/update from perception. Always connect to a generating world state.
36	- `DesireProcess`: Generates desires from existing beliefs. Preserves the motivational chain.
37	- `IntentionProcess`: Commits to selected desires as actionable intentions.
38
39	### Cognitive Chain Pattern
40
41	Wire beliefs, desires, and intentions into directed chains using bidirectional properties (`motivates`/`isMotivatedBy`, `fulfils`/`isFulfilledBy`) because this enables both forward reasoning (what should the agent do?) and backward tracing (why did the agent act?):
42
43	```turtle
44	:Belief_store_open a bdi:Belief ;
45	rdfs:comment "Store is open" ;
46	bdi:motivates :Desire_buy_groceries .
47
48	:Desire_buy_groceries a bdi:Desire ;
49	rdfs:comment "I desire to buy groceries" ;
50	bdi:isMotivatedBy :Belief_store_open .
51
52	:Intention_go_shopping a bdi:Intention ;
53	rdfs:comment "I will buy groceries" ;
54	bdi:fulfils :Desire_buy_groceries ;
55	bdi:isSupportedBy :Belief_store_open ;
56	bdi:specifies :Plan_shopping .
57	```
58
59	### World State Grounding
60
61	Always ground mental states in world state references rather than free-text descriptions, because ungrounded beliefs break semantic querying and cross-agent interoperability:
62
63	```turtle
64	:Agent_A a bdi:Agent ;
65	bdi:perceives :WorldState_WS1 ;
66	bdi:hasMentalState :Belief_B1 .
67
68	:WorldState_WS1 a bdi:WorldState ;
69	rdfs:comment "Meeting scheduled at 10am in Room 5" ;
70	bdi:atTime :TimeInstant_10am .
71
72	:Belief_B1 a bdi:Belief ;
73	bdi:refersTo :WorldState_WS1 .
74	```
75
76	### Goal-Directed Planning
77
78	Connect intentions to plans via `bdi:specifies`, and decompose plans into ordered task sequences using `bdi:precedes`, because this separation allows plan reuse across different intentions while keeping execution order explicit:
79
80	```turtle
81	:Intention_I1 bdi:specifies :Plan_P1 .
82
83	:Plan_P1 a bdi:Plan ;
84	bdi:addresses :Goal_G1 ;
85	bdi:beginsWith :Task_T1 ;
86	bdi:endsWith :Task_T3 .
87
88	:Task_T1 bdi:precedes :Task_T2 .
89	:Task_T2 bdi:precedes :Task_T3 .
90	```
91
92	### T2B2T Paradigm
93
94	Implement Triples-to-Beliefs-to-Triples as a bidirectional pipeline because agents must both consume external RDF context and produce new RDF assertions. Structure every T2B2T implementation in two explicit phases:
95
96	Phase 1: Triples-to-Beliefs -- Translate incoming RDF triples into belief instances. Use `bdi:triggers` to connect the external world state to a `BeliefProcess`, and `bdi:generates` to produce the resulting belief. This preserves provenance from source data through to internal cognition:
97	```turtle
98	:WorldState_notification a bdi:WorldState ;
99	rdfs:comment

People who liked this also viewed

6 picks

Type