bdi-mental-states

Name: bdi-mental-states
Rating: 71 (1 reviews)
Author: muratcankoylan

tessl install github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill bdi-mental-states

github.com/muratcankoylan/Agent-Skills-for-Context-Engineering

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.

Review Score

71%

Validation Score

14/16

Implementation Score

73%

Activation Score

55%

SKILL.md

Review

Evals

Generated

12 days ago

Warnings & errors only

Criteria	Score
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing

Overall Assessment

This skill provides excellent actionable RDF/Turtle examples and SPARQL queries for BDI modeling, with good progressive disclosure through referenced documentation. However, it over-explains foundational BDI concepts that Claude already knows, and the workflow for actually implementing a BDI system lacks explicit validation checkpoints and step-by-step guidance.

Suggestions

Remove or drastically condense the 'Core Concepts' section explaining what Beliefs, Desires, and Intentions are - Claude knows BDI theory; focus only on the ontology-specific patterns
Add an explicit numbered workflow for implementing BDI mental state modeling with validation steps (e.g., '1. Parse RDF context, 2. Validate against BDI ontology schema, 3. If validation fails: check X, Y, Z')
Convert the T2B2T paradigm section into a concrete step-by-step implementation guide with checkpoints rather than conceptual description

Dimension	Score	Reasoning
Conciseness	2/3	The skill contains substantial content that Claude likely already knows (basic BDI concepts, what beliefs/desires/intentions are). While the RDF examples are valuable, sections like 'Core Concepts' explain foundational BDI theory that could be trimmed significantly.
Actionability	3/3	Provides concrete, executable Turtle/RDF examples throughout, complete SPARQL queries for validation, and a Python code snippet for LAG integration. The examples are copy-paste ready and demonstrate actual implementation patterns.
Workflow Clarity	2/3	The T2B2T paradigm describes a two-phase process but lacks explicit validation checkpoints. The skill describes what to do conceptually but doesn't provide a clear step-by-step workflow with verification steps for implementing BDI models.
Progressive Disclosure	3/3	Well-structured with clear sections progressing from core concepts to integration patterns. References folder is clearly signaled with one-level-deep links to detailed documentation (bdi-ontology-core.md, rdf-examples.md, etc.).

Overall Assessment

This description excels at trigger term coverage and distinctiveness but fundamentally fails at completeness by only describing when to use the skill without explaining what it actually does. The description reads as a pure trigger list rather than a balanced skill description that would help Claude understand both the capability and appropriate usage context.

Suggestions

Add a clear 'what' statement at the beginning describing concrete capabilities (e.g., 'Models agent mental states using BDI architecture, transforms RDF data into belief structures, and generates intention-based reasoning systems.')
Restructure to lead with capabilities, then follow with 'Use when...' clause to maintain the good trigger terms while adding the missing functionality description
Include specific outputs or deliverables the skill produces (e.g., 'generates belief-desire-intention models', 'produces cognitive agent specifications')

Dimension	Score	Reasoning
Specificity	2/3	Names the domain (BDI architecture, mental state modeling) and mentions some actions like 'transform RDF to beliefs' and 'build cognitive agent', but lacks comprehensive concrete actions describing what the skill actually does beyond triggering contexts.
Completeness	1/3	The description is entirely focused on 'when' to use the skill but completely lacks the 'what does this do' component. There's no explanation of capabilities, outputs, or concrete functionality beyond trigger conditions.
Trigger Term Quality	3/3	Excellent coverage of natural trigger terms including quoted phrases ('model agent mental states', 'implement BDI architecture'), technical terms (BDI ontology, neuro-symbolic AI), and variations users might naturally say.
Distinctiveness Conflict Risk	3/3	Highly distinctive with very specific niche terminology (BDI, belief-desire-intention, RDF to beliefs, neuro-symbolic AI) that is unlikely to conflict with other skills.