bdi-mental-states

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.

Quality

63%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/bdi-mental-states/SKILL.md

Quality

Discovery

54%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a list of trigger conditions without explaining what the skill actually does. While it excels at providing distinctive, natural trigger terms for a specialized domain, it completely fails to describe the skill's capabilities, actions, or outputs. The description reads as a 'Use when...' clause without the preceding capability statement.

Suggestions

Add a capability statement before the trigger conditions explaining what the skill does (e.g., 'Models agent mental states using BDI architecture, transforms knowledge graphs into belief structures, and implements rational agency patterns.')

Include specific concrete actions the skill performs (e.g., 'Creates belief bases from RDF data, defines desire hierarchies, generates intention plans, validates mental state consistency')

Restructure to follow the pattern: '[What it does]. Use when [triggers]' rather than only listing when to use it

Dimension	Reasoning	Score
Specificity	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.	2 / 3
Completeness	The description only addresses 'when' (trigger conditions) but completely fails to explain 'what' the skill actually does. There's no explanation of capabilities, outputs, or functionality beyond listing trigger phrases.	1 / 3
Trigger Term Quality	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.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche with very specific technical terminology (BDI, belief-desire-intention, RDF, neuro-symbolic AI) that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 Passed

Implementation

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a comprehensive BDI modeling skill with excellent actionability through concrete RDF/Turtle examples, SPARQL queries, and integration code. The progressive disclosure is well-executed with clear navigation to reference materials. However, the content is moderately verbose with explanatory 'because' clauses throughout, and the workflow lacks explicit validation checkpoints for the multi-step T2B2T pipeline.

Suggestions

Remove or condense the 'because' explanatory clauses throughout - Claude can infer rationale from context

Add explicit validation checkpoints to the T2B2T paradigm (e.g., 'Validate belief graph consistency before Phase 2', 'Check ontology constraints after triple generation')

Consolidate the Guidelines section which largely repeats content already covered in detail above

Dimension	Reasoning	Score
Conciseness	The skill contains substantial valuable content but includes some unnecessary explanations (e.g., explaining why to separate endurants from perdurants, why to use bidirectional properties). The 'because' clauses throughout add verbosity that Claude could infer. The Guidelines section largely repeats concepts already covered in detail above.	2 / 3
Actionability	Provides fully executable Turtle/RDF examples, complete SPARQL queries, and concrete Python code for LAG integration. The T2B2T paradigm includes copy-paste ready patterns, and the Prolog rule translation is directly usable.	3 / 3
Workflow Clarity	The T2B2T paradigm describes a two-phase process but lacks explicit validation checkpoints between phases. No verification steps for checking ontology consistency after belief formation or before projecting back to RDF. The LAG integration mentions validation but doesn't detail what happens on failure beyond 'retry_with_feedback()'.	2 / 3
Progressive Disclosure	Clear structure with well-organized sections progressing from core concepts to integration patterns. References section provides one-level-deep links to internal references with clear 'Read when' guidance. Content is appropriately split between overview and detailed reference files.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Commit: 3ab8c94

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.