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

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bdi-mental-states/SKILL.md

Quality

Content

61%Scale 1-5

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 good concrete RDF/Turtle examples and clear structural organization. Its main weaknesses are verbosity in explaining foundational BDI concepts Claude already knows, and the lack of explicit validation workflows for ensuring ontological consistency when constructing or modifying RDF graphs. The progressive disclosure structure is reasonable but some inline content could be moved to referenced files.

Suggestions

Trim the 'Core Concepts' section to remove explanations of what beliefs, desires, and intentions are—focus only on the ontology patterns and property relationships that are specific to this implementation.

Add an explicit validation workflow: after constructing BDI triples, validate against ontology constraints (e.g., check existential restrictions), with error recovery steps if validation fails.

Make the Python LAG integration code more executable by either providing actual function implementations or replacing with a concrete library-based example.

Move the full Competency Questions SPARQL section to the referenced sparql-competency.md file and keep only 1-2 key examples inline.

Dimension	Reasoning	Score
Conciseness	The skill is quite lengthy (~250 lines) and includes explanatory content about core BDI concepts that Claude likely already knows (e.g., what beliefs, desires, and intentions are). The 'Core Concepts' section explains basic BDI theory rather than focusing purely on actionable patterns. However, the RDF examples themselves are useful and not padded.	3 / 5
Actionability	Provides concrete RDF/Turtle examples, SPARQL queries, Python code for LAG integration, and Prolog rules. The examples are mostly executable and cover common patterns. However, the Python code is pseudocode-like (serialize_ontology, extract_rdf_triples are undefined), and there's no complete end-to-end implementation example.	4 / 5
Workflow Clarity	The T2B2T paradigm describes a two-phase workflow but lacks explicit validation checkpoints or error recovery steps. The Guidelines section lists principles but doesn't sequence them as a workflow. For an ontology modeling skill that involves RDF manipulation (which can produce invalid graphs), there are no validation steps or feedback loops for checking ontological consistency.	3 / 5
Progressive Disclosure	References a `references/` folder with four specific files for detailed documentation, keeping the main skill as an overview. The structure uses clear sections with headers. However, no bundle files are provided to verify the referenced paths exist, and some content (like the full competency questions section) could arguably be in the referenced sparql-competency.md file instead of inline.	4 / 5
	Total	14 / 20 Passed

Description

47%Scale 1-5

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

The description is heavily weighted toward 'when to use' triggers but almost entirely lacks a 'what does this do' component, making it incomplete. The trigger terms are well-chosen and domain-specific, providing good distinctiveness, but the absence of concrete capability descriptions means Claude would know when to select this skill without understanding what it actually does.

Suggestions

Add a clear 'what' clause describing concrete actions, e.g., 'Generates BDI agent architectures with belief, desire, and intention modules; transforms RDF ontologies into belief representations; produces cognitive agent code with rational decision-making loops.'

Restructure to lead with capabilities before the 'Use when...' clause, following the pattern: '[What it does]. Use when [trigger conditions].'

Include mention of specific outputs or artifacts the skill produces (e.g., code files, ontology mappings, agent configurations) to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (BDI architecture, mental state modeling) but provides almost no concrete actions. Phrases like 'model agent mental states' and 'implement BDI architecture' hint at actions but remain generic and lack detail about what the skill actually does (e.g., what outputs it produces, what transformations it performs).	2 / 5
Completeness	The description provides a 'when' clause with explicit trigger phrases, but the 'what' is almost entirely absent. There is no clear explanation of what the skill actually does—what it produces, what inputs it takes, or what concrete capabilities it offers. The 'what' is only weakly implied through the trigger terms themselves.	2 / 5
Trigger Term Quality	The description includes a good range of natural trigger terms: 'BDI architecture', 'belief-desire-intention models', 'transform RDF to beliefs', 'cognitive agent', 'BDI ontology', 'mental state modeling', 'rational agency', 'neuro-symbolic AI integration'. These are domain-specific and cover several synonyms and related concepts, though they are fairly technical and may miss more casual phrasings.	4 / 5
Distinctiveness Conflict Risk	The domain is highly specialized (BDI architecture, neuro-symbolic AI, RDF-to-beliefs transformation), making it unlikely to conflict with most other skills. Minor overlap could exist with general AI/ontology or RDF-related skills, but the BDI focus is quite distinctive.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/bdi-mental-states/SKILL.md
Commit: 57c135b

Reviewed: 23 hours 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.