Name: bdi-mental-states
Rating: 59.2 (1 reviews)
Author: administrakt0r

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

69%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/bdi-mental-states/SKILL.md

The canonical home for this skill is bdi-mental-states in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

65%Weight 40%Scale 1-5

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

A well-structured, concept-dense ontology reference with concrete Turtle/SPARQL/Prolog patterns, undermined by pseudocode in its one Python example, implicit workflow checkpoints, and references to a `references/` folder whose files are missing while their claimed content is inlined.

Suggestions

Provide the referenced files (bdi-ontology-core.md, rdf-examples.md, sparql-competency.md, framework-integration.md) or remove the dangling references and keep the inlined examples as the canonical source.

Make the LAG Python example runnable by defining or stubbing serialize_ontology/validate_triples/retry_with_feedback, or explicitly label it as illustrative pseudocode.

Add an explicit validate-then-fix loop to the T2B2T workflow (e.g. run competency questions after reasoning, fix inconsistencies before projecting back to RDF).

Dimension	Reasoning	Score
Conciseness	The body is dense and technical, presenting Turtle/SPARQL/Prolog/Python patterns without explaining basics Claude already knows; a few sections (e.g. the Notation Selection table, repeated justification blocks) could be trimmed without losing value.	4 / 5
Actionability	Concrete copy-pasteable Turtle templates, executable SPARQL competency queries, and Prolog rules give actionable patterns, but the Python LAG snippet relies on undefined helpers (serialize_ontology, llm.generate, validate_triples, retry_with_feedback) making it pseudocode rather than runnable.	4 / 5
Workflow Clarity	The T2B2T paradigm is broken into Phase 1/Phase 2 plus a three-step guideline, and competency questions serve as validation, but the checkpoints between translate/reason/project steps are implicit and there is no validate-then-fix feedback loop.	3 / 5
Progressive Disclosure	Section structure is clear and references are explicitly signaled with a bulleted list, but the referenced files (bdi-ontology-core.md, rdf-examples.md, sparql-competency.md, framework-integration.md) do not exist in the bundle, and full examples that the references claim to hold are inlined in SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

73%Weight 40%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.

A trigger-rich, niche-specific description that clearly signals when to use the skill, but it buries the "what does this skill do" inside user-asks phrasing rather than stating it declaratively. Strong on distinctiveness and trigger coverage.

Suggestions

Lead with a declarative third-person capability sentence, e.g. "Transforms external RDF context into BDI (belief-desire-intention) mental-state models." before listing triggers.

Clarify the concrete output the skill produces (e.g. Turtle/SPARQL ontology patterns vs. runnable code) so the "what" is unambiguous.

Dimension	Reasoning	Score
Specificity	Phrases like "model agent mental states", "transform RDF to beliefs", and "implement BDI architecture" name the domain with several concrete capability phrases, but they are framed as user requests rather than explicit statements of what the skill does, leaving the actual action only implicit.	3 / 5
Completeness	The "when" is explicit and thorough ("when the user asks to... or mentions..."), and the "what" is conveyed through the capability phrases, but the what is implicit rather than a standalone declarative statement.	4 / 5
Trigger Term Quality	Natural quoted triggers ("model agent mental states", "create belief-desire-intention models", "build cognitive agent") plus synonym coverage (BDI ontology, rational agency, neuro-symbolic AI) are strong; a few common natural variations are absent and no file-extension cues apply.	4 / 5
Distinctiveness Conflict Risk	BDI ontology / belief-desire-intention modeling is a clear niche with highly specific triggers ("BDI ontology", "transform RDF to beliefs") unlikely to fire for unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/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.