Name: bdi-mental-states
Rating: 65.60000000000001 (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

78%

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-claude/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

71%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 dense, well-structured ontology reference with concrete executable examples across Turtle, SPARQL, Prolog, and Python, plus a clear T2B2T workflow and competency-question validation. Its main defect is progressive disclosure: the four referenced detail files are missing, so the body over-inlines content that has nowhere to live.

Suggestions

Create the referenced files under references/ (bdi-ontology-core.md, rdf-examples.md, sparql-competency.md, framework-integration.md) or remove the References section if the inlined content is intended to be the whole skill.

Move the bulk of the repeated Turtle examples and full SPARQL/Prolog listings into the corresponding reference files, keeping SKILL.md as a concise overview with one representative example per concept.

Tighten the Python LAG and SEMAS snippets so the helper functions are at least stub-defined, making them closer to copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and example-driven without padding generic concepts Claude already knows, though the many Turtle/SPARQL blocks repeat similar structures that could be tightened or consolidated.	4 / 5
Actionability	Provides concrete, copy-ready Turtle, SPARQL, Prolog, and Python examples covering common cases; the Python and Prolog snippets are partly illustrative (undefined helpers like llm.generate/retry_with_feedback), which is a minor gap.	4 / 5
Workflow Clarity	The T2B2T paradigm gives a clear three-phase sequence and the Competency Questions section provides an explicit validation mechanism, though there are no error-recovery feedback loops within the flow.	4 / 5
Progressive Disclosure	Sections are clearly organized and a References section signals one-level-deep files, but the referenced files (bdi-ontology-core.md, rdf-examples.md, sparql-competency.md, framework-integration.md) do not exist, and a large volume of detail is inlined that those files are meant to hold.	3 / 5
	Total	15 / 20 Passed

Description

86%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, well-targeted description for a specialized domain, with explicit 'use when' guidance and concrete action verbs. Its main weakness is the absence of a single explicit 'what does this do' capability statement, leaving the purpose implied through the trigger phrases.

Suggestions

Prepend a concise capability sentence (e.g. 'Transforms external RDF context into BDI mental states (beliefs, desires, intentions) using formal ontology patterns.') before the trigger clause so 'what' is stated as plainly as 'when'.

Convert the 'should be used when the user asks to' framing into a direct third-person capability + 'Use when...' form to match the strongest anchor examples.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability verbs ('model agent mental states', 'implement BDI architecture', 'create belief-desire-intention models', 'transform RDF to beliefs', 'build cognitive agent'), though framed as user requests rather than a direct capability statement, leaving minor gaps in coverage framing.	4 / 5
Completeness	The 'when' is explicit and specific via the 'should be used when the user asks to...' clause, and the 'what' is conveyed through the concrete action verbs, but the what is distributed and implied rather than stated as a single clear capability sentence.	4 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases including synonyms and variations ('model agent mental states', 'implement BDI architecture', 'BDI ontology', 'mental state modeling', 'rational agency', 'neuro-symbolic AI integration') that a user would plausibly say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear specialized niche (BDI ontology, rational agency, neuro-symbolic integration) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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-claude/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.