bdi-mental-states

This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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.

The body is a well-structured, highly actionable BDI modeling guide with concrete Turtle/SPARQL/Prolog examples, a sequenced six-pass workflow ending in validation, and clean one-level-deep progressive disclosure to verified reference files. Its main weakness is moderate redundancy between Core Concepts, Guidelines, and Examples plus non-deprecated version metadata that bloats the token budget.

Suggestions

Collapse the Guidelines section or fold its unique points into Core Concepts to remove the overlap with the endurant/perdurant, hasPart, temporal, bidirectional-property, and T2B2T guidance already stated above.

Replace the placeholder Python LAG functions (serialize_ontology, validate_triples, retry_with_feedback) with real or more complete implementations, or explicitly mark the snippet as illustrative pseudocode.

Move the Created/Last Updated/Version metadata out of the SKILL.md body (or into a clearly marked non-instructional footer) to keep time-sensitive info out of the instructional token budget, and add an explicit 'if a competency query fails, revise the relevant pass and re-validate' loop to the Six Passes workflow.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence (no primers on RDF/Turtle/SPARQL) but the Guidelines section restates Core Concepts, the Examples re-demonstrate the cognitive chain, and the Skill Metadata block carries version/date info outside any deprecated section; not a 4 because the redundancy is more than minor.	3 / 5
Actionability	Extensive concrete, copy-paste-ready Turtle, SPARQL, and Prolog examples covering the common BDI cases (cognitive chain, world-state grounding, T2B2T, temporal, compositional); not a 5 because the Python LAG snippet relies on placeholder functions (serialize_ontology, validate_triples, retry_with_feedback) rather than executable code.	4 / 5
Workflow Clarity	The 'Six Passes' workflow is a clear sequence with an explicit validation checkpoint (pass 6: validate with competency questions) and the LAG section adds a validate-then-retry loop; not a 5 because the main workflow lacks an explicit 'if validation fails, return to step X' error-recovery feedback loop.	4 / 5
Progressive Disclosure	A clear overview with four one-level-deep references, each signaled with a 'Read when:' trigger (BDI Ontology Core, RDF Examples, SPARQL Competency Queries, Framework Integration — all verified to exist), with bulk material appropriately split into those bundle files; easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

70%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.

The description is specific to a well-defined BDI niche with explicit use-when guidance and strong trigger-term coverage, though it leans on domain concepts rather than concrete action verbs and fuses its what/when statements. Distinctiveness is good with only minor overlap risk from the generic 'cognitive agents' phrasing.

Suggestions

Lead with concrete action verbs (e.g. 'Model agent mental states as BDI beliefs, desires, and intentions; transform RDF context into beliefs; project intentions back to RDF') to lift specificity from a concept list to an action list.

Separate the 'what' and 'when' clauses (e.g. '...and neuro-symbolic AI integration. Use when modeling BDI cognitive agents or transforming external RDF into agent beliefs.') for a cleaner completeness score.

Replace or qualify the broad term 'cognitive agents' with more distinctive BDI-specific phrasing to reduce overlap with multi-agent or memory skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('modeling agent mental states with BDI concepts') and lists several specific concept areas (beliefs, desires, intentions, RDF-to-belief transformations, BDI ontologies), but only one generic action verb ('modeling') — concepts rather than concrete actions, so not a 4.	3 / 5
Completeness	Explicitly provides both a 'when' ('This skill should be used when...') and a 'what' ('modeling agent mental states with BDI concepts...') with concrete trigger phrases; not a 5 because what and when are largely fused in the same phrase rather than cleanly separated.	4 / 5
Trigger Term Quality	Good keyword coverage including 'beliefs, desires, intentions', 'BDI concepts', 'RDF-to-belief transformations', and 'neuro-symbolic AI integration'; not a 5 because several terms (e.g. 'rational agency traces', 'neuro-symbolic AI integration') are jargon-heavy rather than natural user phrases and lack synonyms.	4 / 5
Distinctiveness Conflict Risk	A clear BDI mental-state niche with distinct triggers (BDI ontologies, RDF-to-belief, beliefs/desires/intentions) gives minimal conflict risk; not a 5 because the broad term 'cognitive agents' invites minor overlap with adjacent agent skills.	4 / 5
	Total	15 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: skills/bdi-mental-states/SKILL.md
Commit: 6dbe1a1

Reviewed: 19 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.