Tessl • The package manager for agent skills

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

75%

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

67%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 strong, example-rich skill body: concrete ontology patterns with executable Turtle/SPARQL snippets, a clear six-pass workflow with a validation step, and well-signaled reference files. The main costs are redundancy between Core Concepts, Guidelines, Gotchas, and Integration, and overlap between the body and the bundle files.

Suggestions

Consolidate the Guidelines section into Core Concepts (or cut it to pointers), and fold the Integration boundary list into the existing When-to-Activate list — both currently restate earlier content almost verbatim.

Move the Competency Questions section and the SEMAS/LAG integration patterns into the existing sparql-competency.md and framework-integration.md references, keeping only one exemplar of each inline.

Drop or relocate the dated Skill Metadata block (Created/Last Updated/Version) — time-stamped fields add tokens without aiding execution.

Dimension	Reasoning	Score
Conciseness	The pattern sections are dense and rationale-driven, but there is real redundancy: the Guidelines section restates Core Concepts (endurants/perdurants, hasPart, justifications, T2B2T, temporal bounds), the Integration section restates the When-to-Activate boundary list, and a dated "Skill Metadata" block (Created/Last Updated/Version) adds time-sensitive clutter that belongs elsewhere. Tightening these would cut meaningful length without losing content.	3 / 5
Actionability	Concrete Turtle, SPARQL, Prolog, and Python snippets with named ontology properties (motivates/isMotivatedBy, refersTo, hasValidity) dominate the body, and competency questions are executable queries. Minor gaps remain: the LAG Python example calls undefined helpers (serialize_ontology, extract_rdf_triples) and the SEMAS rules are illustrative rather than runnable.	4 / 5
Workflow Clarity	"Build a BDI Model in Six Passes" gives a clear ordered sequence that ends in an explicit validation step ("Validate with competency questions") backed by concrete SPARQL queries. It stops short of a 5 because there is no fix-and-retry feedback loop described for failed validation.	4 / 5
Progressive Disclosure	Four real, one-level-deep reference files (bdi-ontology-core.md, rdf-examples.md, sparql-competency.md, framework-integration.md) are each signaled with a purposeful "Read when" condition — good navigation. However, body sections (Competency Questions, SEMAS/LAG integration patterns) duplicate content the reference files already own, so the split is not as clean as it could be.	4 / 5
	Total	15 / 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.

A well-targeted, third-person description with an explicit trigger list of domain-relevant terms. Its main weakness is that the capability side is implicit — it enumerates topics to model but never states what the skill actually does or produces.

Suggestions

Lead with a concrete capability statement before the trigger clause, e.g., "Transforms external RDF context into belief-desire-intention chains using a formal BDI ontology, with SPARQL competency validation. Use when ..."

Add a couple of capability verbs (e.g., "grounds beliefs in world states", "validates models with competency questions") so the what-side matches the strength of the when-side.

Trim broad tail terms like "neuro-symbolic AI integration" if they are not core triggers, to reduce overlap with adjacent agent-design skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("modeling agent mental states with BDI concepts") and includes two concrete actions ("modeling agent mental states", "RDF-to-belief transformations"), but the remainder is a topic noun list ("rational agency traces, cognitive agents, BDI ontologies") rather than capability verbs, so coverage of concrete actions is not comprehensive.	3 / 5
Completeness	The "when" is explicit and trigger-rich ("This skill should be used when modeling agent mental states with BDI concepts: ..."), but the "what" is only a bare gerund phrase — it never states what the skill produces or does (e.g., transforms external RDF context into belief/desire/intention chains using a BDI ontology). Not 3 because the when-clause is fully explicit with concrete triggers; not 5 because the what-side is thin.	4 / 5
Trigger Term Quality	Terms like "beliefs, desires, intentions", "cognitive agents", "BDI ontologies", and "neuro-symbolic AI" are natural phrasings a user with this need would say, and they appear alongside the "BDI" acronym itself. A few natural variants are missing, keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	The BDI mental-state niche is clearly distinct with specific triggers (beliefs, desires, intentions, BDI ontologies), but broad terms like "cognitive agents" and "neuro-symbolic AI integration" create minor overlap risk with general agent-architecture 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: 58b55a8

Reviewed: 11 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.