CtrlK
BlogDocsLog inGet started
Tessl Logo

mps-aspect-behavior

Use when defining or editing MPS `ConceptBehavior` — per-concept methods (non-virtual / virtual / abstract / static / virtual static), constructors, virtual dispatch (MRO), super and interface-default calls (`super<Interface>.method`), overriding methods from `lang.core.behavior` interfaces such as `ScopeProvider.getScope` / `INamedConcept.getName` / `BaseConcept.getPresentation`, calling sibling methods (`LocalBehaviorMethodCall`) and behavior methods from other aspects via `node.method(...)`. Reach for this skill whenever the task involves authoring or modifying `<lang>/languageModels/behavior.mps`.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A dense, highly actionable reference skill whose body stays lean by offloading detail to eight well-signaled reference files, with a clear modifier table and a numbered workflow. The only gap is that the workflow's validation feedback loop is implicit rather than spelled out inline.

Suggestions

Make the validation feedback loop explicit in the Common-Path Workflow: after 'Validate with mps_mcp_check_root_node_problems', add an 'if problems are reported, fix them and re-run the check; only rebuild once it is clean' step so error recovery is inline rather than only in common-failures.md.

Consider moving the verbose per-row 'Notes' column of the Method Modifier Quick Reference table (e.g. the baseLanguage example callouts) into references/method-declarations.md to further tighten the overview, since the call-shape and dispatch columns already carry the core guidance.

DimensionReasoningScore

Conciseness

Every section carries MPS-specific domain knowledge (behavior-aspect internals, MRO, modifier dispatch, MCP tool names) rather than explaining concepts Claude already knows, and detailed material is offloaded to eight reference files — lean and efficient with no padding.

3 / 3

Actionability

Gives concrete, executable guidance: named MCP tools (mps_mcp_insert_root_node_from_json, mps_mcp_parse_java_and_insert, mps_mcp_check_root_node_problems), exact model-naming ('<lang>.behavior'), JSON blueprint pointers, and a modifier table with concrete call shapes (node.m(...), ConceptName.m(...)).

3 / 3

Workflow Clarity

The Common-Path Workflow is a clearly numbered 5-step sequence with a validation step ('Validate with mps_mcp_check_root_node_problems, rebuild the language'), but it lacks an explicit validate→fix→revalidate feedback loop inline — error recovery is only referenced indirectly via common-failures.md, so it does not reach the 'explicit feedback loops' top anchor.

2 / 3

Progressive Disclosure

The body is a well-organized overview (Critical Directives, Common-Path Workflow, Modifier Quick Reference, Related Skills, Reference Index) with a clearly signaled, one-level-deep Reference Index whose eight 'Open X when ...' entries all resolve to real files in references/.

3 / 3

Total

11

/

12

Passed

Description

100%

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 highly specific, well-triggered description that explicitly covers both what the skill does and when to use it, scoped tightly to the MPS behavior aspect. It uses the standard third-person/infinitive trigger form with no first- or second-person voice to penalize.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'per-concept methods (non-virtual / virtual / abstract / static / virtual static), constructors, virtual dispatch (MRO), super and interface-default calls ... overriding methods ... calling sibling methods ... behavior methods from other aspects via node.method(...)' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (methods, constructors, dispatch, super/interface calls, overrides, cross-aspect calls) and 'when' via two explicit trigger clauses ('Use when ...', 'Reach for this skill whenever ...'), matching the top anchor.

3 / 3

Trigger Term Quality

Opens with 'Use when defining or editing MPS ConceptBehavior' and closes with 'Reach for this skill whenever the task involves authoring or modifying <lang>/languageModels/behavior.mps' — natural verbs/nouns an MPS user would say, with good coverage of common variations rather than only technical jargon.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to MPS ConceptBehavior and the specific file behavior.mps with distinct triggers, giving it a clear niche unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
JetBrains/MPS
Reviewed

Table of Contents

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.