mps-aspect-constraints

Use when defining or editing MPS language constraints — property validators / setters / getters, referent search scopes (imperative or inherited via `ScopeProvider.getScope`), `referentSetHandler` side effects, default-scope blocks, `canBeChild` / `canBeParent` / `canBeAncestor` / `canBeRoot` placement rules, `defaultConcreteConcept` for abstract concepts, `set <read-only>` and `{name}` aliasing, and scope helpers (`SimpleRoleScope`, `ListScope`, `CompositeScope`, `HidingByNameScope`). Reach for this skill whenever the task involves authoring or modifying `<lang>/languageModels/constraints.mps`.

Quality

92%

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

Quality

Content

88%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 lean, highly actionable reference skill with concrete MCP tooling, a sequenced workflow that includes validation and a runtime-reload feedback loop, and a strong reference index. The main gap is that the referenced bundle files could not be verified as present.

Suggestions

Trim the Reference Index bullets to a short 'open when' clause plus a few representative tokens, moving the long sub-topic enumerations into the referenced files themselves.

Ensure every referenced ./references/*.md file (concept-roots, property-constraints, referent-constraints, scope-helpers, scope-fqn-reference, canbe-rules, common-failures) actually ships in the bundle so the signaled navigation resolves.

Move the inline 'Critical Directives' items that are pure concept inventories (e.g. the full scope-helper name list) into references, keeping only the decision rules inline.

Dimension	Reasoning	Score
Conciseness	Dense and operational throughout, assuming MPS/BaseLanguage competence (no basic-concept padding), but the Reference Index bullets are long compound sentences enumerating many sub-topics each and could be trimmed.	4 / 5
Actionability	Gives concrete executable MCP commands with parameters (mps_mcp_create_model, mps_mcp_create_root_node, mps_mcp_parse_java_and_insert, mps_mcp_check_root_node_problems, mps_mcp_reload_all) plus specific concept names and used-languages, covering the common cases and pointing to JSON blueprints in references.	5 / 5
Workflow Clarity	A 6-step Common-Path Workflow is clearly sequenced with an explicit validation checkpoint (step 6: mps_mcp_check_root_node_problems + rebuild) and an error-recovery feedback loop ('if the new constraint is invisible at runtime, run mps_mcp_reload_all').	5 / 5
Progressive Disclosure	Excellent structure with a dedicated Reference Index giving one-level-deep, well-signaled pointers and per-file 'when to open' guidance, but the referenced ./references/*.md files are not present in the bundle to verify, leaving a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

96%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 highly specific, well-triggered description that names comprehensive concrete capabilities and gives explicit 'what' and 'when' guidance anchored on a concrete file path. Its only weakness is minor overlap with related MPS aspect skills around scopes and placement rules.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'property validators / setters / getters', 'referent search scopes', 'referentSetHandler side effects', 'canBeChild / canBeParent / canBeAncestor / canBeRoot placement rules', 'defaultConcreteConcept', 'set <read-only> and {name} aliasing', and named scope helpers — giving comprehensive coverage of the constraints aspect.	5 / 5
Completeness	Explicitly answers both what ('defining or editing MPS language constraints — ...') and when, with two concrete trigger clauses: 'Use when defining or editing ...' and 'Reach for this skill whenever the task involves authoring or modifying <lang>/languageModels/constraints.mps'.	5 / 5
Trigger Term Quality	Uses the natural terms an MPS developer would say ('defining or editing MPS language constraints', 'property validators', 'referent search scopes', 'placement rules', 'scope helpers') plus the concrete file trigger '<lang>/languageModels/constraints.mps', covering the domain's synonyms comprehensively.	5 / 5
Distinctiveness Conflict Risk	The constraints.mps file path and constraints-specific terms (canBe*, validators, referentSetHandler) carve a clear niche, but scope work via 'ScopeProvider.getScope' and placement rules overlap with sibling skills (mps-aspect-behavior, mps-aspect-structure-concepts), giving minor conflict risk.	4 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	13 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-aspect-constraints/SKILL.md
Commit: c74b207

Reviewed: 3 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.