mps-aspect-typesystem

Use when authoring or debugging MPS typesystem — inference rules (`typeof :==: / :<=: / :>=:`), `SubtypingRule`, `ComparisonRule`, `InequationReplacementRule`, `SubstituteTypeRule`, `WhenConcreteStatement` blocks, `NonTypesystemRule` checking rules, `TypesystemQuickFix`, error/warning/info reports with `messageTarget` highlighting and quick-fix wiring (`helginsIntention`), and shared BaseLanguage helpers in the typesystem model. Reach for this skill whenever the task involves editing `<lang>/languageModels/typesystem.mps`.

Quality

85%

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

85%

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

A well-architected skill body: concise, well-sequenced with validation, and cleanly split into one-level references. The only gap is actionability — the body stays at the directive/prose level while the executable JSON lives in the reference files rather than inline.

Suggestions

Inline one minimal executable JSON skeleton (e.g. a complete InferenceRule root via mps_mcp_insert_root_node_from_json) so the body itself reaches the 'copy-paste ready' actionability anchor.

Two body links resolve to other skills' bundles (references/aspect-model-stereotypes.md and references/variable-declarations.md) rather than this skill's references/ folder; qualify those paths (../mps-mcp-workflow/...) as already done for the aspect-stereotype link to keep navigation unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes MPS competence — it does not explain what a typesystem or BaseLanguage is, and every directive (NormalTypeClause wrapping, infer softness, <...> presentation, when concrete deferral) earns its tokens, matching the 'lean and efficient' anchor.	3 / 3
Actionability	It names concrete MCP tools (mps_mcp_insert_root_node_from_json, mps_mcp_check_root_node_problems) and precise rule/operator shapes, but the body itself is prose directives rather than copy-paste executable code; the executable JSON skeletons live in references/, so it clears 2 but not the 'fully executable, copy-paste ready' anchor at 3.	2 / 3
Workflow Clarity	The 'Common-Path Workflow' is a clearly numbered 8-step sequence with an explicit validation checkpoint (step 8: check_root_node_problems + compile + test on sample models) and a feedback loop for quick-fix wiring, satisfying the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	A concise overview with a 'Reference Index' that signals exactly when to open each of 8 real one-level-deep reference files, none of which cross-reference further .md files, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 strong, highly specific description that answers what and when explicitly and occupies a clear niche. Its only weakness is heavy reliance on internal rule-class jargon as trigger terms rather than the phrasing a user would naturally utter.

Suggestions

Add plain-language trigger variants users would actually say (e.g. 'MPS type inference', 'MPS type errors', 'subtype rule') alongside the rule-class jargon so trigger_term_quality can reach 3.

Trim the long parenthetical class inventory so the description stays scannable while preserving the concrete actions.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — inference rules, SubtypingRule/ComparisonRule/InequationReplacementRule/SubstituteTypeRule, checking rules, quick fixes with helginsIntention wiring, and message-target highlighting — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (the listed rule/editing actions) and 'when' via the 'Use when authoring or debugging MPS typesystem' and 'Reach for this skill whenever the task involves editing <lang>/languageModels/typesystem.mps' clauses.	3 / 3
Trigger Term Quality	The natural user trigger 'MPS typesystem' is present, but most terms (e.g. ':<=:', 'InequationReplacementRule', 'WhenConcreteStatement') are internal jargon a user would rarely say aloud; common-variation coverage is thin, so it sits at 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The narrow MPS typesystem niche anchored to the concrete typesystem.mps path is clearly distinguishable from sibling skills (behavior, constraints, intentions) and unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-aspect-typesystem/SKILL.md
Commit: 52c9d63

Reviewed: about 4 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.