mps-language-modularity

Use when designing how multiple MPS languages relate or compose — choosing between language referencing, extension, reuse, and embedding, or deciding where a cross-language dependency should live and how generated code interacts. Covers the 2×2 modularity taxonomy adapted to MPS, a decision procedure, per-kind recipes (references + search scopes; subconcepting + overloaded operations; abstract hooks + adapter languages + separated/interwoven generation; guest + composition languages + type bridges), the annotations escape hatch, and per-kind validation. This is the design tier above the aspect-implementation skills: it picks the strategy, then routes into the relevant mps-aspect-* skills (structure, constraints, typesystem, generator, generation-plan, intentions) and mps-tests. Reach for it before authoring aspects, or whenever one language must see, extend, embed, or adapt another.

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

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.

A well-structured, dense reference skill that excels at routing a user from a design question to the right modularity kind and aspect skill. Its main weakness is progressive disclosure: the body advertises a reference index whose target files are absent from the bundle.

Suggestions

Ship the referenced files (references/referencing.md, extension.md, reuse.md, embedding.md, design-principles.md, validation.md) alongside SKILL.md, or remove the Reference index entries that have no backing file.

Fold a one-line validation checkpoint into the decision procedure (e.g. 'after picking a kind, run the per-kind checklist from references/validation.md') so verification is part of the workflow rather than only a separate section.

Trim the Voelter attribution and any 'Critical directives' bullets that merely restate the four-kinds table to tighten the opening.

Dimension	Reasoning	Score
Conciseness	Information-dense and assumes MPS competence rather than padding generic concepts; the only mildly trimmable bits are the Voelter attribution and a few 'Critical directives' that restate the later table, so it sits just below the leanest anchor.	4 / 5
Actionability	The 3-step decision procedure and the four-kinds table give concrete, executable routing ('subconcept the host's concepts', 'build a separate adapter language', 'add a third composition language') with only the detailed per-kind recipes deferred to references.	4 / 5
Workflow Clarity	The decision procedure is a clearly sequenced 3-step flow with explicit branch outcomes and a separate validation section; it stops short of a 5 only because validation is referenced rather than wired in as an explicit checkpoint inside the decision flow.	4 / 5
Progressive Disclosure	Structure and signaling are strong — a 'Reference index' with six one-level-deep links and a 'Related skills' section — but the referenced files (references/referencing.md, extension.md, reuse.md, embedding.md, design-principles.md, validation.md) do not exist in the bundle, so the navigation the overview promises is broken.	3 / 5
	Total	15 / 20 Passed

Description

100%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.

An excellent description: third-person voice, explicit 'Use when' trigger, concrete and comprehensive capability list, and a distinct niche with synonyms covering the ways users would phrase the need. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain and a comprehensive set of concrete actions — 'choosing between language referencing, extension, reuse, and embedding', 'deciding where a cross-language dependency should live', taxonomy, decision procedure, per-kind recipes, annotations escape hatch, and validation — with no generic filler.	5 / 5
Completeness	Explicitly answers both what (choosing a modularity kind via taxonomy, decision procedure, recipes, validation) and when ('Use when designing…', 'Reach for it before authoring aspects, or whenever one language must see, extend, embed, or adapt another') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers the natural phrasings an MPS user would say — 'designing how multiple MPS languages relate or compose', 'cross-language dependency', and the synonym cluster 'see, extend, embed, or adapt another' — giving comprehensive coverage including variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a sharply defined niche — MPS multi-language modularity/composition — with triggers unlikely to fire for any other skill, so conflict risk is minimal.	5 / 5
	Total	20 / 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: 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	13 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-language-modularity/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.