Name: mps-build-language
Rating: 70.39999999999999 (1 reviews)
Author: JetBrains

mps-build-language

Use when authoring or modifying MPS Build Language scripts (`BuildProject` roots) — the declarative DSL that generates Ant `build.xml` to package MPS language plugins, IDEA plugins, plain Java modules, standalone IDE/RCP distributions, module tests, or `run code from solution` tasks. Covers build solution setup, macros, project/external/Java dependencies, MPS module declarations (`BuildMps_Language` / `_Solution` / `_Generator`), groups, layouts, IDEA-plugin declarations, MPS settings, and the workflow language. Trigger terms: `BuildProject`, `BuildMps_*`, `BuildLayout_*`, `jetbrains.mps.build`, `build.mps` solution, `internalBaseDirectory`, `compactBuildScriptFileName`, Ant target generation, `mps_home`, `idea_home`.

Quality

86%

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

72%

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

The body is lean, domain-specific, and excellently structured with one-level-deep references and clear navigation. Its main gaps are the absence of inline executable code skeletons and a missing explicit validation/verification checkpoint in the build workflow.

Suggestions

Add a validation checkpoint to the Common-Path Workflow after 'Make the build solution' and after 'Run Ant' (e.g., verify build.xml was written and check ./build/artifacts for expected artifacts), with a retry loop for the 'class not found' failure listed in Critical Directives.

Inline at least one minimal copy-paste-ready BuildProject JSON skeleton in the body so the core action is executable without first opening references/buildproject-skeleton.md.

Consolidate the 10-step Common-Path Workflow's repeated per-step reference pointers into a single 'See also' line to reduce repetition and tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific, assumes Claude's competence (e.g., "Never hand-edit the .mps file as if it were Ant XML"), and avoids explaining what MPS or Ant is; nearly every line carries non-obvious build-language guidance rather than padding.	3 / 3
Actionability	Gives concrete tool names, macro names, UUIDs, menu paths, and intentions, but the actual executable JSON skeletons and code are deferred to referenced files rather than provided copy-paste-ready inline, leaving some key details out of the body.	2 / 3
Workflow Clarity	The 10-step Common-Path Workflow is clearly sequenced with prerequisites (generate languages first, re-run Load required information), but it lacks an explicit output-validation checkpoint/feedback loop for the file-generating, Ant-running build process, which the rubric caps at 2 for such operations.	2 / 3
Progressive Disclosure	A concise overview plus a Reference Index pairs each of the 16 real, one-level-deep reference files with the exact condition to open it, yielding well-signaled navigation and an appropriately split structure.	3 / 3
	Total	10 / 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.

The description is concrete, complete, and highly distinct: it names specific actions, explicit use-conditions, and a rich set of natural trigger terms. It uses third-person voice with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("package MPS language plugins, IDEA plugins, plain Java modules, standalone IDE/RCP distributions, module tests, or run code from solution tasks") rather than vague language, matching the comprehensive multi-action anchor.	3 / 3
Completeness	Explicitly answers both what it does (generates Ant build.xml to package various artifact types) and when to use it ("Use when authoring or modifying MPS Build Language scripts") with explicit trigger terms, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Surfaces the natural identifiers a user of this domain would actually name (BuildProject, BuildMps_*, jetbrains.mps.build, mps_home, idea_home, Ant target generation), giving good coverage of likely trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a highly specific niche (the MPS Build Language DSL) with distinct technical triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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

Reviewed: about 5 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.