CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mps-distribution-build

Use when bundling a new plain Java/Kotlin plugin into MPS distribution archives, debugging packaging/layout issues in `build/mps*.xml`, tracing where per-plugin artefacts end up, or editing `plugins/mps-build/solutions/mpsBuild/models/build.mps` (the source of truth that generates every `build/mps*.xml`). The skill covers the generated Ant pipeline, plugin-to-distribution wiring, and the per-plugin / aggregator / distribution layers.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a lean, concrete, well-sequenced guide with explicit validation steps and an honest set of critical directives. Its critical flaw is bundle integrity: every detail it defers to lives in nine reference files that do not exist in the bundle, so the promised depth is unreachable and the skill stands alone as an overview only.

Suggestions

Ship the nine referenced files under references/ (architecture.md, diagnostics.md, validation.md, plugin-bundling-options.md, build-mps-authoring.md, build-mps-source-of-truth.md, touchpoint-checklist.md, test-suite-wiring.md, key-files.md) or inline the essential details — currently every "See references/..." pointer dangles.

Add an explicit error-recovery branch to the workflow (e.g., what to inspect when "ant -f build/<projectName>.xml assemble" fails) instead of relying on step 1's diagnosis only for the missing-plugin case.

Trim the "Loading companion skills" meta-boilerplate paragraph and deduplicate the platform pre-run note, which appears in Critical Directives, workflow step 6, and the validation reference blurb.

DimensionReasoningScore

Conciseness

The body is dense and high-signal — Critical Directives, an 8-step workflow, and a pipeline diagram with no explanations of concepts Claude already knows. However, the meta "Loading companion skills" boilerplate paragraph and the platform pre-run note repeated three times (Critical Directives, step 6, the validation blurb) could be trimmed, which keeps it out of the score-5 "every token earns its place" anchor.

4 / 5

Actionability

Concrete executable commands ("ant -f build/<projectName>.xml assemble", "grep -r <plugin-name> build/", "ant -f build/build.xml platform") and exact concept/file names ("BuildProject", "BuildLayout", "BuildSource_JavaDependencyModule", "BuildJavaPlugin") make the workflow actionable. It falls short of score-5 copy-paste readiness because key authoring details (BuildLayout shape, aggregator wiring specifics) are deferred to reference files rather than shown.

4 / 5

Workflow Clarity

The 8-step "Bundle a New Plain Java/Kotlin Plugin" sequence is explicit with validation checkpoints — a "Smoke step (no full build)" before the full build and "Verify the three artefact locations" after it. It is not score 5 because there is no inline if-fails error-recovery branch, and the checklist/validation detail is deferred to references rather than included.

4 / 5

Progressive Disclosure

The Reference Index is clearly signaled ("Open ... when ..." per file) and one level deep, but all nine referenced files (references/architecture.md, build-mps-source-of-truth.md, plugin-bundling-options.md, build-mps-authoring.md, diagnostics.md, validation.md, touchpoint-checklist.md, test-suite-wiring.md, key-files.md) are absent from the bundle — every navigation target is a dangling path. Scored against the actual (empty) bundle structure, broken references are worse than the score-3 "not clearly signaled" case, but the well-structured, non-nested overview keeps it above score 1.

2 / 5

Total

14

/

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.

A strong description: four concrete actions, an explicit multi-trigger "Use when" clause, a clear what-it-covers sentence, and tightly scoped file-level triggers that distinguish it from sibling skills. It is dense but every clause is a trigger, not padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "bundling a new plain Java/Kotlin plugin into MPS distribution archives", "debugging packaging/layout issues in `build/mps*.xml`", "tracing where per-plugin artefacts end up", "editing ... `build.mps`" — with comprehensive in-domain coverage and no vague or padded language. Matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage), not 4, since no meaningful action in the domain is missing.

5 / 5

Completeness

Explicitly answers both parts: "Use when bundling ... debugging ... tracing ... editing ..." gives concrete trigger phrases, and "The skill covers the generated Ant pipeline, plugin-to-distribution wiring, and the per-plugin / aggregator / distribution layers" states what it does. This mirrors the score-5 good example; the "when" is explicit and multi-trigger, so it is not the score-4 "could be more specific" case.

5 / 5

Trigger Term Quality

Natural trigger phrases ("bundling a ... plugin", "packaging/layout issues") plus concrete file patterns and synonyms ("build/mps*.xml", "distribution archives", "build.mps", "source of truth") mirror what a user working in this repo would actually say. Comprehensive keyword coverage including file extensions/globs fits the score-5 anchor rather than the score-4 "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

A clear niche (MPS distribution build packaging) anchored to repo-specific files, with no generic wording that would collide with other skills — it even scopes itself away from build-language authoring. Distinct triggers and minimal conflict risk fit the score-5 anchor.

5 / 5

Total

20

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 14 missing

Warning

Total

14

/

16

Passed

Repository

JetBrains/MPS

Path

.agents/skills/mps-distribution-build/SKILL.md

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.