mps-tests

Use when writing or modifying tests inside MPS `@tests` models — `NodesTestCase` (typesystem, constraints, scopes, dataflow, generator output), `EditorTestCase` (intentions, actions, keystrokes, side-transforms, completion), `MigrationTestCase` (migration scripts), `BTestCase` (plain JUnit on hand-written Java/Kotlin runtime), inline annotations such as `has error` / `has type` / `ScopesTest`, label-based `node<label>` cross-references, caret markers, and running tests via MCP / in MPS. Reach for this skill whenever the task involves authoring or fixing tests in a `tests`-stereotype model, or interpreting failures from one.

Quality

89%

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

86%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.

An excellent, dense, actionable reference body with a clear validating workflow. Its main weakness is progressive disclosure: the overview correctly points to a references bundle, but that bundle is absent, so the signaled navigation is broken in practice.

Suggestions

Ship the references/ bundle files that the Reference Index promises (test-types.md, nodes-test-case.md, editor-test-case.md, common-failures.md, concept-identifiers.md, etc.) so the one-level-deep navigation actually resolves.

Fix or remove the cross-skill link to ../mps-mcp-workflow/references/aspect-model-stereotypes.md, which does not resolve from this skill's directory.

Add a brief inline error-recovery feedback loop (validate -> inspect problem -> fix -> re-validate) in the Common-Path Workflow rather than only delegating diagnosis to common-failures.md.

Dimension	Reasoning	Score
Conciseness	Dense, expert-level reference that assumes Claude's competence — no padding about what tests or MPS are — and every line carries non-obvious specifics (concept refs, exact mps_mcp_* calls, gotchas), matching the lean-and-efficient score-5 anchor.	5 / 5
Actionability	Provides copy-paste-ready guidance: concrete mps_mcp_* tool calls, exact concept identifiers with r: refs, cell-ID conventions, and named annotation concepts covering the common cases per the score-5 anchor.	5 / 5
Workflow Clarity	The Common-Path Workflow is a clear 6-step sequence with an explicit validation checkpoint (mps_mcp_check_root_node_problems) before running, but the error-recovery feedback loop is delegated to references rather than presented inline, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	The Reference Index uses well-signaled one-level-deep 'Open X when…' navigation, but the referenced files (all 10 references/*.md and the cross-skill aspect-model-stereotypes.md) do not exist, so the navigation resolves to broken links — content that should be split out is effectively stranded.	3 / 5
	Total	17 / 20 Passed

Description

92%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 clearly answers both what the skill does and when to use it. Slightly jargon-heavy in places, which keeps trigger-term coverage just below the top anchor.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities by test type (NodesTestCase, EditorTestCase, MigrationTestCase, BTestCase) plus inline annotations, label-based cross-references, and caret markers — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly states both what (authoring/fixing tests in @tests models across the listed test types) and when ('Use when writing or modifying tests…', 'Reach for this skill whenever the task involves authoring or fixing tests… or interpreting failures'), matching the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('writing or modifying tests', 'authoring or fixing tests', 'interpreting failures', 'via MCP / in MPS'), but leans heavily on technical concept names rather than the broad synonym/extension coverage expected for a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to MPS @tests models with named test concepts, giving it a clear niche with minimal overlap risk against other skills.	5 / 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: 14 missing	Warning

	Total	13 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-tests/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.