mps-model-manipulation

Use when writing or editing MPS BaseLanguage code that lives inside a model — behavior methods, typesystem rules, checking rules, generator queries, constraints, intentions, scope/canBe callbacks, dataflow builders — and combines the `smodel`, `collections`, and `closures` language extensions. Covers querying nodes (`.descendants<C>`, `.ancestor<C>`, `.children`, `.parent`, `containingRoot`), filtering sequences (`.where`, `.select`, `.translate`, `.ofConcept<C>`), building closures (`{ it => ... }`, `yield`, recursion), creating and mutating nodes (`new node<C>()`, `add new(C)`, `set new(C)`, `replace with new(C)`, `.detach`, `.copy`), property and link access (`SPropertyAccess`, `SLinkAccess`, `SLinkListAccess`), reference operations (`.reference/C : role/`, `.target`), null-safe node equality (`:eq:` / `:ne:`), smodel/Java type casts (`node:C`, `node as C`, `/`, `downcast`), foreach choice, the `command` / `read action` lock wrappers, and JSON blueprints for every shape the Java parser cannot produce.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/mps-model-manipulation/SKILL.md

Quality

Content

63%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 well-structured reference catalog with concrete MCP tool calls, a sequenced validation-included workflow, and clearly signaled references, but it is held back by a verbose Reference Index and by referencing ~18 bundle files that are not present to verify.

Suggestions

progressive_disclosure: Ensure every referenced references/*.md file actually exists in the bundle — the body routes to ~18 reference files (e.g. references/node-equality.md, references/closures-catalog.md) that are not present, breaking the navigation promise the Reference Index makes.

conciseness: Shorten the Reference Index entries to one-line pointers; many descriptions repeat material already covered in Critical Directives, so trimming them would reduce tokens while preserving discoverability.

workflow_clarity: Add an explicit error-recovery feedback loop after the validation step, e.g. 'If mps_mcp_check_root_node_problems reports problems, fix them and re-run until onlyNodesWithProblems=true returns none.'

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no padding with basic MPS/programming concepts), but the ~18-entry Reference Index uses verbose descriptions that repeat information already stated in Critical Directives, so it could be tightened — anchor 3.	3 / 5
Actionability	It provides concrete MCP tool calls with parameters ('mps_mcp_check_root_node_problems(nodeReference, onlyNodesWithProblems=true)', 'mps_mcp_parse_java_and_insert') and concrete operation names, but the detailed node blueprints are deferred to reference files, leaving minor gaps — anchor 4.	4 / 5
Workflow Clarity	The Common-path workflow is a clear 6-step numbered sequence with an explicit validation checkpoint at step 5, but the error-recovery feedback loop (fix and re-validate) is only weakly implied rather than spelled out — anchor 4, not 5.	4 / 5
Progressive Disclosure	The body has clear sections and well-signaled one-level-deep references, but per the guideline to score against the actual bundle structure, the ~18 referenced references/*.md files are not present in the bundle (no references/, scripts/, or assets/ directories exist), so the navigation promise is unfulfilled — anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

88%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.

The description is highly specific and explicitly answers both what the skill does and when to use it, with concrete syntax examples and natural MPS-domain trigger terms. Its only weakness is verbosity — it is one long run-on sentence — and minor overlap with related MPS aspect skills.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions with real syntax examples — 'querying nodes (`.descendants<C>`, `.ancestor<C>`, `.children`)', 'creating and mutating nodes (`new node<C>()`, `add new(C)`, `set new(C)`)', reference operations, type casts — giving comprehensive concrete coverage matching the anchor-5 example.	5 / 5
Completeness	It opens with an explicit 'Use when writing or editing MPS BaseLanguage code that lives inside a model — behavior methods, typesystem rules...' (when) and follows with 'Covers querying nodes... creating and mutating nodes... and JSON blueprints for every shape the Java parser cannot produce' (what), explicitly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural MPS-domain terms a user would say ('MPS BaseLanguage', 'smodel', 'behavior methods', 'typesystem rules', 'generator queries', 'constraints', 'intentions'), but the language is jargon-heavy and lacks synonyms or file extensions, fitting anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (MPS model code combining smodel/collections/closures) but acknowledges overlap with closely related MPS skills (mps-baselanguage, mps-aspect-behavior/generator/typesystem/constraints), which is minor overlap risk with closely related skills per anchor 4.	4 / 5
	Total	18 / 20 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
referenced_paths_exist	Referenced path issues: 34 missing	Warning

	Total	14 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-model-manipulation/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.