CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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 uses the `smodel` language extension. Covers querying nodes (`.descendants<C>`, `.ancestor<C>`, `.children`, `.parent`, `containingRoot`, `.ofConcept<C>`), 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`, `/`), the `command` / `read action` lock wrappers, and JSON blueprints for every shape the Java parser cannot produce. Collection operations and closures (`.where`, `.select`, `.translate`, `{ it => }`) are in the companion skill `mps-collections-and-closures`; most bodies need both.

Quality

94%

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

92%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-engineered reference-skill body: concrete tool calls and operation names throughout, a numbered workflow with explicit validation and error-recovery routing, and exemplary progressive disclosure that budget the reader to one or two files. The only trimmable content is the thrice-repeated 'open only one file' instruction.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — it never explains what MPS or smodel is, and every directive carries domain-specific substance (exact tool names, error strings, persistent node-ref IDs). What keeps it below the lean anchor 5 is repetition of the reading-budget message: "One file is enough to write the body", "One file serves all four", the Stopping Rule paragraph, and "expect to open **one** entry" in the Reference Index all restate the same instruction — minor over-explanation that could be trimmed to one statement.

4 / 5

Actionability

Guidance is fully concrete: exact tool invocations with arguments ("`mps_mcp_check_root_node_problems(nodeReference, onlyNodesWithProblems=true)`", "`mps_mcp_model_used_language` / `mps_mcp_model_dependency`"), exact operation and concept names (`NPEEqualsExpression`, `SLinkListAccess`, `MetaAdapterFactory.getContainmentLink`), real error messages ("out of search scope"), and a full persistent node-ref for `INamedConcept.name`. As an instruction/catalog skill its guidance is copy-paste actionable without code blocks; there are no minor gaps.

5 / 5

Workflow Clarity

The Common-path workflow is a clearly numbered 6-step sequence with an explicit validation checkpoint (step 5, check_root_node_problems) and explicit error-recovery branches: step 6 ("If imports/dependencies break") and the Stopping Rule routing unexplained errors to golden-rules-and-pitfalls.md before any catalog. This matches the top anchor (explicit validation, feedback loops for error recovery); it is above anchor 4, where checkpoints are only mostly present.

5 / 5

Progressive Disclosure

No bundle files are present in this review directory, so structure is judged from the SKILL.md itself: the body is an overview that routes to one-level-deep references via a decision table ("Minimum reading set"), conditional add-on rules, a symptom-keyed Reference Index, and Related Skills — every reference clearly signaled with when to open it. Navigation is exactly the 'clear overview with well-signaled one-level-deep references' anchor-5 pattern; it exceeds anchor 4 because there are no organization gaps — even the failure path has a designated first file.

5 / 5

Total

19

/

20

Passed

Description

96%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 exemplary description: explicit 'Use when' trigger with the full list of body shapes, a comprehensive catalog of concrete smodel operations with their syntax, and an explicit boundary delegation to the companion collections skill. The only residual risk is overlap with the sibling MPS skills that share the BaseLanguage-authoring trigger space.

DimensionReasoningScore

Specificity

The description lists multiple concrete action categories — "querying nodes (`.descendants<C>`, `.ancestor<C>`, `.children`...)", "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`)", "null-safe node equality (`:eq:` / `:ne:`)", "the `command` / `read action` lock wrappers", "JSON blueprints for every shape the Java parser cannot produce" — with named syntax for each, giving comprehensive coverage of the domain's operations. It exceeds anchor 4 ('several specific actions; minor gaps') because no operation category of smodel authoring is left unnamed.

5 / 5

Completeness

It opens with an explicit trigger clause — "Use when writing or editing MPS BaseLanguage code that lives inside a model — behavior methods, typesystem rules, checking rules... — and uses the `smodel` language extension" — and follows with an explicit 'what' ("Covers querying nodes..., creating and mutating nodes..., property and link access..."). Both what and when are answered explicitly with concrete trigger phrases, exactly the anchor-5 pattern; not anchor 4, where the 'when' is present but less specific.

5 / 5

Trigger Term Quality

It covers the natural phrases an MPS user would say: "behavior methods", "typesystem rules", "checking rules", "generator queries", "constraints", "intentions", "scope/canBe callbacks", "dataflow builders", plus both surface syntax (`.descendants<C>`, `:eq:`) and API/concept names (SPropertyAccess, smodel). Coverage is comprehensive for the domain — surface-notation and concept-level synonyms are both present — matching the top anchor rather than the 'a few natural terms missing' anchor 4.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (smodel-extension code inside MPS models) and the closing sentence actively delegates "Collection operations and closures (`.where`, `.select`, `.translate`, `{ it => }`)") to the companion `mps-collections-and-closures` skill. However, the skill lives in a family of closely related companions (`mps-baselanguage`, `mps-node-editing`, `mps-aspect-*`) whose triggers overlap "writing or editing MPS BaseLanguage code", so it is 'mostly distinct; minor overlap risk with closely related skills' (anchor 4) rather than the minimal-conflict anchor 5.

4 / 5

Total

19

/

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: 39 missing

Warning

Total

14

/

16

Passed

Repository

JetBrains/MPS

Path

.agents/skills/mps-model-manipulation/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.