CtrlK
BlogDocsLog inGet started
Tessl Logo

mps-aspect-structure-concepts

Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's `structure` aspect. Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation, and the full `mps_mcp_alter_structure` / `mps_mcp_query_structure` reference. Use when authoring or modifying a language's structure model.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/mps-aspect-structure-concepts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-structured reference skill with exemplary progressive disclosure and concrete operation-level guidance. The main gaps are redundancy across the Critical Directives and Workflow, deferred executable JSON detail, and the absence of an explicit validation feedback loop.

Suggestions

De-duplicate the rebuild directive and alias/smart-reference rules — state them once in Critical Directives and have the Workflow reference them rather than restating them in steps 5–7 and 11.

Add a short inline JSON blueprint example for one concept creation so the body is actionable without requiring the reference file, or at minimum show the mps_mcp_alter_structure parameter shape.

Add an explicit validate→fix→retry feedback loop (e.g., check makeStatus on MAKE, and on runtime_stale/failed fix and re-run) for the batch/structural operations.

DimensionReasoningScore

Conciseness

The body is dense and directive, but the rebuild directive and the alias/smart-reference rules are restated across 'Critical Directives' and the Workflow (steps 5–7 and 11), so it could be tightened; not score 3 because not every token earns its place, and not score 1 because it largely assumes competence rather than explaining basics.

2 / 3

Actionability

It names concrete operations (mps_mcp_alter_structure, mps_mcp_update_node, mps_mcp_alter_nodes MAKE), exact cardinalities (0..n, 1..n), and exact interfaces (INamedConcept), but the executable JSON/blueprint formats are deferred to the reference files, so key executable detail is missing from the body itself.

2 / 3

Workflow Clarity

The 11-step workflow is clearly sequenced and includes a rebuild/MAKE checkpoint, but there is no explicit validate→fix→retry feedback loop for the batch/structural operations the skill performs, which the rubric caps at 2; it is above score 1 because the sequence and a make checkpoint are present.

2 / 3

Progressive Disclosure

The body is an overview that points to two clearly-signaled, one-level-deep references (references/structure-operation-api.md and references/attributes-and-annotations.md), both of which exist and match, with detail appropriately split out — matching the score-3 anchor of a clear overview with well-signaled references.

3 / 3

Total

9

/

12

Passed

Description

85%

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, highly specific description with an explicit 'Use when' clause and a clear, conflict-resistant niche. Its only weakness is trigger-term breadth: the lone trigger clause and embedded API jargon limit natural-keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Define concepts, interface concepts, enumerations, and constrained data types' and 'Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation' — matching the score-3 anchor of multiple specific concrete actions; it is comprehensive, not merely naming a domain.

3 / 3

Completeness

Explicitly answers both what ('Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's structure aspect') and when ('Use when authoring or modifying a language's structure model'), matching the score-3 anchor; it is not the level below because the 'when' is explicit, not implied.

3 / 3

Trigger Term Quality

The 'Use when authoring or modifying a language's structure model' clause is a natural trigger, but it is fairly singular and the description also leans on API jargon ('mps_mcp_alter_structure', 'mps_mcp_query_structure') that a user would not actually say, leaving common variations uncovered.

2 / 3

Distinctiveness Conflict Risk

The scope is a narrow, clearly-bounded MPS niche (structure-aspect concepts, INamedConcept, mps_mcp_alter_structure) that is unlikely to trigger for the related editor/constraints/behavior/actions skills, matching the score-3 anchor of a clear distinct niche.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
JetBrains/MPS
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.