CtrlK
BlogDocsLog inGet started
Tessl Logo

mps-aspect-typesystem

Use when authoring or debugging MPS typesystem — inference rules (`typeof :==: / :<=: / :>=:`), `SubtypingRule`, `ComparisonRule`, `InequationReplacementRule`, `SubstituteTypeRule`, `WhenConcreteStatement` blocks, `NonTypesystemRule` checking rules, `TypesystemQuickFix`, error/warning/info reports with `messageTarget` highlighting and quick-fix wiring (`helginsIntention`), and shared BaseLanguage helpers in the typesystem model. Reach for this skill whenever the task involves editing `<lang>/languageModels/typesystem.mps`.

70

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 high-quality, dense reference skill body that is actionable, well-sequenced with validation feedback loops, and cleanly split across a one-level-deep reference index. Conciseness is strong with only minor trim opportunities in the directives and reference-index prose.

DimensionReasoningScore

Conciseness

The body is dense and information-rich with little concept padding — it jumps straight into directives, operator vocabulary, and MCP tool calls — though the Critical Directives and Reference Index sections are somewhat long and could be trimmed slightly. It mostly assumes Claude's competence rather than explaining basics.

4 / 5

Actionability

It gives concrete, executable guidance including specific MCP tool names (`mps_mcp_insert_root_node_from_json`, `mps_mcp_check_root_node_problems`, `mps_mcp_apply_intention`), a concrete error-message pattern (`error "Expected " + <expectedType> + ... -> node;`), and precise JSON-shape directives; the executable detail is strong though some guidance points to reference files rather than being fully inline.

4 / 5

Workflow Clarity

The Common-Path Workflow is a clear numbered sequence (create model → add languages → add rule roots → add quick fixes → write bodies → validate) with explicit validation checkpoints (`mps_mcp_check_root_node_problems` plus compile and test) and an error-recovery feedback loop described in the directives and final step.

5 / 5

Progressive Disclosure

The body is a well-organized overview with a clear Reference Index pointing one level deep to dedicated `references/*.md` files (inference-rules, when-concrete, lattice-rules, non-typesystem-checking, quick-fixes, messages-and-helpers, json-blueprints, common-failures), each clearly signaled with what it contains and when to open it; navigation is easy and content is appropriately split.

5 / 5

Total

18

/

20

Passed

Description

91%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 explicitly covers both what the skill does and when to reach for it, with strong natural language and minimal conflict risk. Minor additional lay synonyms could push trigger term quality to a perfect 5.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities — `InferenceRule` operators (`:==:`, `:<=:`, `:>=:`), `SubtypingRule`, `ComparisonRule`, `InequationReplacementRule`, `SubstituteTypeRule`, `WhenConcreteStatement`, `NonTypesystemRule`, `TypesystemQuickFix`, and `messageTarget` quick-fix wiring — giving comprehensive, concrete coverage of the typesystem aspect.

5 / 5

Completeness

It explicitly answers both 'what' (the listed rule types, blocks, helpers, and reports) and 'when' ('Use when authoring or debugging MPS typesystem ... Reach for this skill whenever the task involves editing ... typesystem.mps') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes strong natural trigger phrases like 'authoring or debugging MPS typesystem', 'Reach for this skill whenever the task involves editing `<lang>/languageModels/typesystem.mps`', plus concrete rule and block names; minor common variations are covered but a few lay synonyms for the domain are absent.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche scoped to the MPS typesystem/checking aspect and a specific model file (`typesystem.mps`), with distinct MPS-internal terminology that minimizes overlap with sibling skills like behavior, constraints, or intentions.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.