Claude Docs Consultant
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's structure aspect.
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JetBrains/MPS mps-aspect-structure-concepts --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .claude/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .claude/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-conceptsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JetBrains/MPS mps-aspect-structure-concepts --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .agents/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .agents/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JetBrains/MPS mps-aspect-structure-concepts --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .cursor/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .cursor/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JetBrains/MPS.git --path .agents/skills/mps-aspect-structure-concepts--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JetBrains/MPS mps-aspect-structure-concepts --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .gemini/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .gemini/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JetBrains/MPS mps-aspect-structure-conceptsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .github/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .github/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JetBrains/MPS mps-aspect-structure-concepts --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JetBrains/MPS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/mps-aspect-structure-concepts .opencode/skills/mps-aspect-structure-concepts && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mps-aspect-structure-concepts" agent skill from https://github.com/JetBrains/MPS/tree/master/.agents/skills/mps-aspect-structure-concepts into .opencode/skills/mps-aspect-structure-concepts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mps-aspect-structure-concepts", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
mps-aspect-structure-conceptsDefine concepts, interface concepts, enumerations, and constrained data types in an MPS language's structure aspect.
Mps Aspect Structure Concepts is an agent skill from JetBrains/MPS, published by the product's own GitHub organization. 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 mpsmcpalterstructure / mpsmcpquerystructure reference. Use when authoring or modifying a language's structure model.
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `references/attributes-and-annotations.md`, `references/structure-operation-api.md` and `references/structure-operation-api/concept-hierarchy-queries.md`).
It works with Model Context Protocol and JetBrains IDEs. The repository describes itself as: JetBrains Meta programming System. The licence is Apache-2.0.
11 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 3e9cfcd. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Mps Aspect Structure Concepts loads about 2.8k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 1,161 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from JetBrains/MPS at commit 3e9cfcd, republished under its Apache-2.0 licence (© JetBrains). 1,161 words, ~2,810 tokens.
.claude/skills/mps-aspect-structure-concepts/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.Companion names in this skill are lazy dependencies: load only those relevant to the current task. If this skill came from an MCP server, use the host's skill loader to resolve the companion's unique discovered entry URI on the same host-assigned originating server. If the host has no server-backed skill loader, stop and report that limitation; do not silently fall back to a filesystem copy. If this skill came from a filesystem catalog, load the named sibling from that same catalog at <skills-root>/<skill-name>/SKILL.md, even if remote skill loaders are also available. Do not invent a tool name or server endpoint.
Concepts (ConceptDeclaration), interface concepts (InterfaceConceptDeclaration), enumerations (EnumerationDeclaration), and constrained data types (ConstrainedDataTypeDeclaration) are root nodes in a language's structure model. They use the language jetbrains.mps.lang.structure.
INamedConcept instead of declaring name directly. A name property declared directly on a concept is an antipattern in MPS — implement jetbrains.mps.lang.core.structure.INamedConcept instead.conceptAlias, determine whether the concept is an "Implicit Smart Reference". If it has exactly one mandatory reference and no properties or children of its own, do NOT set a conceptAlias — the concept should be transparent in the editor and completion menu so the user types the target's name directly. Examples: variable references, method calls, routine calls.StatementList).mps_mcp_alter_nodes MAKE and rebuild="true" after structural changes, so the new concepts are discoverable by runtime tools.Each row names the file(s) for one operation. Read them — two files in one parallel batch — and nothing else in references/.
| Job | Read |
|---|---|
parameter wire shape, rejected keys, booleans, …Ref/…Reference suffixes, nulls | references/structure-operation-api/tool-conventions.md |
| create concepts (greenfield) | references/structure-operation-api/create-concepts.md — on the first CREATE_CONCEPTS call also references/structure-operation-api/tool-conventions.md |
| create an enumeration | references/structure-operation-api/create-enum.md |
| add/change/delete a property | references/structure-operation-api/update-concept-property.md |
| add/change/delete a child | references/structure-operation-api/update-concept-child.md |
| add/change/delete a reference | references/structure-operation-api/update-concept-reference.md |
| rename a property / child / reference | references/structure-operation-api/rename-concept-feature.md |
| enum literals | references/structure-operation-api/get-enumeration-literals.md |
| is-subconcept / subconcepts / assignable concepts / superconcepts | references/structure-operation-api/concept-hierarchy-queries.md |
| completion/scope candidates for a reference | references/structure-operation-api/get-assignable-references.md |
| find aspect roots for a concept | references/structure-operation-api/list-concept-aspects.md |
| smart-reference check | references/structure-operation-api/is-smart-reference.md |
structure model.jetbrains.mps.lang.structure language.structure model.mps_mcp_get_project_structure to find the language and its structure model.mps_mcp_create_module using an absolute path.NodeAttribute / PropertyAttribute / ChildAttribute / LinkAttribute that graft extra children/data onto other concepts without editing them — see Attributes section below.jetbrains.mps.lang.core.structure.INamedConcept if the concept needs a name property.StatementList.EnumerationDeclaration first, then set the property dataType to reference it.0..n or 1..n.0..1 or 1. There is no 0..n reference in MPS, and no multiple parameter for references. Model a [0..n] reference as a 0..n child role holding smart-reference wrapper concepts; see "Multi-valued references" below.mps_mcp_alter_structure for creating multiple concepts or enums efficiently.mps_mcp_alter_nodes with MAKE and rebuild="true") after structural changes to make concepts discoverable.[0..n])An MPS reference link is always single-valued: 0..1 (optional) or 1 (mandatory). Cardinality on
references does not exist, so multiple: true is rejected on both write paths —
UPDATE_CONCEPT_REFERENCE and a references entry of a CREATE_CONCEPTS blueprint. Only a
children entry takes multiple.
Model a [0..n] reference as a thin smart-reference wrapper concept held in a 0..n child
role on the owner. The wrapper is a non-rootable BaseConcept subconcept with exactly one mandatory
reference, no alias, and no own properties or children — so the editor shows it transparently and the
user just types the target's name. This is what MPS itself does: ConceptDeclaration.implements is a
0..n child list of InterfaceConceptReference, each holding one intfc reference.
[
{
"name": "CourseRef",
"shortDescription": "Reference to a Course",
"references": [
{ "role": "course", "target": "Course", "optional": false }
]
},
{
"name": "Curriculum",
"rootable": true,
"conceptAlias": "curriculum",
"implements": ["jetbrains.mps.lang.core.structure.INamedConcept"],
"children": [
{ "role": "courses", "target": "CourseRef", "multiple": true, "optional": true }
]
}
]Keep the wrapper bare: give it an own property, an own containment link, or a plain conceptAlias
and it stops qualifying implicitly, so the user has to instantiate it explicitly instead of typing
the target's name. Two things do still make a non-bare concept smart, but neither is worth the
trouble here: an explicit SmartReferenceAttribute, which short-circuits every structural check, and
a smart alias of the form pre<{role}>post, which MPS's editor honours (though
IS_SMART_REFERENCE reports it as not smart). Confirm with mps_mcp_query_structure
IS_SMART_REFERENCE on the wrapper: expect isSmartReference: true and
characteristicReferenceName naming its single reference role.
Attributes let one language attach extra children, references, or property data to nodes of a concept it does not own — without editing or subclassing that concept. The host carries a universal smodelAttribute child slot (0..n, every BaseConcept has it); the attribute's own declaration says where it may attach. Used heavily for cross-cutting concerns: generator macros (NodeMacro/PropertyMacro/ReferenceMacro), documentation/description comments, requirement traces, error suppression.
ConceptDeclaration that extends one of NodeAttribute (whole node), PropertyAttribute (one property), ChildAttribute (one child link), or LinkAttribute (one reference link), plus an AttributeInfo (alias @attribute info) in its smodelAttribute role specifying the extension point: role (the attach key), attributed (which concept(s) may receive it — BaseConcept = any), and multiple (one vs. many per node).CREATE_CONCEPTS cannot express the AttributeInfo — create the concept extending the base attribute, then add the AttributeInfo with mps_mcp_update_node. Full walkthrough, concept reference, and the canonical RequirementTrace blueprint live in references/attributes-and-annotations.md.mps-aspect-editor-menus-and-keymaps — once concepts exist, define their editors (often the next step).mps-aspect-constraints — property validators, scopes, and canBe* rules layered on top of structure.mps-aspect-behavior — virtual methods per concept.mps-aspect-actions — node factories for newly created concepts.mps-language-inheritance — for extendedLanguages and concept super/interface relationships.Start here — most common case: creating or changing concepts, enumerations, or data types → read the file(s) in the matching Section index row above. Attributes/annotations → only references/attributes-and-annotations.md.
references/structure-operation-api/, listed in the index at references/structure-operation-api.md) for the exact mps_mcp_alter_structure or mps_mcp_query_structure operation you are about to call — JSON parameter formats, structure blueprint schemas, make flag handling, and makeStatus semantics.references/attributes-and-annotations.md for attributes/annotations: the four attribute kinds (NodeAttribute / PropertyAttribute / ChildAttribute / LinkAttribute), how to choose between them (feature-pinned kinds need a visible feature cell — whole-role markers should be a NodeAttribute + LinkDeclaration reference, converted at runtime via MetaAdapterByDeclaration), the AttributeInfo extension-point spec (role, attributed, multiple), the two-step MCP creation flow, the smodelAttribute slot, and worked examples (RequirementTrace, generator macros, doc/comment annotations).© JetBrains, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 14 other files (references) in .agents/skills/mps-aspect-structure-concepts of JetBrains/MPS.
Open the folder on GitHubat commit 3e9cfcd
Mps Aspect Structure Concepts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mps Aspect Structure Concepts this skillJetBrains/MPS | 1.7k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT | |
| Spock AdbWahdanZ/SpockAdb | 116 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Amplicode InstallAmplicode/spring-skills | 126 | — | ~2.6k | Automated safety check: Pass | None | |
| Idea MCPdtprj/dongting | 208 | — | ~698 | Automated safety check: Pass | Apache-2.0 | |
| Spring Data JpaAmplicode/spring-skills | 126 | — | ~838 | Automated safety check: Pass | None |
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
WahdanZ/SpockAdb
Debug Android apps on a connected device or emulator through the Spock ADB MCP server (tools named android).
Amplicode/spring-skills
Installs the Amplicode IntelliJ plugin into IntelliJ IDEA (Ultimate/Community) and GigaIDE on the user's machine.
dtprj/dongting
IntelliJ IDEA MCP for Java code analysis, testing, refactoring, and project navigation.
Amplicode/spring-skills
Rules and guidelines for working with Spring Data JPA in the project.
Amplicode/spring-skills
Explores a Spring Boot application and builds primary context: tech stack, module structure, domain entities, REST endpoints.
JetBrains/MPS
Analyze an MPS language by name — discover concepts, properties, references, children, aspects (editor/constraints/behavior), metadata, and answer type questions (is A a subtype of B, common…
JetBrains/MPS
Add, update, or delete MPS nodes using JSON blueprints — covers the unified blueprint format, staged construction for large subtrees, validation, and reference repair.
JetBrains/MPS
Open an MPS project in a running or freshly started MPS instance when MCP tools fail because no project is open (welcome screen), close an open project with mpsmcpcloseproject, or create a new empty…
JetBrains/MPS
Complete JetBrains MPS workflow guide for DSL projects — models, languages, generators, node JSON blueprints, type queries, validation, MPS MCP tool usage, and the index of companion skills.
JetBrains/MPS
Structured MPS bugfix workflow driven by a YouTrack issue ID — preflight tool checks, version/branch derivation, parallel-agent problem analysis, solution design, branch creation, implementation…
JetBrains/MPS
A skill your agent uses when bundling a new plain Java/Kotlin plugin into MPS distribution archives, debugging packaging/layout issues in build/mps.xml, tracing where per-plugin artefacts end up, or…
Works with
Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's structure aspect. Mps Aspect Structure Concepts is an agent skill from JetBrains/MPS, published by the product's own GitHub organization. Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's structure aspect.
Mps Aspect Structure Concepts fits situations like: modifying a languages structure model.
Run `npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a claude-code`. Or copy the skill folder (.agents/skills/mps-aspect-structure-concepts in JetBrains/MPS) into .claude/skills/mps-aspect-structure-concepts in your project. Claude Code loads it when a task matches its description.
Run `npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a codex`. Or copy the skill folder (.agents/skills/mps-aspect-structure-concepts in JetBrains/MPS) into .agents/skills/mps-aspect-structure-concepts in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JetBrains/MPS --skill mps-aspect-structure-concepts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mps-aspect-structure-concepts, .gemini/skills/mps-aspect-structure-concepts, .github/skills/mps-aspect-structure-concepts and .opencode/skills/mps-aspect-structure-concepts in your project.
SKILL.md names no scripts, command-line tools or credentials: Mps Aspect Structure Concepts is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Mps Aspect Structure Concepts is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Mps Aspect Structure Concepts: Claude Docs Consultant (centminmod/my-claude-code-setup, 2.7k stars), Spock Adb (WahdanZ/SpockAdb, 116 stars), Amplicode Install (Amplicode/spring-skills, 126 stars) and Idea MCP (dtprj/dongting, 208 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
JetBrains (a GitHub organization, an official publisher) maintains it in JetBrains/MPS, which has 1,661 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 8, 2026.
Source: JetBrains/MPS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.