JetBrains

Use for debugger-driven runtime root-cause analysis in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, and other GameDev or mixed-language projects. Trigger when runtime state or control-flow evidence is needed — actual values, branch taken, call order, thread context, whether execution reaches a chosen line — and cannot be derived confidently from source or logs; when pinning the relevant path would otherwise mean reading many files or tracing a deep call chain; or on an explicit request to debug, set breakpoints, step, or inspect runtime values. Do not use for compile-time or syntax errors, source-obvious bugs, failures already pinpointed by logs/tests, or code merely named debug/Debugger.

Use when semantic refactoring is needed in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, XAML, Razor, and other GameDev or mixed-language projects. Trigger when edits must update declarations and usages across IDE-resolved references — rename symbols, move types or namespaces, safe-delete unused code, extract interface/base class/method, change signatures, or reorganize namespaces. Do not use for file-only moves, config keys, strings, comments, prose-only edits, generated output, or logic changes with unchanged names/signatures.

Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

End-to-end workflow to fix a `_LastInSuiteTest.testProjectLeak` failure reported by TeamCity. Given a TC hashcode / leak diagnostic, this skill drives the full cycle — identify the culprit test, reproduce the leak locally 10x with `tests.cmd`, analyze every unique retention chain observed, apply fixes per chain, and verify by rerunning the leak-hunter until it stops firing. Use when the user asks to fix (not just investigate) a project leak surfaced by TC. Self-contained: does not depend on other skills.

End-to-end workflow to fix a `_LastInSuiteTest.testProjectLeak` failure reported by TeamCity. Given a TC hashcode / leak diagnostic, this skill drives the full cycle — identify the culprit test, reproduce the leak locally 10x with `tests.cmd`, analyze every unique retention chain observed, apply fixes per chain, and verify by rerunning the leak-hunter until it stops firing. Use when the user asks to fix (not just investigate) a project leak surfaced by TC. Self-contained: does not depend on other skills.

Generate New UI icons for the IntelliJ Platform. Use when creating, editing, or reviewing SVG icons for the New UI — action icons (16×16), tree-node icons (16×16), tool-window icons (16×16 + 20×20), main-toolbar icons (20×20), editor-gutter icons (12×12 / 14×14), status-bar icons, and other system icons. Produces a light and a `_dark` variant that share geometry and use the canonical New UI palette so the icons theme correctly in both themes.

Generate New UI icons for the IntelliJ Platform. Use when creating, editing, or reviewing SVG icons for the New UI — action icons (16×16), tree-node icons (16×16), tool-window icons (16×16 + 20×20), main-toolbar icons (20×20), editor-gutter icons (12×12 / 14×14), status-bar icons, and other system icons. Produces a light and a `_dark` variant that share geometry and use the canonical New UI palette so the icons theme correctly in both themes.

Guide for writing UI tests using IDE Starter and UI Driver frameworks. Use when creating or modifying UI tests or when user ask to implement test case from testops.

Guide for writing UI tests using IDE Starter and UI Driver frameworks. Use when creating or modifying UI tests or when user ask to implement test case from testops.

Guidelines for structuring and developing IntelliJ remote development modules. Use when working on Remote Development features.

Internals of tests.cmd execution flow, test discovery, and troubleshooting. Use when debugging test discovery issues or understanding the test runner.

Wire MPS module and model dependencies, used languages, used devkits, extended languages, runtime solutions, accessory models, and language/dependency versions. Use when adding/removing module dependencies, importing languages or devkits into a model, declaring runtime solutions, or shipping accessory content visible to consumers without explicit import.

Use when creating or changing MPS editor definitions — the overall workflow from scaffolding a `ConceptEditorDeclaration` through componentizing reusable `EditorComponentDeclaration`s, refining cell models and cell layouts, applying style sheets and indent-layout style items, wiring smart references, leveraging inheritance via super-concepts and interfaces, inspecting (`print_node_json`, `show_node_representation`) and validating (`check_root_node_problems`). Covers `jetbrains.mps.lang.editor` cell models (`CellModel_RefNode`/`CellModel_RefNodeList`/`CellModel_RefCell`/`CellModel_Property`/`CellModel_Constant`), layout choices, and JSON blueprints for common editor shapes. For the non-layout side (action maps, keymaps, transformation/substitute menus) use `mps-aspect-editor-menus-and-keymaps`.

Analyze an MPS language by name — discover concepts, properties, references, children, aspects (editor/constraints/behavior), and metadata. Use when investigating an unfamiliar language, exploring concept structure, or finding sample nodes to use as templates for JSON blueprints.

Complete JetBrains MPS workflow guide for DSL projects — models, languages, generators, node JSON blueprints, validation, MPS MCP tool usage, and the index of companion skills. Use whenever working in an MPS project, when AGENTS.md says to load the MPS workflow skill, or when you need to pick the right MPS aspect-specific skill.

Use when writing or modifying tests inside MPS `@tests` models — `NodesTestCase` (typesystem, constraints, scopes, dataflow, generator output), `EditorTestCase` (intentions, actions, keystrokes, side-transforms, completion), `MigrationTestCase` (migration scripts), `BTestCase` (plain JUnit on hand-written Java/Kotlin runtime), inline annotations such as `has error` / `has type` / `ScopesTest`, label-based `node<label>` cross-references, caret markers, and running tests via MCP / in MPS. Reach for this skill whenever the task involves authoring or fixing tests in a `tests`-stereotype model, or interpreting failures from one.

Use when running or generating MPS Console code, or when writing `jetbrains.mps.lang.smodel.query` queries anywhere in MPS (intentions, behavior, actions, generator queries, plain BaseLanguage). Covers the console command languages (`jetbrains.mps.console.base` / `ideCommands` / `internalCommands` / `scripts`): `BLCommand` / `BLExpression`, the `#print*` / `#show` result printers, IDE commands (`#make` / `#clean` / `#removeGenSources` / `#reloadClasses` / `#stat` / `#showGenPlan` / `#showBrokenRefs`), `#exec` / `forEach` / `refactor` scripts. Covers the smodel query language: `#nodes` / `#references` / `#models` / `#modules` / `#instances` / `#usages`, the `with`-statement scope wrapper, scopes (`project` / `editable` / `global` / `visible` / `modules` / `models` / `custom`) and query parameters (`scope` / `exact` / `r/o+`). Also how to insert, read, recall, and run console commands with `mps_mcp_insert_console_command_from_json`, `mps_mcp_get_current_editor_root_node(source="console")`, `mps_mcp_get_console_

Investigate inheritance between MPS languages and between concepts — extended languages, superconcepts, implemented interfaces, sub-/assignable concepts, and cross-language specialization. Use when tracing language hierarchies, finding extension points, or checking concept assignability.

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.

Review code, test, and workflow-machinery changes across multiple dimensions using specialized agents with triage-based selection.

Research the codebase and create an implementation plan with architecture notes, design document, and track decomposition. Use when starting a new feature or large change.

Execute the implementation plan: autonomous plan review (Phase 2) on first invocation, then track-by-track execution (Phase A review + decomposition, Phase B implementation, Phase C code review). Use after /create-plan to implement the planned work.

Diagnose and fix a CI test failure from a GitHub PR or workflow run. Includes root cause analysis, dimensional code review, and PR creation.

Apply an edit to `design.md` or `design-mechanics.md` through the mutation discipline: apply → auto-review → iterate → present. Use this instead of directly Editing those files.

Audit a finished design document for hard-to-read or hard-to-understand paragraphs, then harden the house-style rules so future design docs avoid them. Fans out audit sub-agents, classifies each obscure passage as caught-by-an-existing-rule or a gap, and proposes plus (on approval) applies rule changes across the style docs. Use when the user wants to feed a design doc back into the style guide, find obscure paragraphs and fix the rules, harden the writing rules from a real DD, or close the readability feedback loop. Accepts a design-doc path, an adr dir name, or defaults to the current branch's design. Reports the doc's own violations; does not rewrite the doc.

Reviews any draft for AI writing tells and produces a clean rewrite. Catches structural fingerprints (negative parallelism like "It's not X, it's Y", bullet-everything, Title Case headings, adjective triads), analysis fingerprints (superficial -ing clauses, passive voice, vague attribution, hedge stacking), and tone fingerprints (throat-clearing, closing phrases like "In conclusion"). Use this skill whenever the user asks to humanize, de-AI, edit, polish, or sanity-check writing, including phrases like "does this sound like ChatGPT", "make this less AI", "humanize this", "edit this draft", "remove the AI smell", "is this AI-y", or "clean this up". Also trigger when the user pastes a draft and asks for feedback on the writing without naming AI specifically.

Manually re-run the autonomous plan review (Phase 2 — consistency + structural). The same review runs automatically as the first phase of /execute-tracks; this command is for re-runs after inline replanning or whenever the plan needs explicit re-validation. TRIGGER when: user asks to re-validate the plan after inline replanning; user requests explicit plan review outside /execute-tracks. SKIP: /execute-tracks already running State 0 in this session (autonomous Phase 2 path will fire) — do not double-run.

Run the full development pipeline autonomously without pausing between phases. Stops only on quality-gate failures.

Run test coverage measurement, analyze results, and fix gaps when coverage falls below the 80% threshold.

Fetch unresolved PR review threads, triage them, implement fixes, validate, reply in-thread, and resolve.

Stage, commit, push, and open a GitHub PR following project conventions. Use when code is ready to ship.

Run structured evaluations on skills to measure quality and track improvements.

Review local code changes for correctness, regressions, missing tests, and Databao-specific risks.

Ensure a YouTrack issue exists before starting work. Validates existing tickets or creates new ones.

Review architecture quality, maintainability, and developer experience.

Senior Android engineer workflows — Kotlin-first (Java legacy supported), Jetpack Compose + View system, MVVM, Coroutines/Flow, Room, Retrofit, Hilt, plus device orchestration via plugin tools (device management, logcat, crash reports, app run) and mobile-mcp for UI interaction (element tree, taps, swipes). Use when implementing features, debugging crashes, fixing builds, writing tests, reviewing Android code, or running QA on an emulator.

Use when working on Laravel projects. Covers architecture decisions (Services vs Actions), thin controllers, Form Requests, API Resources, and API versioning. Enforces Larastan verification after code generation.

Up-to-date library and framework documentation via Context7 MCP. Use when setup, API, or version-specific questions require current documentation.

Modern PHP 8.x policy and pitfalls. Use when writing, reviewing, or refactoring PHP code — enforces strict types, enum/readonly/match/DNF policy, PHPStan discipline, and catches the subtle traps (type coercion, mixed abuse, readonly mutation through references, enum serialization, fiber lifecycle, PDO emulation) that LLMs get wrong by default.

Redis policy & pitfalls — key naming, atomicity, TTL strategy, distributed locks, cache patterns, production traps. Use when designing Redis-backed caches, locks, queues, rate limiters, or sessions. Covers the traps LLMs get wrong by default: SETNX + EX (deprecated), KEYS on production, Pub/Sub no-persistence, HGETALL on big hashes, maxmemory-policy defaults, cluster hash tags, RDB fork memory.

SQL policy & pitfalls — query correctness, indexing strategy, safe migrations. Use when writing SQL, diagnosing slow queries, designing schemas, or reviewing Flyway/Liquibase migrations. Covers the traps LLMs miss by default: NOT IN with NULLs, function-on-column breaking indexes, OFFSET on large tables, NOT NULL column lock, CREATE INDEX blocking writes, immutable migrations.

Java 17–25 policy and pitfalls. Use when writing, reviewing, or refactoring Java code — enforces idioms around records, sealed types, switch exhaustiveness, Optional, virtual threads, and null-safety that LLMs frequently get wrong.

Kotlin 2.x policy and pitfalls. Use when writing, reviewing, or refactoring Kotlin code — enforces coroutine-safety, Flow correctness, null-safety, and API-design rules that LLMs frequently get wrong.

Explore and understand unfamiliar codebases using semantic code search

Experimental jbcontext org-wide blast-radius analysis across multiple repositories. Use when Codex needs to estimate the impact of changing an API, endpoint, schema, event, shared library, config, feature flag, data model, behavior, or dependency by finding producers, consumers, owners, tests, and related repos.

Install jbcontext and complete first-time setup — login and configure agent integration. Use when `jbcontext` is not found or the user asks to install jbcontext.

Research and understand unfamiliar codebases using semantic search with `jbcontext search`

Use this skill to review code changes using semantic search to understand context and impact

Experimental jbcontext org-wide dependency search across multiple repositories. Use when need to find APIs in other repositories, or dependency configuration are used across repos for upgrades, removals, CVEs, migrations, or ownership discovery.

Experimental jbcontext org-wide semantic search across multiple repositories

Maintains the IdeaVim changelog (CHANGES.md). Use when updating the changelog, documenting releases, or reviewing commits/PRs for changelog entries.

IdeaVim git workflow conventions covering commits, branches, PRs, and CI. Use when creating commits, managing branches, creating pull requests, reviewing git history, or any git-related activity in the IdeaVim project.

Migrates IdeaVim extensions from the old VimExtensionFacade API to the new @VimPlugin annotation-based API. Use when converting existing extensions to use the new API patterns.

Handles deduplication of YouTrack issues. Use when cleaning up duplicate issues, consolidating related bug reports, or organizing issue tracker.

Maintains IdeaVim test suite quality. Reviews disabled tests, ensures Neovim annotations are documented, and improves test readability. Use for periodic test maintenance.

Keeps IdeaVim documentation in sync with code changes. Use this skill when you need to verify documentation accuracy after code changes, or when checking if documentation (in doc/, README.md, CONTRIBUTING.md) matches the current codebase. The skill can work bidirectionally - from docs to code verification, or from code changes to documentation updates.

Use when locating code in a Rider-supported solution (.NET/C#, F#, VB, C++, Unity, Unreal, XAML, Razor, mixed-language) — find where a symbol is declared, find usages/text/regex matches, or find files by glob. Trigger instead of shell grep/ripgrep/glob/find and instead of opening files to hunt, because these tools query the IDE index and return exact locations only. Do not use for non-Rider projects, for editing/refactoring code, or when you already hold the exact path you need.

Use when semantic refactoring is needed in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, XAML, Razor, and other GameDev or mixed-language projects. Trigger when edits must update declarations and usages across IDE-resolved references — rename symbols, move types or namespaces, safe-delete unused code, extract interface/base class/method, change signatures, or reorganize namespaces. Do not use for file-only moves, config keys, strings, comments, prose-only edits, generated output, or logic changes with unchanged names/signatures.

Use for debugger-driven runtime root-cause analysis in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, and other GameDev or mixed-language projects. Trigger when runtime state or control-flow evidence is needed — actual values, branch taken, call order, thread context, whether execution reaches a chosen line — and cannot be derived confidently from source or logs; when pinning the relevant path would otherwise mean reading many files or tracing a deep call chain; or on an explicit request to debug, set breakpoints, step, or inspect runtime values. Do not use for compile-time or syntax errors, source-obvious bugs, failures already pinpointed by logs/tests, or code merely named debug/Debugger.

Use when writing or modifying UE C++ (classes, actors, components, subsystems, interfaces, function libraries) with Rider MCP available. Value over bash/grep: IDE diagnostics catch UHT/reflection errors and missing module deps without a full build; lint_files enforces cross-file consistency. DO NOT TRIGGER for: Blueprint-only tasks, editor automation with no C++. When Rider MCP is unavailable, runs in reduced mode — standard file tools only, IDE diagnostics skipped.

Use when debugging UE C++ crashes, runtime bugs, or unexpected behavior with Rider MCP available. Value over bash/grep: analyze_calls traces C++ call hierarchies (ReSharper backend); get_file_problems surfaces IDE-detected issues; get_symbol_info confirms API contracts; xdebug_set_breakpoint sets live breakpoints; ue_execute_python queries live PIE state. DO NOT TRIGGER for: pure build errors with no runtime component, net-new feature work, Blueprint-only work. When Rider MCP is unavailable, runs in reduced mode — Bash/Grep only, IDE diagnostics skipped.

Use when writing or modifying UE automated tests (Automation, CQTest, Functional, Gauntlet, LowLevel) with Rider MCP available. Value over bash/grep: IDE diagnostics catch test registration errors, wrong RunTest return type, and missing includes before a build; get_symbol_info verifies the API under test. DO NOT TRIGGER for: debugging existing test failures (use ue-live-debugging), Blueprint-only testing. When Rider MCP is unavailable, runs in reduced mode — standard file tools only, IDE diagnostics skipped.

Bumps the Gradle API version that Kotlin Gradle plugins are compiled against in the Kotlin compiler repository. Use this skill whenever the user asks to upgrade, bump, or update the Gradle compile API version, Gradle plugin API version, or GRADLE_COMMON_COMPILE_API_VERSION. Also use it when the user says something like "update KGP to compile against Gradle X.Y.Z" or "bump Gradle API to X.Y" or "we need to support Gradle X.Y in the plugin".

Add KaResolver resolveSymbol/resolveCall support for a PSI type

Drive the per-module internal-API codebase test, then refine the suggested annotations down to `internal` (or up to `@KaImplementationDetail`) based on actual external usage

Create a KTIJ cherry-pick tracking issue for a KT fix that needs to be cherry-picked to an IntelliJ branch. Use when cherry-picking Analysis API fixes.

Disables the TeamCity generation check (`forbidGenerationOnTeamcity`) for Kotlin version branching. Only invoke manually via /disable-generation-check.

The existing-codebase branch of project-setup: analyze a repo that has code but no specs and draft its first spec graph — goal-and-requirements.md, architecture.md, and short per-module SPEC.md files — deriving everything possible from the code and agent files (AGENTS.md, CLAUDE.md, README, manifests), and interviewing the user only for the intent the code can't reveal. Normally reached via the project-setup dispatcher.

The brand-new / empty-project branch of project-setup: turn a raw idea into a focused goal-and-requirements.md through a short, tailored interview (vision, MVP scope, success criteria, tech). Normally reached via the project-setup dispatcher, on an empty workspace with no code yet. For features in an existing project, use brainstorming instead.

Start here to set up or onboard a project's specs — draft its first goal-and-requirements.md, architecture.md, and module specs. The front door that detects whether the workspace is a brand-new/empty project or an existing codebase with no specs, then routes to the right flow. Use whenever asked to set up, onboard, initialize, or spec a project.

Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.

The project's specs are its ground truth: durable documents describing the architecture, decisions, contracts, and boundaries behind the code, organized as a connected graph. Read this skill and reach for the spec tools FIRST — before reading code — whenever you explore the project, plan or start a task, add or change a feature, implement anything, investigate an area, check work against recorded decisions and contracts, or otherwise work with specs. Also use it to create or maintain specs.

This skill should be used when the user asks about "running iOS tests", "iOS instrumented tests", "how to run ios tests", "launch specific ios test", "add new ios instrumented test" and these tests are located in the "compose/ui/ui/src/uikitInstrumentedTest" directory.

A skill for building instrumented tests in Remote Compose using GridScreenshotUI.

A skill for building instrumented screenshot tests in Remote Compose using RemoteComposeScreenshotTestRule.

This skill should be used when the user asks to "update Kotlin version", "upgrade Kotlin", "change Kotlin to X.Y.Z", or mentions updating the Kotlin compiler version in the project.