Impertio-Studio

Use when a task spans multiple AEC technologies (Blender, IfcOpenShell, Bonsai, Sverchok) and you need to decide which tool handles which step, or when orchestrating multi-step BIM pipelines such as IFC creation to visualization to authoring. Prevents the…

Use when implementing end-to-end BIM workflows that combine IfcOpenShell, Bonsai, and Blender -- such as IFC creation from scratch, model enrichment, validation pipelines, geometry extraction, or batch processing of building models. Prevents the common…

Use when reviewing, validating, or auditing Blender Python code for correctness. Runs systematic checks for deprecated API usage, context errors, version compatibility issues, threading violations, data reference invalidation, incorrect operator calls, and…

Use when migrating, porting, or upgrading Blender Python scripts and addons across major versions (3.x to 4.x to 5.x). Provides a systematic migration process covering API renames, removed functions, changed parameters, extension system migration, BGL to GPU…

Use when writing Blender Python scripts that access bpy module structure, RNA data, the context system, dependency graph, or operator invocation. Prevents the common mistake of accessing context attributes outside their valid scope or calling operators…

Use when drawing custom overlays, viewport visualizations, or offscreen renders in Blender Python. Prevents the critical mistake of using the deprecated bgl module (removed in Blender 5.0) instead of the gpu module. Covers gpu.shader, gpu.batch, gpu.state,…

Use when dealing with Blender Python runtime behavior -- mathutils, threading, handlers, timers, or crashes after undo/redo. Prevents the #1 runtime crash: using threading for bpy operations instead of bpy.app.timers, or caching bpy.data references across…

Use when writing Blender Python code that must work across multiple versions (3.x/4.x/5.x), or when migrating scripts between Blender versions. Prevents breakage from renamed APIs, removed modules (bgl in 5.0), and changed function signatures. Provides the…

Use when receiving vague or unclear ERPNext/Frappe development requests that need interpretation. Transforms requirements like 'make invoice auto-calculate' or 'add approval workflow' into concrete technical specifications. Determines which Frappe mechanisms…

Use when reviewing or validating Frappe/ERPNext code against best practices and common pitfalls. Checks generated code before deployment, validates against all 61 frappe-* skills, catches v16 patterns (extend_doctype_class, type annotations), validates ops…

Deploy HTML/CSS websites to ERPNext/Frappe (v15/v16) as Web Pages via the REST API. Use this skill whenever a user wants to host a website on ERPNext, deploy HTML mockups to Frappe, create Web Pages programmatically, configure Website Settings, or integrate…

Use when designing multi-app Frappe architectures, deciding whether to split functionality into separate apps, or implementing cross-app communication patterns. Prevents monolithic app sprawl, circular dependencies between apps, and broken override chains.…

Use when debugging Frappe errors, using bench console for live inspection, analyzing tracebacks, or reading Frappe log files. Prevents wasted debugging time from ignoring log context, misreading tracebacks, and not using bench console effectively. Covers…

Use when migrating a Frappe app between major versions, detecting breaking API changes, or resolving post-migration errors. Prevents failed migrations from undetected deprecated APIs, removed methods, and changed function signatures. Covers breaking change…

Use when building ERPNext/Frappe API integrations (v14/v15/v16) including REST API, RPC API, authentication, webhooks, and rate limiting. Covers external API calls, endpoint design, token/OAuth2/session authentication. Keywords: API integration, REST…

Use when implementing Redis caching, cache invalidation, or distributed locking in Frappe. Prevents stale cache bugs, race conditions from missing locks, and memory bloat from unbounded cache keys. Covers frappe.cache(), @redis_cache decorator,…

Use when you need to understand or explain how the IFC schema is organized, decide which conceptual layer an entity belongs to, judge whether one schema is allowed to reference another, or work out why an entity does or does not carry a GlobalId. Prevents the…

Use when authoring a new IFC file from scratch and the minimal valid skeleton must be built before any element can be added: the IfcProject context root, the IfcUnitAssignment, the IfcGeometricRepresentationContext, the spatial tree, the IfcOwnerHistory, the…

Use when producing, reading, or extracting COBie facility-management handover data from an IFC model: mapping COBie worksheets to IFC entities, deciding which records belong in COBie scope, choosing between the IFC STEP exchange and the spreadsheet form, or…

Use when choosing which IFC implementation library to use for a project, or when unsure which tool reads and writes IFC files for a given language, platform, or target IFC version. Prevents picking a library that does not fit the language or platform,…

Use when reading, generating, or evaluating an ifcJSON file, choosing a JSON encoding for IFC data in a web or REST application, or resolving the ref-based cross-references in an ifcJSON document. Prevents treating ifcJSON as a stable standardized format,…

Use when you need to read, write, or recognise an ifcXML file, understand the iso_10303_28 / uos document structure, or resolve id / ref / href references in IFC XML data. Prevents confusing ifcXML (ISO 10303-28) with the STEP Physical File (ISO 10303-21),…

Use when asked to migrate an IFC file to another schema version, upgrade an IFC2x3 model to IFC4 or IFC4.3, downgrade an IFC4 model, or plan a schema-version conversion of an IFC dataset end to end. Prevents copying attributes blindly across a version…

Use when an IFC file is schema-valid but you must judge whether it is actually useful, audit an IFC model for information completeness, score model quality before handover, or answer why a valid IFC file is empty in facility management, quantity take-off, or…

Use when starting any Rust task to route to the correct rust-* skill, and when finishing any Rust task to run the cross-skill quality checklist (clippy, rustfmt, MSRV, edition idioms, error handling, async hygiene, doc coverage). Prevents loading the wrong…

Use when the user asks about Rust editions (2015/2018/2021/2024), MSRV, the version matrix, channels (stable/beta/nightly), what stabilized in which release, or how Rust evolves. Prevents writing pre-2024 idioms in edition-2024 code, recommending unstabilised…

Use when the user needs to understand Rust's type system fundamentals: nominal typing, zero-sized types, repr attributes, niche optimization, primitive types, the never type, type-state pattern, or const generics. Prevents misusing repr(C) when default repr…

Use when the user needs Generic Associated Types: `type Item<'a>` in a trait, the `LendingIterator` pattern, callback registries parameterised by lifetime, or families of types whose lifetime/type varies per call. Prevents reaching for higher-kinded-type…

Use when the user writes a `match`, `if let`, `let else`, `while let`, an if-let chain (edition 2024 stable in 1.88), destructures a struct/tuple/enum/slice/reference, uses `ref` / `ref mut`, guards, or or-patterns. Prevents non-exhaustive `match` on enums,…

Use when iterating on rustc compile errors: how to read a rustc error, which errors to fix first, when to apply rustc's suggestion blindly vs inspect it, when to consult `rustc --explain`, and when to stop and ask instead of cascading edits. Prevents fixing…

Use when reviewing Rust code for quality: clippy lint categories, naming idioms, error-handling hygiene, async correctness, memory-pattern appropriateness, and justified lint suppressions. Prevents approving code with unjustified `.unwrap()`, `.await` inside…

Use when the user chooses an error-handling crate: `thiserror` for structured library errors, `anyhow` for opaque application errors, both together, or migrates between them. Prevents using anyhow in a public library API, using thiserror where a one-off…

Use when running any shadcn CLI command (init, add, view, search, apply, preset, build, docs, info, migrate), when writing or editing components.json, when choosing between tsconfig path aliases and package.json#imports aliases (new in shadcn@4.7.0), when…

Use when adding a new component to a project that already uses shadcn, when bootstrapping shadcn for the first time in a fresh app, when deciding between `shadcn add`, a hand-built primitive, or a pre-built block, when wiring path aliases (tsconfig paths or…

Use when authoring or consuming a shadcn registry, when configuring the `registries` field in components.json, when wiring a private or paid component library behind a namespace prefix like `@myorg/datepicker`, when securing a custom registry with bearer…

Use when a shadcn ui Command primitive (command palette, Combobox, search list, fuzzy filter, multi-select dropdown) stops filtering, renders the full list regardless of typing, fails to highlight or click items, throws "TypeError : undefined is not iterable…

Use when initializing shadcn ui inside a Vite, Next.js (App or Pages Router), React Router v7 (former Remix), Astro, or TanStack Start project, or when diagnosing per-framework init issues like wrong rsc flag, broken `@/*` alias resolution, or missing…

Use when reviewing, validating, or auditing a shadcn ui component that uses class-variance-authority (cva), when an LLM has just produced a Button-like, Badge-like, Alert-like, or any other cva-driven component and you must verify the variant API before…

Use when validating a react-hook-form + zod + shadcn Form integration in a code review, a draft AI-generated form, or a bug report ("my validation does not trigger", "the error message never shows", "the Select does not bind", "submit fires but values are…

Use when auditing a Next.js App Router codebase that consumes shadcn ui for misplaced or missing `"use client"` directives, when reviewing a pull request that adds shadcn primitives and you must confirm the boundary is correct before merging, when a build…

Use when reviewing a database migration for production safety before it runs, or auditing a migration file in a pull request. Prevents shipping a plain CREATE INDEX that locks writes, a full-rewrite ALTER COLUMN TYPE, a breaking DROP/RENAME without…

Use when reviewing a PostgreSQL schema or DDL design before it ships, or auditing an existing schema for structural problems. Prevents shipping tables with no primary key, un-indexed foreign keys, multi-tenant tables with no RLS strategy, SERIAL where…

Use when a replica is behind, a replication slot is bloating WAL, or a logical subscription is stuck. Prevents primary disk filling from an inactive slot, discovering lag only at failover time, and ignoring a stuck subscription that never self-heals after a…

Use when reviewing SQL queries for correctness and performance before they ship, or auditing existing queries in a codebase. Prevents rubber-stamping queries without checking index usage, missing a WHERE-less UPDATE/DELETE, and overlooking implicit casts or…

Use when queries are canceled by timeout, sessions hold locks while idle, or you need to bound query and transaction duration safely. Prevents a forgotten open transaction blocking vacuum forever (set idle_in_transaction_session_timeout), blindly retrying a…

Use when connections fail with authentication errors, no pg_hba.conf entry, SSL handshake problems, or too-many-connections. Prevents trust auth on production hosts, sslmode=require giving a false sense of security (no server verification), editing…

Use when choosing a transaction isolation level, handling serialization_failure errors, or preventing write-skew anomalies. Prevents treating 40001 as a hard error instead of retrying, retrying only the last statement instead of the whole transaction, and…

Use when inserts or updates fail with unique, foreign-key, not-null, check, or exclusion constraint errors. Prevents the catch-23505-then-UPDATE race (use ON CONFLICT atomically), slow cascading deletes from un-indexed FK columns, and impossible inserts from…

Use when building an accessible data table (semantic markup, sortable columns, sticky header that stays put while users scroll long lists, mobile-safe reflow strategy, row selection with select-all and indeterminate state, virtualised tables that need…

Use when auditing a UI component, page, or feature for the three combined failure modes a frontend product can ship : WCAG 2 2 accessibility violations, Core Web Vitals (LCP / INP / CLS) regressions, and cross-skill consistency drift (naming, structure, token…

Use when auditing a CSS codebase for design-system compliance, reviewing a pull request that touches `.css` / `.scss` / `.ts` / `.tsx` / `.vue` / `.svelte` files with style declarations, hunting for hardcoded color / spacing / font-size / radius values that…

Use when a mobile hero section overflows because of `100vh`, deciding between the small (`svh`), large (`lvh`), and dynamic (`dvh`) viewport-unit families, picking between `em` and `rem` for font-size or component spacing, reasoning about CSS px versus device…

Use when a CSS rule that should clearly win does not (style not applying despite higher specificity), when `!important` is being escalated as a fix-everything hammer (you are about to lose a specificity war by joining it), when an unlayered author rule…

Use when diagnosing the canonical layout failures of modern CSS : a flex child that overflows its parent (the auto `min-content` floor), three `1fr` grid columns that refuse to be equal (the same floor), a `position: sticky` element that never sticks…

Use when a single-page-app DOM swap needs a Shared-Element transition (old and new states cross-fade with named elements morphing between them) without rolling a custom FLIP library, when a multi-page-app navigation should animate seamlessly from one document…

Use when authoring a custom HTML element with `customElements.define`, attaching a shadow root with `attachShadow`, distributing children via `<slot>`, reacting to attribute changes via `observedAttributes` + `attributeChangedCallback`, server-rendering the…

Use when building a WebGPU application end to end, setting up the full adapter to device to pipeline to resource chain, or deciding which WebGPU skill applies to the current step. Prevents setup-order mistakes, wrong buffer usage flags, and bind-group layout…

Use when reviewing or validating generated WebGPU or WGSL code before trusting it, or auditing a WebGPU codebase for correctness. Prevents shipping hallucinated APIs, alignment errors, missing device-loss handling, and unlabeled descriptors. Covers a…

Use when debugging WebGPU: diagnosing validation messages, surfacing WGSL compile errors, or capturing a GPU frame. Prevents the undebuggable-from-a-generic-message problem caused by unlabeled descriptors. Covers object labels, error scopes for isolation,…

Use when handling WebGPU device loss, the device.lost promise, or recovering after a GPU process crash. Prevents the silent-retry-loop anti-pattern and recovering after an intentional device.destroy. Covers the device.lost promise, GPUDeviceLostInfo reason…

Use when a WebGPU call fails validation, when capturing errors with error scopes, or when handling the uncapturederror event. Prevents the mistake of treating uncapturederror like a synchronous getError. Covers GPUValidationError, GPUOutOfMemoryError,…

Use when building WebGPU compute workloads: image processing, particle systems, physics simulation, or reduction and prefix-sum. Prevents data races and stale-read bugs in multi-pass compute pipelines. Covers image processing, particle systems, physics…

Use when building WebGPU render workloads: PBR materials, full-screen passes, post-processing, or screen-space effects. Prevents the unnecessary-vertex-buffer mistake for full-screen passes and WebGL clip-space assumptions. Covers PBR material setup, the…

Use when porting a WebGL or WebGL2 application to WebGPU, or mapping a WebGL concept to its WebGPU equivalent. Prevents broken ports from clip-space differences and the missing automatic mipmap generation. Covers the WebGL to WebGPU concept mapping,…

Use when a user provides a slow query plus its EXPLAIN output and wants a concrete optimization, or asks "make this query faster", or wants an index recommendation validated against MariaDB optimizer behavior. Prevents the common mistake of suggesting an…

Use when reviewing a proposed MariaDB schema before it ships, auditing an existing schema for engine / indexing / naming / normalization problems, or validating a migration DDL. Prevents the common mistake of shipping a schema with MyISAM tables, UUID-text…

Use when a Galera cluster reports certification failures, ER_LOCK_DEADLOCK fires at COMMIT in a multi-master setup, wsrep_local_cert_failures keeps climbing, a hot-row is contended across nodes, or the cluster appears to be in split-brain. Prevents the common…

Use when a query is slow, when reading EXPLAIN output, when deciding on index hints, when tuning optimizer_switch flags, when using optimizer_trace, or when comparing MariaDB and MySQL optimizer behavior. Prevents the common mistake of trusting type=ALL…

Use when writing INSERT, UPDATE, DELETE, REPLACE, or upsert statements, debugging "why was this row not updated", or migrating MySQL DML patterns to MariaDB. Prevents the INSERT IGNORE silent-corruption trap, REPLACE INTO FK cascade, ON DUPLICATE KEY…

Use when investigating "my query worked yesterday and now doesn't", upgrading between LTS releases, migrating from MySQL, or setting up a new MariaDB instance with explicit sql_mode and charset. Prevents the common mistake of relying on implicit defaults that…

Use when choosing which MariaDB version to install, upgrading between LTS releases, reasoning about feature availability, or interpreting EOL dates. Prevents the common mistake of assuming a feature works in 10.6 when it landed in 10.11, or running production…

Use when validating a MySQL SQL dump or schema before importing into MariaDB, checking a codebase for MySQL-specific syntax that breaks on MariaDB, or producing a migration remediation checklist. Prevents the common mistake of importing a MySQL 8 dump with…

Use when starting a new CesiumJS application or feature and deciding how to structure the scene: which viewer class, which imagery and terrain, how to represent a dataset, and whether to enable on-demand rendering. Prevents the wrong-API-tier choice (Entity…

Use when CesiumJS code has just been generated or reviewed and must be checked before it is called done, to catch deprecated APIs and common defects, or when auditing CesiumJS code from an older source. Detects the removed synchronous patterns (readyPromise,…

Use when CesiumJS geometry renders in the wrong place, falls through the terrain, sits at the center of the Earth, or never appears, and when position values come back as NaN. Prevents the radians-versus-degrees mistake, the Cartographic-versus-Cartesian3…

Use when a CesiumJS app's memory keeps growing, the browser tab slows down or crashes after running a while, or the console reports "Too many active WebGL contexts" or "DeveloperError: This object was destroyed". Covers WebGL resource leaks from missing…

Use when a CesiumJS globe renders blank, black, white, or frozen, when the canvas shows nothing, when the WebGL context is lost, or when a render-loop error panel covers the canvas. Prevents the blank-globe trap caused by an unset CESIUM_BASE_URL, a missing…

Use when a Cesium3DTileset does not load or render: the console floods with CORS errors, the network tab shows 401 or 403, readyPromise is undefined, fromUrl resolves but nothing appears, the tileset has holes, or fromUrl rejects with a RuntimeError. Covers…

Use when placing a BIM model, CAD model, IFC export, or city model into a CesiumJS globe at its real geographic location, and the model renders at the center of the Earth, sits at the wrong place, floats above or sinks below terrain, or faces the wrong…

Use when a bundled CesiumJS app shows a blank globe, logs 404s for Workers, Assets, or Widgets, fails with a worker or bundler error, or when converting a Sandcastle example into a production build. Covers the cesium npm package, the four static directories,…

Use when a Tailwind utility class is in the compiled CSS but does NOT visually override a component class or a third-party rule, when @apply produces output that does not behave like the utility applied to a real element, when a custom utility you authored…

Use when upgrading a Tailwind CSS v3 codebase to v4 and hitting silent visual regressions, build errors after switching imports, or unexpected behavior changes that the codemod did not catch. Catalogs every default-behavior change between v3 and v4 with…

Use when reviewing a Tailwind CSS codebase for cross-rule violations, performing a pre-PR audit of changes that touch styling, validating a v3-to-v4 migration result, or running a periodic codebase health check across utility classes, plugin authoring, and…

Use when a Tailwind build completes successfully but the compiled CSS is empty, partial, or stale, when classes appear in markup but styles never render in the browser, when a freshly added utility refuses to take effect, when an HMR update leaves the page…

Use when a Tailwind element has 20+ utility classes on one line, when reviewers complain about "utility soup", or when deciding between leaving utilities inline, extracting a component, or pulling utilities into @apply. Prevents the premature-extraction trap…

Use when Tailwind classes work in development but disappear in production builds, or when class names assembled at runtime (template literals like bg-${color}-500, server-injected JSON, CMS-driven attributes, i18n strings, user-configured colours) render in…

Use when migrating a project from Tailwind CSS v3.4 to v4.0+, deciding between the automated upgrade tool and manual conversion, planning a dual-version monorepo transition, auditing a codebase before the upgrade, or verifying behaviour after the upgrade.…

Use when composing Tailwind class strings dynamically across React, Vue, Svelte, Solid, or any framework where a parent component passes override classes to a child via a className prop, and the child combines them with its own defaults. Solves the…

Use when auditing or reviewing existing Axum code, a diff, or a single file for correctness, reliability, and security defects, when a code review must flag Axum-specific mistakes, or when checking an Axum service against the package best practices before a…

Use when the request is to build a complete Axum service from scratch rather than to fix one isolated piece: "build me an Axum API", "scaffold a Rust web service", "set up a new Axum project", or when a half-built service needs the missing production layers…

Use when an Axum extractor fails and you need control over the HTTP error: customizing a Json/Path/Query rejection, returning a JSON error body instead of Axum's plain text, building a unified API error type, or upgrading 0.7 to 0.8 and Option extractors…

Use when the compiler rejects an Axum handler with "the trait bound ... Handler<_, _> is not satisfied", when a function will not register on a route, when the error block names Handler with inference placeholders and lists unrelated impls as help, or when a…

Use when a handler must return an error, when adding a custom error type to an Axum service, when the question mark operator will not compile inside a handler, when anyhow::Error does not implement IntoResponse, or when a fallible tower middleware Service is…

Use when deploying an Axum service to production, containerizing it with Docker, or when a SIGTERM from Docker, Kubernetes, or systemd kills in-flight requests on every restart or rolling deploy. Prevents dropped requests on shutdown, 1.5 GB images from…

Use when generating an OpenAPI 3 specification and a Swagger UI for an Axum service: documenting handlers, describing request and response schemas, or serving an interactive API explorer. Prevents the hand-written spec that silently drifts from the real…

Use when adding structured logging or request tracing to an Axum service, when wiring a tracing-subscriber, when instrumenting handlers, when log timings look interleaved or spans nest under the wrong parent, or when exporting spans to an OpenTelemetry…