kornia
- 14 skills
- 0 followers
- 5 hours ago last updated
- ▌ Release · korniaUse when cutting a kornia-rs release or pre-release (rc) — bumps the workspace version, updates CHANGELOG.md (moving [Unreleased] into a dated section and referencing the previous release), opens the release PR, and triggers the crates.io / wheel publish workflows. Trigger on "cut a release", "prepare a release", "pre-release", "publish to crates.io", "bump version".
- ▌ Kornia Developer · korniaUse when developing on kornia — making an op torch.compile / dynamo compatible, fixing a graph break, or optimizing for speed. Codifies the compile-first workflow — genuine fullgraph fixes (no is_compiling hacks), byte-to-byte eager preservation, cross-library benchmarking toward the 10x-vs-albumentations moonshot.
- ▌ Bubbaloop Physical AI · kornia bundleManage physical sensors, cameras, and actuators via the bubbaloop skill runtime. Query real-time sensor data, control node lifecycle, and monitor hardware health.
- ▌ UI UX Pro Max · kornia bundleUI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
- ▌ Using Bubbaloop · korniaUse when interacting with a Bubbaloop deployment via its MCP server — guides the discovery → control → automation workflow and prevents the most common mistakes (MCP polling for streaming data, missing Bearer token, ignoring RBAC tier).
- ▌ Vrt Tracking · korniaUse when working on multi-object tracking or metric-3D geometry — the vrt-track 3D Kalman, ByteTrack association, depth gating, NSA noise, occlusion recovery, coasting, world-frame BEV, camera intrinsics/extrinsics/undistort (vrt-types), or the appearance/ReID hook. Covers the tracker's design + tuning knobs and how metric depth feeds it, not GPU/model internals.
- ▌
- ▌ Cuda Kernel Craft · korniaUse when writing, optimizing, or reviewing CUDA kernel code itself (the __global__ functions) — block/grid sizing, memory coalescing, divergence, shared memory, precision, and Jetson Orin (SM87) specifics. Complements rust-cuda-patterns (which covers the Rust launch side).
- ▌ Rust Cuda Patterns · korniaUse when writing or modifying CUDA code from Rust in this repo — kornia CudaKernel JIT, cudarc launches/memory/events, device pointers from TRT, or the trt-sys C FFI shim. Covers this repo's conventions, not general CUDA.
- ▌ Trt Engine Rebuild · korniaUse when building, rebuilding, or debugging TensorRT engines on this Jetson — shape profile errors ("does not satisfy any optimization profiles"), new ONNX exports, FP16 engines, or engine/version mismatch on deserialize.
- ▌ Jetson Benchmarking · korniaUse when measuring, comparing, or reporting performance numbers on this Jetson — FPS, latency, GPU time, before/after optimization claims. Enforces power-mode discipline and correct interpretation of PipelineTiming fields.
- ▌ Vrt Add Model Crate · korniaUse when adding a new model crate to vision-rt (a new detector/segmenter/depth/pose net) — crate layout, the async caller-owned pattern, classifying engine outputs by shape, from_engine_file/from_onnx/from_hub constructors, vrt-hub registration, export/build scripts, and the build/clippy discipline. Copy vrt-rfdetr-seg or vrt-depth-anything as the template.
- ▌ Vrt Pipeline Compose · korniaUse when building or composing a real-time CV pipeline from vrt model crates — wiring RfDetrSeg / DepthAnything / XFeat together, running N models on one frame, feeding the GPU results to the CPU tracker (vrt-track) + live view (vrt-viz, H.264/WebCodecs), going fast, or handling multiple cameras. Covers the async / caller-owned / one-stream idiom, not kernel internals.
- ▌ Model Tensor Semantics · korniaUse when working on XFeat pre/post-processing, keypoints, descriptors, or matching — tensor shapes, coordinate spaces, normalization, NMS/top-K, and the exact algorithm steps implemented in vrt-xfeat.