Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Building or modifying components in the RomM v2 frontend (frontend/src/v2/). Use when creating/editing v2 primitives (R* components in src/v2/lib/), shared composites, or feature composites — covers the three-tier model, file/folder conventions, SFC structure, import order, barrels, Storybook requirements, and v2 anti-patterns. Trigger on any work under frontend/src/v2/.
Universal input (mouse, touch, keyboard, gamepad) and responsive/universal-viewport layout in the RomM v2 frontend. Use when adding interactive v2 components, focus management, spatial navigation, gamepad/keyboard handling, modality-gated focus rings, breakpoints, or responsive layout. Covers useInput, focus geometry primitives, the overlay scope stack, useBreakpoint, and the data-bp/data-input attributes. Trigger on interactive or responsive work under frontend/src/v2/.
Cross-cutting feature patterns for the RomM v2 frontend — error/snackbar handling, loading & skeleton states, real-time Socket.IO updates, UI state persistence (URL vs localStorage vs ephemeral), pagination/infinite scroll, forms & validation, permissions (useCan), and destructive confirmations. Use when wiring up a v2 feature's behavior (not just its markup). Trigger when implementing data flows, dialogs, forms, toggles, or permission gating under frontend/src/v2/.
Ingest tabular Parquet files into Rerun chunk streams with rerun.experimental.ParquetReader. Read when converting trajectory or sensor tables (LeRobot-style parquet, exported logs) into entities and components — column grouping, timeline/index columns, static columns, and lenses (DeriveLens) that assemble the typed components (Transform3D, Scalars) from the reader's grouped struct/scalar output. Builds on rerun-chunk-processing and rerun-data-model.
Core mechanics of the Rerun Chunk Processing API (rerun.experimental) — LazyChunkStream pipelines, Chunk, lenses (MutateLens/DeriveLens/Selector), RrdReader, writing optimized RRDs. Read BEFORE writing any ingestion/conversion/preprocessing code (convert an MCAP, build a recording from a dataset, preprocess an .rrd, port an old converter): it mandates reader+lens pipelines and steers away from hand-built chunks — no Chunk.from_columns for data a reader/lens can produce, no per-message rr.log, no manual pa.array assembly. Source-specific knowledge lives in the importer skills (rerun-mcap, rerun-urdf, rerun-parquet, rerun-lerobot); read rerun-data-model first to decide what the data should become.
How raw multimodal robot data maps onto the Rerun data model. Read FIRST, before modeling or converting a dataset — and whenever you are about to convert/ingest/preprocess robot data into an .rrd or build a Rerun recording, even if not asked for the data model. Resolves the entity-vs-component, property-vs-component-vs-layer, and static-vs-temporal decisions and routes to the mechanism (do it with readers and lenses, not hand-built chunks or per-message rr.log): rerun-chunk-processing and the importer skills rerun-mcap, rerun-urdf, rerun-parquet, rerun-lerobot.
Add a new business memory kind end-to-end. Pick the storage combination (Markdown / SQLite / LanceDB), pick the markdown strategy (daily-log / skill-named / single-file), then wire up the schema(s), repo(s), and writer(s).
Create a GitHub branch from main with the project naming convention
Update LanceDB to a specific Lance release or tag. Use when bumping Lance dependencies in the lancedb repository, including Rust workspace Lance crates, Java lance-core, validation, branch creation, commit, push, and PR creation when requested.
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.