Agent skill · NVIDIA
i4h-workflow
Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.
What it needs
About 3k tokens when loaded.
What this skill does
i4h Workflows Purpose Orient the user from live repository facts, then hand execution to the narrowest stage skill. Instructions 1. Run the base-checkout resolver. 2. Read live support and DESIGN.md. 3. Use only current architecture facts in the answer. 4. Use the narrowest stage skill for execution. Resolve the checkout Treat this resolver as part of the skill contract: a hosted copy may run outside the base repository, so never assume the current checkout contains workflows/i4hworkflows. I4HWORKFLOWSREPOURL selects the clone source. When I4HWORKFLOWS is unset, derive the fallback directory from that URL; set I4HWORKFLOWS only to reuse or choose a specific destination. Never replace an existing checkout. Inspect before answering Read ./DESIGN.md for architecture and skills/i4h-workflow/references/repo-map.md for ownership. Discover current support instead of copying a static table: If discovery fails because setup is incomplete, report that limitation and route to i4h-workflow-setup. Explain the design Keep the summary precise: A Scene owns the simulated world, assets, embodiment, cameras, randomization, adapters, and reset hooks. A Task owns one reusable capability. It reads ctx.scene, writes ctx.act, and never advances the simulator. A Workflow selects one Scene, exposes run-mode-specific TaskGraph builders, and owns goal semantics. A run mode answers how that workflow should run; code and CLI use the shorter term mode. The Engine schedules graph nodes; the shared SimulationRunner alone resets, steps, renders, records, retries whole episodes, and prints run summaries. Online RL is a separate training lifecycle: its trainer owns vectorized stepping and returns a checkpoint to the normal policy Task and SimulationRunner validation path. Simulator-compatible exported RSL-RL actors may run as in-process Tasks; incompatible foundation-model policy stacks remain remote. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills NVIDIA/i4h-workflow