simready-foundation-add-capability

par nvidia

Ajouter les documents de capacité SimReady, les index d'exigences, les stubs de validation et les enregistrements pour les nouvelles familles d'exigences.

npx skills add https://github.com/nvidia/simready-foundation --skill simready-foundation-add-capability

SimReady Add Capability

Purpose

Use this skill when a new requirement does not fit an existing capability. A capability groups related requirements and validators under its owning package in nv_core/tiers/.

After creating the capability, use simready-foundation-add-requirement for each requirement and simready-foundation-add-validator for executable checks.

Prerequisites

Before editing, read:

  • AGENTS.md
  • nv_core/sr_specs/docs/guides/guides.md
  • nv_core/sr_specs/docs/guides/naming_conventions.md
  • nv_core/sr_specs/docs/guides/features_expansion_workflow.md
  • existing neighboring capability folders
  • nv_core/sr_specs/docs/shared/capabilities/capabilities.md
  • the owning tier's capabilities/__init__.py

No network access, API key, or external service is required for the authoring pass.

Inputs

Collect or infer:

InputRequirement
capability_groupExisting top-level group such as physics_bodies, visualization, or a new group if justified.
owning_tierTier package that owns the capability, requirements, and validators.
capability_slugSnake_case folder name.
display_nameHuman-readable capability name.
scopeWhat requirement family belongs here.
requirement_prefixRequirement code prefix, if new.
initial_requirementsOptional first requirement docs to add.
validator_scopeWhether validation is objective, manual, runtime, or deferred.

Instructions

Use this checklist when changing the repository:

  1. Confirm no existing capability already covers the scope.
  2. Choose names using the naming guide:
    • group folder: snake_case
    • folder: snake_case
    • overview: capability-<folder_name>.md
    • requirement docs: kebab-case
  3. Create the capability folder in the appropriate group; if the group is new, add the group landing page too.
  4. Add capability-<slug>.md with purpose, scope, requirement table, related capabilities, and validation notes.
  5. Add requirements.md with {requirements-table} and a toctree for requirement docs.
  6. Add an empty or initial requirements/ folder content only for real requirements.
  7. Add validation.py with imports and placeholder structure only when validators are planned; otherwise document deferred validation in the capability overview.
  8. Update parent group toctrees, group landing pages, and the shared global capability hub when needed.
  9. Update the owning tier's capabilities/__init__.py when a new validation module must be registered. Keep the shared legacy aggregate import hub in sync until simready-foundation-core is retired.
  10. Validate consistency:
    • folder and overview names match
    • requirements index builds conceptually
    • validator registration path is documented
    • no duplicate requirement prefix or capability slug exists

Examples

Example request:

Add a SimReady capability for factory connection points, with requirement index registration and a validation plan.

Expected result summary:

capability_path: nv_core/tiers/<owning-tier>/simready/foundation/<tier-module>/capabilities/<group>/<capability_slug>
overview_doc: capability-<capability_slug>.md
requirements_index: requirements.md
validation_module: validation.py or deferred
next_step: add concrete requirements with simready-foundation-add-requirement

Policies

  • Prefer adding requirements to an existing capability when the domain already exists.
  • Do not create a capability as a thin wrapper for one feature unless the requirement family is truly distinct.
  • Keep capability docs about requirement families, not profile workflows.
  • Make validation status explicit; incomplete validators are acceptable only when called out.

Limitations

  • Do not create new feature or profile versions from this skill; hand off to the relevant add/update feature or profile skill.
  • Do not invent requirement IDs when the capability scope is still ambiguous; record the naming question instead.
  • Do not add executable validators unless the objective checks and registration path are clear.

Troubleshooting

  • Error: an existing capability already owns the scope. Solution: update that capability instead of creating a parallel one.
  • Error: the validator registration path is unclear. Solution: document deferred validation in the overview and list the exact follow-up.
  • Error: indexes and folder names disagree. Solution: re-check the naming guide, then align folder, overview, requirements index, and imports.

Resources

  • assets/openai.yaml preserves optional UI metadata for clients that read skill display hints. It is not required for the authoring workflow.

Summary Format

Report:

FieldMeaning
capability_pathNew capability folder.
overview_docCapability overview path.
requirements_indexRequirements index path.
validation_moduleValidator path or deferred.
initial_requirementsRequirement IDs added, if any.
indexes_changedGlobal/group index files changed.
next_stepAdd requirements, validators, features, or review.

Plus de skills de nvidia

fhir-basics
nvidia
Apprend aux agents comment fonctionnent les API FHIR R4, quelles ressources sont disponibles, comment les interroger avec des paramètres de recherche, et comment analyser correctement tous les formats de réponse…
compileiq-validate-result
nvidia
Utiliser APRÈS qu'une recherche soit terminée et AVANT de réclamer un accélérateur ou d'expédier un ACF. Charge le CSV dump_results, extrait les K meilleurs candidats (mono-objectif)…
changelog-audit
nvidia
Auditer le CHANGELOG.md de Warp avant une publication : récupérer les entrées perdues, trier par impact utilisateur, affiner le langage des entrées, ajuster les retours à la ligne et (en mode branche de publication) mettre à jour la comparaison…
dgx-diagnose
nvidia
Diagnostiquer les problèmes courants du DGX Station GB300 — plantages CUDA, ciblage incorrect du GPU, bugs de conteneur vLLM/SGLang, problèmes d'état MIG, erreurs NVLink/Fabric Manager,…
aicr-managing-openvex
nvidia
Use when adding, updating, or removing CVE/GHSA suppressions in `.openvex.json` — the OpenVEX document consumed by the daily image vulnerability scan workflow.…
aicr-creating-slide-decks
nvidia
À utiliser lors de la création d'un diaporama HTML autonome ou d'un support visuel pour un concept technique ou un flux de travail (par exemple un demos/*.html) — affiché en plein écran ou…
aicr-creating-guided-demos
nvidia
Génère un script de démonstration guidée interactive (demos/*.sh), en direct ou à son rythme, avec le modèle Frame → Tell → Show → Close. Se déclenche sur « script de démonstration », « guidé…
aicr-analyzing-snapshots
nvidia
À utiliser lors de l'analyse d'un fichier YAML de snapshot AICR, de l'examen de l'état du cluster, de la comparaison des caractéristiques des fournisseurs, de l'extraction d'informations sur la topologie GPU/réseau, ou…