simready-foundation-add-profile

bởi nvidia

Sử dụng để thêm các phiên bản hồ sơ SimReady với các gói tính năng, tài liệu, chỉ mục và ghi chú xác thực.

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

SimReady Add Profile

Purpose

Use this skill to add a brand-new profile under nv_core/sr_specs/docs/profiles/. A profile is a named, versioned bundle of exact feature IDs and versions for a target asset class or runtime.

Do not use this skill for a new version of an existing profile. Use simready-foundation-update-profile for that.

Prerequisites

Before editing, read:

  • AGENTS.md
  • nv_core/sr_specs/docs/guides/guides.md
  • nv_core/sr_specs/docs/guides/profiles/profiles.md
  • nv_core/sr_specs/docs/guides/feature_adapters/feature_adapters.md
  • nv_core/sr_specs/docs/profiles/ (per-profile TOML files, one per profile)
  • nv_core/sr_specs/docs/profiles/profiles.md
  • nearby profile markdown files for the same asset class or runtime
  • nv_core/sr_specs/docs/features/feature-dependency-graph.md

Inputs

Collect or infer:

InputRequirement
profile_nameNew profile name, such as Prop-Robotics-Neutral. Use title-case words separated by hyphens.
profile_versionInitial version, usually 1.0.0 unless the user states otherwise.
target_asset_classProp, robot body, scene, material library, or another concrete class.
target_runtimeNeutral OpenUSD, PhysX, Isaac, or another runtime target.
feature_bundleExact feature IDs and versions.
profile_markdown_nameMarkdown file path under docs/profiles/.
adapter_planRequired adapters from related profiles, or none.
validation_strategyExample assets, validator command, runtime test, or documented gap.

Instructions

Use this checklist when changing the repository:

  1. Confirm the profile name is new across the per-profile TOML files in profiles/.
  2. Choose a feature bundle from exact existing feature JSON manifests. Do not reference a feature version that does not exist.
  3. Check feature dependencies. Avoid duplicating dependencies unless existing profiles do so intentionally for clarity.
  4. Create a new per-profile TOML file under profiles/ (e.g. profiles/<profile_name>.toml) containing a [Profile-Name] table with the initial version and ordered feature list.
  5. Create a profile markdown page under nv_core/sr_specs/docs/profiles/:
    • purpose and target asset class
    • target runtime/environment
    • exact feature list and versions
    • authoring requirements and known conditional features
    • validation and runtime-test guidance
    • references to feature docs and related profiles
  6. Update nv_core/sr_specs/docs/profiles/profiles.md with the new profile row and toctree entry if the index uses one.
  7. Add feature adapter notes when this profile is expected to be an upgrade or conversion target from another profile.
  8. When the new profile differs from an existing related profile, identify every feature difference and whether a direct adapter path exists or is intentionally blocked.
  9. When validation tooling is available, run workspace validate or the equivalent simready-validate command against a representative asset.
  10. Validate consistency:
  • TOML parses
  • every referenced feature ID/version exists in docs/features/*.json
  • profile markdown and the profile's TOML feature lists agree
  • profiles.md includes the new profile

Examples

Example request:

Create a new prop-factory-neutral SimReady profile similar to prop-robotics-neutral.

Expected result summary:

changed_files: new docs, manifests, indexes, or validation scaffolding
validation: focused static checks and any relevant docs/build checks
remaining_gaps: requirement, validator, adapter, profile, or runtime-test follow-up

Policies

  • The per-profile TOML files in profiles/ are the machine-readable source of truth.
  • Keep the initial feature bundle focused. Do not add features that are merely nice to have.
  • A feature may be conditionally applicable only when the profile docs and validator behavior make that condition clear.
  • If new features are needed, create them with simready-foundation-add-feature before referencing them.
  • If the new profile supersedes or branches from another profile, document migration/adapters instead of rewriting the old profile.

Limitations

  • Do not mutate published feature or profile versions in place.
  • Do not invent requirement IDs or validator behavior when the contract is ambiguous; record the question.
  • Do not skip index, manifest, validation, or downstream follow-up notes.

Troubleshooting

  • Error: the new concept overlaps an existing artifact. Solution: update the existing capability, requirement, feature, profile, or adapter instead.
  • Error: names or IDs conflict. Solution: re-check naming conventions and nearby indexes before editing further.
  • Error: validation strategy is unclear. Solution: document deferred validation and the exact follow-up skill.

Resources

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

Summary Format

Report:

FieldMeaning
profile_nameNew profile.
profile_versionInitial version.
profiles_tomlTOML path changed.
profile_markdownProfile docs path.
featuresExact feature IDs and versions.
adaptersAdapter plan or none.
validationChecks run and remaining gaps.
next_stepFeature creation, adapter work, runtime test, or review.

Thêm skills từ nvidia

compileiq-debug
nvidia
Sử dụng khi có điều gì đó không ổn: Search() bị treo, tất cả các đánh giá đều trả về INVALID_SCORE, điểm số không cải thiện, mọi cấu hình đều trả về cùng một số, lỗi ptxas…
create-github-pr
nvidia
Tạo pull request GitHub bằng cách sử dụng gh CLI. Sử dụng khi người dùng muốn tạo PR mới, gửi mã để xem xét, hoặc mở pull request. Từ khóa kích hoạt -…
nemoclaw-maintainer-cross-issue-sweep
nvidia
Quét các vấn đề đang mở khác để tìm những vấn đề mà một PR nhất định có thể sửa hoặc vô tình làm hỏng. Đưa ra các cơ hội sửa lỗi liền kề và rủi ro mâu thuẫn với file:dòng…
fhir-basics
nvidia
Dạy các tác nhân cách hoạt động của API FHIR R4, những tài nguyên có sẵn, cách truy vấn chúng với tham số tìm kiếm, và cách phân tích chính xác tất cả các định dạng phản hồi…
compileiq-validate-result
nvidia
Sử dụng SAU KHI tìm kiếm hoàn tất và TRƯỚC KHI yêu cầu tăng tốc hoặc gửi ACF. Tải tệp CSV dump_results, trích xuất các ứng viên top-K (đơn mục tiêu)…
changelog-audit
nvidia
Kiểm tra Warp CHANGELOG.md trước khi phát hành: khôi phục các mục bị mất, sắp xếp theo tác động người dùng, tinh chỉnh ngôn ngữ mục, xuống dòng và (chế độ nhánh phát hành) so sánh bump…
maintain-dynamic-plugins
nvidia
Duy trì các bộ nạp plugin động NeMo Relay, tệp kê khai, SDK gốc Rust, giao thức worker gRPC, SDK worker Python, tài liệu, kiểm thử và phạm vi quy trình phát hành
dgx-diagnose
nvidia
Chẩn đoán các sự cố thường gặp của DGX Station GB300 — lỗi CUDA, nhắm sai GPU, lỗi container vLLM/SGLang, vấn đề trạng thái MIG, lỗi NVLink/Fabric Manager,…