add-binding-feature

por nvidia

Add or change a public NeMo Relay API surface across the core runtime and every affected binding

npx skills add https://github.com/nvidia/nemo-relay --skill add-binding-feature

Add a Binding Feature

Companion Guidance

Use karpathy-guidelines alongside this skill for implementation or review work. Keep changes scoped, surface assumptions, and define focused validation before editing.

Use this skill when a change affects the public runtime surface and must stay in parity across the Rust core, FFI, and one or more bindings.

Do not use this skill for:

  • Internal-only core refactors with no public API change
  • Binding-local bug fixes that do not change shared behavior
  • Docs-only or example-only updates

Implementation Order

  1. Core Rust Implement the behavior first in crates/core/src/api/ and related core modules such as crates/core/src/api/runtime/, crates/core/src/codec/, or crates/core/src/json.rs.
  2. FFI / shared C surface Add or update FFI wrappers in the relevant crates/ffi/src/api/*.rs module, re-export them through crates/ffi/src/api/mod.rs, and ensure the generated crates/ffi/nemo_relay.h stays correct.
  3. Language-native bindings Update Python, Go, and Node.js for every surface that should expose the capability.
  4. Language wrapper helpers Update Python wrapper modules, Go shorthand packages, typed helpers, or adaptive/plugin helpers if the new behavior belongs there.
  5. Docs and examples Update reference docs, language-binding docs, and examples when the public surface or expected usage changed.
  6. Validation Run the validation matrix from the validate-change skill for the affected surfaces.

Naming Conventions

LayerConventionExample
Rustsnake_casenemo_relay_tool_call
C FFInemo_relay_ prefixnemo_relay_tool_call
Pythonsnake_casenemo_relay.tools.call
GoPascalCasenemo_relay.ToolCall
Node.jscamelCasetoolCall

Parity Checklist

  • Core function with doc comment in crates/core/src/api/
  • Runtime callback/state, codec, JSON, or event/tool/LLM/scope types added in the relevant core module if needed
  • FFI wrapper in the relevant crates/ffi/src/api/*.rs module and re-export in crates/ffi/src/api/mod.rs
  • Regenerate the shared library/header path with just build-go
  • Python native binding in crates/python/src/py_api/mod.rs
  • Python wrapper with docstring in python/nemo_relay/<module>.py
  • Python type stubs updated in the relevant python/nemo_relay/*.pyi modules
  • Go wrapper in go/nemo_relay/nemo_relay.go with doc comment
  • Go shorthand package updated if the capability belongs there
  • Node.js binding in crates/node/src/api/mod.rs
  • Typed wrapper or adaptive/plugin helper surfaces updated when applicable
  • Tests added in every affected language surface
  • SPDX license header on any new files
  • Relevant pages under docs/reference/ updated
  • README.md, docs/getting-started/, or binding-level READMEs updated if behavior differs by language
  • Relevant getting-started, README, or example docs updated if usage changed

Decision Points

Lock these before implementing:

  • Which bindings actually expose the new surface?
  • Is the change part of the plain JSON API, typed wrappers, adaptive/plugin helpers, or observability helpers?
  • Does the new API need manual lifecycle and managed execute variants, or only one of them?
  • Does the new behavior change event fields, metadata, or scope expectations?
  • Are docs/examples required because the intended usage changed?

Key References

  • Architecture: docs/about/architecture.md
  • Reference index: docs/reference/api/index.md
  • Getting started and binding status: README.md, docs/getting-started/quick-start.md, docs/about/release-notes/support-matrix.md
  • Typed wrappers and codecs: docs/integrate-frameworks/using-codecs.md, docs/integrate-frameworks/provider-codecs.md
  • Adaptive config/plugins: docs/about/concepts/plugins.md, docs/build-plugins/about.md, docs/plugins/adaptive/configuration.md
  • Existing pattern: follow a surface already implemented across core, FFI, Python, Go, and Node.js rather than inventing a new shape

Más skills de nvidia

compileiq-debug
nvidia
Úsalo cuando algo esté mal: Search() se cuelga, todas las evaluaciones devuelven INVALID_SCORE, las puntuaciones no mejoran, cada configuración devuelve el mismo número, errores de ptxas…
official
create-github-pr
nvidia
Crear solicitudes de extracción de GitHub usando la CLI gh. Usar cuando el usuario quiera crear un nuevo PR, enviar código para revisión o abrir una solicitud de extracción. Palabras clave de activación -…
official
diagnose-perf
nvidia
First-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and…
official
eagle3-review-logs
nvidia
Revisa los registros de experimentos del pipeline EAGLE3 desde el directorio experiments/ del lanzador. Resume el estado de aprobación/fallo para las 4 tareas, diagnostica fallos con la causa raíz…
official
nemoclaw-maintainer-cross-issue-sweep
nvidia
Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line…
official
karpathy-guidelines
nvidia
Pautas de comportamiento para reducir errores comunes de codificación en LLM. Úselas al escribir, revisar o refactorizar código para evitar la sobrecomplicación, realizar cambios quirúrgicos,…
official
fhir-basics
nvidia
Enseña a los agentes cómo funcionan las APIs de FHIR R4, qué recursos están disponibles, cómo consultarlos con parámetros de búsqueda y cómo analizar correctamente todos los formatos de respuesta…
official
underdeclared-agent
nvidia
A helpful assistant agent
official