nvidia/maintain-optimizer
Maintain or extend the NeMo Relay adaptive surface across config, plugins, docs, and bindings; use this when users still say optimizer
npx skills add https://github.com/NVIDIA/NeMo-Relay --skill maintain-optimizer
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 changing adaptive config schema, built-in sections, shared
plugin lifecycle, plugin registration, or binding-native helper
APIs.
The stable adaptive boundary is the config document plus the shared plugin
lifecycle:
There is no separate public adaptive runtime handle.
See docs/plugins/adaptive/configuration.md and
docs/about/concepts/plugins.md.
crates/adaptivepython/nemo_relay/adaptive.py andpython/nemo_relay/plugin.py
go/nemo_relay/adaptive plus shared pluginhelpers in go/nemo_relay
docs/plugins/adaptive/configuration.mddocs/plugins/adaptive/about.mddocs/plugins/adaptive/acg.mddocs/plugins/adaptive/adaptive-hints.mddocs/build-plugins/basic-guide.mddocs/build-plugins/validate-configuration.mddocs/about/concepts/plugins.mdvalidate-changeTake nvidia/maintain-optimizer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.