feat: add repo-root skills for NVSkills catalog

AGENTS.md

@@ -94,7 +94,7 @@ Both `HEAD~n` and `git rebase -i HEAD~n` are safe because they only operate on c
 
 ## Setting up the local platform
 
-Before doing anything that requires a running NeMo platform (`nemo services`, `nemo agents invoke`, etc.), follow [SETUP.md](SETUP.md). It covers `make bootstrap`, the data-dir layout, DB reset, and the manual `nemo services run` path. The same content is symlinked into `.agents/skills/nemo-setup/SKILL.md` so coding agents pick it up automatically — you do not need to install it via `nemo skills install`.
+Before doing anything that requires a running NeMo platform (`nemo services`, `nemo agents invoke`, etc.), follow [skills/nemo-setup/SKILL.md](skills/nemo-setup/SKILL.md). It covers `make bootstrap`, the data-dir layout, DB reset, and the manual `nemo services run` path. You do not need to install it via `nemo skills install`.
 
 ## NeMo CLI
 

README.md

@@ -29,7 +29,7 @@ nemo setup
 
 `nemo setup` starts local services, registers your LLM provider, discovers available models, installs agent skills, and deploys a sample agent (see more below).
 
-See **[SETUP.md](SETUP.md)** for the full setup playbook (local data dir, DB reset, manual service start, troubleshooting). Coding agents pick the same playbook up automatically via `.agents/skills/nemo-setup/SKILL.md`.
+See **[skills/nemo-setup/SKILL.md](skills/nemo-setup/SKILL.md)** for the full setup playbook (local data dir, DB reset, manual service start, troubleshooting).
 
 Verify:
 

packages/nemo_platform_ext/src/nemo_platform_ext/skills/inference/SKILL.md

@@ -11,7 +11,7 @@ description: >
   OpenAI/Anthropic cross-format setups), making inference calls through IGW,
   or debugging routing and translation failures locally. For platform startup,
   Switchyard install, and DB-reset prerequisites, see the `nemo-setup` skill
-  (repo-level `SETUP.md`, mirrored at `.agents/skills/nemo-setup/SKILL.md`).
+  (`skills/nemo-setup/SKILL.md`).
 user-invocable: true
 allowed-tools: Bash, Read, Grep
 ---
@@ -23,7 +23,7 @@ allowed-tools: Bash, Read, Grep
 This skill assumes the platform is already running and any required plugins
 (`nemo-switchyard`, `nemo-guardrails`) are loaded. For local-platform startup,
 Switchyard install, and DB-reset choices, follow the **`nemo-setup` skill**
-(`SETUP.md` at the repo root, also at `.agents/skills/nemo-setup/SKILL.md`)
+(`skills/nemo-setup/SKILL.md`)
 first and then return here.
 
 ## API key environment variables
@@ -66,7 +66,7 @@ printf '%s' "$INFERENCE_NVIDIA_API_KEY" | nemo secrets create nvidia-inference-k
 - Workspace: `my-workspace` (substitute as needed; `default` also works)
 - Backend: `https://inference-api.nvidia.com/v1`
 
-For platform startup (`nemo services run`), Switchyard install, and state reset, see the `nemo-setup` skill (`SETUP.md` at the repo root).
+For platform startup (`nemo services run`), Switchyard install, and state reset, see the `nemo-setup` skill (`skills/nemo-setup/SKILL.md`).
 
 ---
 

packages/nemo_platform_ext/src/nemo_platform_ext/skills/nemo-teardown/SKILL.md

@@ -121,7 +121,7 @@ case "$DATA_DIR" in
 esac
 # Verify the platform is fully down BEFORE wiping; otherwise the running process keeps
 # its file descriptors open against the old inode (the "macOS unlinked-inode gotcha"
-# in SETUP.md) and the next run sees ghost state.
+# in skills/nemo-setup/SKILL.md) and the next run sees ghost state.
 lsof -iTCP:8080 -sTCP:LISTEN >/dev/null 2>&1 && { echo "PLATFORM_STILL_RUNNING — abort before wipe"; exit 1; }
 rm -rf "$DATA_DIR"
 ```

plugins/nemo-auditor/README.md

@@ -11,7 +11,7 @@ Before running the `nemo auditor configs create` and `nemo auditor targets
 create` commands below, make sure you have:
 
 - **NeMo CLI installed and platform running** — follow
-  [SETUP.md](../../SETUP.md) (`make bootstrap` + `nemo setup`).
+  [skills/nemo-setup/SKILL.md](../../skills/nemo-setup/SKILL.md) (`make bootstrap` + `nemo setup`).
 - **CLI pointed at the platform** — `nemo setup` configures
   `http://localhost:8080` automatically; otherwise set it explicitly with
   `nemo config set --base-url <url>`.

plugins/nemo-data-designer/src/nemo_data_designer_plugin/skills/data-designer

@@ -0,0 +1 @@
+../../../../../skills/nemo-data-designer-plugin

plugins/nemo-evaluator/src/nemo_evaluator/skills/evaluator-plugin

@@ -0,0 +1 @@
+../../../../../skills/nemo-evaluator-plugin

plugins/nemo-evaluator/src/nemo_evaluator/skills/evaluator-plugin/resources/api-auth.md → skills/nemo-evaluator-plugin/resources/api-auth.md

@@ -8,6 +8,6 @@ Use the correct `model.api_key_secret` (if `model` is used) for the evaluator ex
 The remote job runtime cannot read local environment variables. In remote mode, if a model sets `api_key_secret`, create or verify the platform secret before submitting the job:
 
 ```bash
-nemo secrets create nvidia-api-key --value "$NVIDIA_API_KEY"
+printf '%s' "$NVIDIA_API_KEY" | nemo secrets create nvidia-api-key --from-file -
 nemo secrets list
 ```

SETUP.md → skills/nemo-setup/SKILL.md

@@ -8,7 +8,7 @@ version: "0.1"
 
 Get a local NeMo platform running on `localhost:8080`. Work through the prereq questions below before bootstrapping — they shape which services start and what state survives the run. When setup is finished, [What's next?](#whats-next) maps the user's stated goal to the right follow-up skill.
 
-> This document is the canonical setup guide. It lives at the repository root as `SETUP.md` and is symlinked into `.agents/skills/nemo-setup/SKILL.md` so coding agents (Claude Code, Cursor, Codex, OpenCode) load the same content. Unlike the other skills, it is **not** installed by `nemo skills install` — it has to be available before the platform is bootstrapped, when the CLI may not yet exist.
+> This document is the canonical setup guide at `skills/nemo-setup/SKILL.md`. Unlike the other skills, it is **not** installed by `nemo skills install` — it has to be available before the platform is bootstrapped, when the CLI may not yet exist.
 
 ## Question 1 — Is a NeMo platform already running locally?
 
@@ -177,7 +177,7 @@ CLI built-ins (always present):
 
 - **`inference`** — ModelProvider + VirtualModel + Switchyard reference. End-to-end inference flow, routing patterns, middleware ordering, troubleshooting.
 
-> Setup itself (this document) lives at the repo root as `SETUP.md` rather than as a CLI-installable skill, since coding agents need it before the platform is bootstrapped. After `make bootstrap`, agents pick it up via `.agents/skills/nemo-setup/SKILL.md` (a symlink to `SETUP.md`).
+> Setup lives at `skills/nemo-setup/SKILL.md` rather than as a CLI-installable skill, since coding agents need it before the platform is bootstrapped.
 
 Plugin-provided (appear once the plugin is installed):