Official agent skill

Prepare Code Freeze

Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR.

OfficialApache-2.0Auto-check passedDevelopment

Install Prepare Code Freeze

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .claude/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .claude/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .agents/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .agents/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .cursor/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .cursor/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/NVIDIA/NeMo-Relay.git --path .agents/skills/prepare-code-freeze

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .gemini/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .gemini/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .github/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .github/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install NVIDIA/NeMo-Relay prepare-code-freeze --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/prepare-code-freeze .opencode/skills/prepare-code-freeze && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "prepare-code-freeze" agent skill from https://github.com/NVIDIA/NeMo-Relay/tree/main/.agents/skills/prepare-code-freeze into .opencode/skills/prepare-code-freeze/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prepare-code-freeze", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: prepare-code-freeze
GitHub stars: 192
Token cost: ~895 tokens
SKILL.md length: 322 words
Files: 1
Skills in repo: 30
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR.

Works in 9 steps: Confirm or infer the target release… → Prompt for if the user did not provide… → Fetch the latest main and create the… → …
An ordinary version bump
SKILL.md covers Workflow and Guardrails
Calls git, cargo and just

What it does

Prepare Code Freeze is an agent skill from NVIDIA/NeMo-Relay, published by the product's own GitHub organization. Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR. Do not use for an ordinary version bump or release-note draft.

Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Changelog and release notes. It works with NVIDIA AI Platform. The repository describes itself as: Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls. The licence is Apache-2.0.

When your agent uses it

An ordinary version bump
Release-note draft

Example prompts

“/prepare-code-freeze”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

Confirm or infer the target release version from upstream/main:Cargo.toml.
Prompt for if the user did not provide it. This is the
Fetch the latest main and create the release branch from upstream/main
Create a PR branch from latest upstream/main, for example
Update .github/nightly-alpha-branches.yaml to include the new release
Run just set-version to update all project-owned
Search documentation source for references to the old version and update
Validate with targeted checks
After explicit approval to publish, open a PR targeting main using

What it can do on your machine

Read from SKILL.md and the folder at commit 16d73b4. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
- cargo
- just
- rg
- ruby
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prepare Code Freeze loads about 895 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~59
When it runs · the whole SKILL.md, loaded when a task matches: ~895

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/NeMo-Relay at commit 16d73b4, republished under its Apache-2.0 licence (© NVIDIA). 322 words, ~895 tokens.

Download SKILL.mdSave it as .claude/skills/prepare-code-freeze/SKILL.md (or your agent's skills folder).

name: prepare-code-freeze
description: Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR. Do not use for an ordinary version bump or release-note draft.
license: Apache-2.0

Prepare Code Freeze

Use this skill when the user asks to start, prepare, or automate a NeMo Relay code freeze.

Workflow

This workflow assumes upstream is the NVIDIA repository remote (NVIDIA/NeMo-Relay). The origin remote can be a maintainer's personal fork.

Confirm or infer the target release version from upstream/main:Cargo.toml. Derive the release branch as release/<major>.<minor>.
Prompt for <next-version> if the user did not provide it. This is the version that main moves to after the release branch is cut.
Fetch the latest main and create the release branch from upstream/main:
bash
```
git fetch upstream main
git branch release/<major>.<minor> upstream/main
git push upstream release/<major>.<minor>
```
If the remote release branch already exists, verify it points where expected before continuing.
Create a PR branch from latest upstream/main, for example chore/version-bump-<major>.<minor>.
Update .github/nightly-alpha-branches.yaml to include the new release branch.
Run just set-version <next-version> to update all project-owned unified-release version surfaces on main, including Cargo, Python, Node, plugins, lockfiles, and coding-agent manifests. Regenerate the dynamic worker-plugin fixture lockfile so its path dependencies use the new workspace version:
bash
```
cargo generate-lockfile --manifest-path crates/core/tests/fixtures/worker_plugin/Cargo.toml
```
Search documentation source for references to the old version and update current-version install commands, package examples, and configuration examples to <next-version> where appropriate:
bash
```
rg -n '<old-version>' README.md docs fern --glob '!docs/_build/**' || true
```
Review matches before changing them. Leave intentional historical references alone, such as release notes, changelogs, generated build output, and third-party dependency attribution entries.

Validate with targeted checks:

bash

ruby -e 'require "yaml"; YAML.load_file(".github/nightly-alpha-branches.yaml"); YAML.load_file(".github/workflows/nightly-alpha-tag.yaml")'
just set-version <next-version>
cargo generate-lockfile --manifest-path crates/core/tests/fixtures/worker_plugin/Cargo.toml
cargo build --locked --manifest-path crates/core/tests/fixtures/worker_plugin/Cargo.toml
rg -n '<old-version>' README.md docs fern --glob '!docs/_build/**' || true
git diff --check

Any remaining documentation matches for <old-version> should be intentional and called out in the PR description.

After explicit approval to publish, open a PR targeting main using .github/pull_request_template.md. The PR must mention:
- the new release branch
- the nightly alpha branch config update
- the just set-version <next-version> bump
- documentation old-version reference updates or intentional leftovers
- that subsequent release-bound PRs target the new release/* branch

Show full SKILL.md (41 more words)Show less

Guardrails

Do not create release tags. Code freeze only creates the branch and the main PR.
Do not target the code-freeze PR at the release branch. It targets main.
Do not leave uncommitted user changes mixed into the code-freeze PR branch.

Files

Just SKILL.md in .agents/skills/prepare-code-freeze of NVIDIA/NeMo-Relay.

Open the folder on GitHubat commit 16d73b4

Compare with similar skills

Prepare Code Freeze next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prepare Code Freeze compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Prepare Code Freeze this skillNVIDIA/NeMo-Relay	192	—	~895	Automated safety check: Pass	Apache-2.0	today
Nemoclaw Maintainer Release NotesNVIDIA/NemoClaw	23k	—	~2.1k	Automated safety check: Pass	Apache-2.0	today
Aicr Reviewing Component DriftNVIDIA/aicr	439	—	~2.8k	Automated safety check: Pass	Apache-2.0	today
LLM Torch Profiler Analysissgl-project/sglang	37k	2 repos	~6.4k	Automated safety check: Pass	Apache-2.0	today
Simple Englishmoeru-ai/airi	50k	2 repos	~4.6k	Automated safety check: Pass	MIT	today
StarRocks Release NotesStarRocks/starrocks	12k	—	~1.9k	Automated safety check: Notes	Apache-2.0	today

Similar skills

Nemoclaw Maintainer Release Notes
NVIDIA/NemoClaw
Official
Draft a post-tag NemoClaw Announcement from the verified release range and shipped PRs.
23k GitHub stars~2.1k tokensUpdated today
DevelopmentAuto-check passed
Aicr Reviewing Component Drift
NVIDIA/aicr
Official
A skill your agent uses when reviewing the weekly AICR component drift report — the Slack digest and drift-report.json artifact produced by Registry Drift Report (registry-drift.yaml) listing which…
439 GitHub stars~2.8k tokensUpdated today
DevOps & CloudAuto-check passed
LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
37k GitHub starsUsed in 2 repos~6.4k tokens
DevelopmentAuto-check passed
Simple English
moeru-ai/airi
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.
50k GitHub starsUsed in 2 repos~4.6k tokens
DevelopmentAuto-check passed
StarRocks Release Notes
StarRocks/starrocks
Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.
12k GitHub stars~1.9k tokensUpdated today
DevelopmentAuto-check: notes
Cutting A Release
TriliumNext/Trilium
A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.
38k GitHub stars~3.2k tokensUpdated today
DevelopmentAuto-check passed

More from NVIDIA/NeMo-Relay

All 30 skills in this repo

Draft Release Notes
NVIDIA/NeMo-Relay
Official
Compare NeMo Relay release refs and draft the current documentation release-notes page from verified repository evidence.
192 GitHub stars~575 tokensUpdated today
Auto-check passed
Nemo Relay Migrate From Flow
NVIDIA/NeMo-Relay
Official
A skill your agent uses when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python, Rust, Node.js, Go, C FFI, CLI…
192 GitHub stars~1.8k tokensUpdated today
Auto-check passed
Add Middleware
NVIDIA/NeMo-Relay
Official
Add a new NeMo Relay guardrail or intercept type, registration surface, or pipeline stage.
192 GitHub stars~1.2k tokensUpdated today
Auto-check passed
Contribute Docs
NVIDIA/NeMo-Relay
Official
Author or edit NeMo Relay documentation or examples when repository-specific MDX, public API, integration, or release-history conventions matter.
192 GitHub stars~710 tokensUpdated today
Auto-check passed
Maintain CI
NVIDIA/NeMo-Relay
Official
Change or review NeMo Relay GitHub Actions workflows where permissions, pinned actions, caching, reusable workflows, or release gates require repository-specific handling.
192 GitHub stars~1k tokensUpdated today
Auto-check passed
Nemo Relay Install
NVIDIA/NeMo-Relay
Official
A skill your agent uses when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, or maintained framework integrations, or when explaining Hermes Agent's…
192 GitHub stars~1.7k tokensUpdated today
Auto-check passed

Works with

NVIDIA AI Platform

Questions about Prepare Code Freeze

What does Prepare Code Freeze do?

Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR. Prepare Code Freeze is an agent skill from NVIDIA/NeMo-Relay, published by the product's own GitHub organization. Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR.

When should I use Prepare Code Freeze?

Prepare Code Freeze fits situations like: an ordinary version bump; release-note draft.

How do I install Prepare Code Freeze in Claude Code?

Run `npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a claude-code`. Or copy the skill folder (.agents/skills/prepare-code-freeze in NVIDIA/NeMo-Relay) into .claude/skills/prepare-code-freeze in your project. Claude Code loads it when a task matches its description.

How do I install Prepare Code Freeze in Codex?

Run `npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a codex`. Or copy the skill folder (.agents/skills/prepare-code-freeze in NVIDIA/NeMo-Relay) into .agents/skills/prepare-code-freeze in your project. Codex loads it when a task matches its description.

Can I use Prepare Code Freeze in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/NeMo-Relay --skill prepare-code-freeze -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prepare-code-freeze, .gemini/skills/prepare-code-freeze, .github/skills/prepare-code-freeze and .opencode/skills/prepare-code-freeze in your project.

What does Prepare Code Freeze need to run?

Going by SKILL.md and its folder, Prepare Code Freeze needs the command-line tools its instructions call (git, cargo, just, rg and ruby).

Does Prepare Code Freeze access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Prepare Code Freeze safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prepare Code Freeze use?

Prepare Code Freeze is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prepare Code Freeze use?

About 895 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prepare Code Freeze?

Skills that share tags, products or a category with Prepare Code Freeze: Nemoclaw Maintainer Release Notes (NVIDIA/NemoClaw, 23k stars), Aicr Reviewing Component Drift (NVIDIA/aicr, 439 stars), LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars) and Simple English (moeru-ai/airi, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prepare Code Freeze?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/NeMo-Relay, which has 192 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 8, 2026.

Source: NVIDIA/NeMo-Relay on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Prepare Code Freeze

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Prepare Code Freeze

Workflow

Guardrails

Files

Compare with similar skills

Similar skills

More from NVIDIA/NeMo-Relay

Related

Questions about Prepare Code Freeze