New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Mcore Split PR

by NVIDIA in NVIDIA/Megatron-LM

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

OfficialApache-2.0Auto-check passedDevelopment

Install Mcore Split PR

skills CLI
$ npx skills add NVIDIA/Megatron-LM --skill mcore-split-pr -a claude-code

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

GitHub CLI
$ gh skill install NVIDIA/Megatron-LM mcore-split-pr --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/Megatron-LM.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcore-split-pr .claude/skills/mcore-split-pr && 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/

Facts

Skill name
mcore-split-pr
GitHub stars
18k
Token cost
~1.4k tokens
SKILL.md length
782 words
Files
5
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

  • Works in 3 steps: Analyze the PR → Propose a split that minimizes reviewer… → Execute the split (after user approval)
  • Development work in your project
  • SKILL.md covers Answer-First Constraints, Workflow and Important guidelines
  • Calls gh and git

What it does

Mcore Split PR is an agent skill from NVIDIA/Megatron-LM, published by the product's own GitHub organization. Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `BENCHMARK.md`, `evals/evals.json` and `skill-card.md`).

It sits in Development. It works with NVIDIA AI Platform. The repository describes itself as: Ongoing research training transformer models at scale. The licence is Apache-2.0.

When your agent uses it

  • Development work in your project

Example prompts

  • “/mcore-split-pr”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Analyze the PR
  2. Propose a split that minimizes reviewer groups per PR
  3. Execute the split (after user approval)

What it can do on your machine

Read from SKILL.md and the folder at commit 486a126. 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:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.github.com

    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

Mcore Split PR loads about 1.4k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 782 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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/Megatron-LM at commit 486a126, republished under its Apache-2.0 licence (© NVIDIA). 782 words, ~1,395 tokens.

Download SKILL.mdSave it as .claude/skills/mcore-split-pr/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
mcore-split-pr
description
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
license
Apache-2.0
when_to_use
User asks to split a PR, reduce reviewer groups, or break up a large PR; 'too many CODEOWNERS', 'split this PR', 'break up PR', 'reduce reviewers needed'.
user_invocable
true
argument
PR URL or number
metadata.author
Philip Petrakian <ppetrakian@nvidia.com>

Split PR by CODEOWNERS Groups

Split a large pull request into multiple smaller PRs, where each PR touches the fewest possible CODEOWNERS reviewer groups. The goal is to reduce review burden: a PR that only touches megatron/core/ needs only the core reviewers, while a PR that also touches examples/, tools/, and megatron/training/ pulls in many additional groups.

Answer-First Constraints

For split-planning questions, lead with these constraints before the full workflow:

  • Minimize CODEOWNERS reviewer groups per PR, but each resulting PR must still be independently mergeable and reviewable.
  • Tests travel with the production code they validate; do not split tests into a separate PR just to reduce reviewer groups.
  • If PR B depends on symbols renamed in PR A, call out the dependency and put backward-compatible aliases, re-exports, or shims in PR A when needed.
  • GitHub's standard stacked-PR flow — push each branch to the upstream repo and base each PR on the previous branch — does not work here: contributors cannot push branches to NVIDIA/Megatron-LM, and a PR's base must be an upstream branch. The only upstream refs containing a fork PR's commits are the pull-request/<N> mirrors that copy-pr-bot creates, so stacking goes through them.
  • Create every PR with base main; the pull-request/<N> mirror refs do not exist until a vetter comments /ok to test <head-sha> (copy-pr-bot). Once the mirror exists, stack a dependent PR with gh pr edit <child> --base pull-request/<base PR number>.
  • Never merge a PR while its base is a pull-request/* ref: the squash lands in the bot's scratch ref, not main, and the PR ends up MERGED and unreopenable. Retarget to main first.
  • Wait for user approval before execution.
  • Execution creates draft PRs from the right base, applies file-scoped diffs with git diff upstream/main..<source-branch> -- <paths> | git apply, pushes to the user's fork, and never pushes directly to upstream.

Workflow

1. Analyze the PR
  1. Fetch the PR details: gh pr view <number> --repo NVIDIA/Megatron-LM --json title,body,headRefName,author and gh pr diff <number> --repo NVIDIA/Megatron-LM --stat. Also determine the current GitHub user with gh api user --jq .login.
  2. Parse .github/CODEOWNERS to build a mapping from file path patterns to owner groups.
  3. For each changed file in the PR, determine which CODEOWNERS groups would be required to review it.
  4. Build a summary table grouped by CODEOWNERS group, showing which files pull in which groups.
  5. Count the total number of distinct reviewer groups the PR currently requires.
Show full SKILL.md (383 more words)Show less
2. Propose a split that minimizes reviewer groups per PR

The primary optimization goal: minimize the number of CODEOWNERS reviewer groups required for each resulting PR.

Strategy:

  1. Cluster files by their CODEOWNERS groups. Files owned by the same set of groups naturally belong together.
  2. Identify the largest cluster — this becomes the first (and usually largest) PR.
  3. Remaining files form one or more additional PRs, each ideally requiring only one or two reviewer groups.
  4. If a split creates a dependency (e.g., PR B uses symbols renamed in PR A), the dependent PR must be merged after the first. Note this explicitly.
  5. Each PR must be independently mergeable to main — no broken imports, no missing symbols. Backward-compatible aliases and re-export stubs in the first PR can make this possible.

Present the proposed split as a table:

  • PR name/description
  • Files included
  • CODEOWNERS groups required
  • Dependencies on other PRs (if any)

Wait for user approval before proceeding.

3. Execute the split (after user approval)

For each new PR:

  1. Create a new branch from the appropriate local base (main, or a dependency PR's branch).
  2. Extract the relevant changes: git diff upstream/main..<source-branch> -- <file paths> | git apply.
  3. Stage, commit with a clear message, and push to the user's fork.
  4. Create the PR as a draft with base main (per repo contributing guidelines). Retarget dependent PRs to pull-request/<base PR number> only after a vetter's /ok to test has created that mirror ref.
  5. If the original PR needs to be narrowed in scope, confirm with the user before force-pushing.
  6. Report all PR URLs when done.

Important guidelines

  • Always create PRs as drafts and push to the user's fork, never directly to upstream.
  • Backward-compatible changes (aliases, re-exports, deprecation shims) should go in the first PR so subsequent PRs can depend on them.
  • Test files should go with the production code they test, not in a separate PR.
  • Prefer a single clean commit per split PR over replaying the original commit history.
  • If a file is hard to categorize (e.g., it touches two groups), ask the user which PR it should go in.
  • If the current GitHub user is not the author of the original PR, each new PR's description must explicitly credit the original author (e.g., "Original changes by @<author> in #<number>").

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/mcore-split-pr of NVIDIA/Megatron-LM.

  • SKILL.md
  • BENCHMARK.md
  • evals/evals.json
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 486a126

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in NVIDIA/Megatron-LM, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Mcore Split PR 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.

Mcore Split PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mcore Split PR this skillNVIDIA/Megatron-LM18k—~1.4kAutomated safety check: PassApache-2.0
LLM Torch Profiler Analysissgl-project/sglang37k2 repos~6.4kAutomated safety check: PassApache-2.0
Nemoclaw Contributor Update DependenciesNVIDIA/NemoClaw23k—~1.4kAutomated safety check: PassApache-2.0
Doc ReviewerNVlabs/alpasim1.3k—~1.2kAutomated safety check: PassApache-2.0
Refactor OpCVCUDA/CV-CUDA2.7k—~1.5kAutomated safety check: PassCustom licence
Nemoclaw Maintainer Analyze PR Value StreamNVIDIA/NemoClaw23k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • 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

  • Nemoclaw Contributor Update Dependencies

    NVIDIA/NemoClaw

    Official

    Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images.

    23k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Doc Reviewer

    NVlabs/alpasim

    Reviews recent code changes and checks if documentation needs updates.

    1.3k GitHub stars~1.2k tokensUpdated 19 days ago
    DevelopmentAuto-check passed

  • Refactor Op

    CVCUDA/CV-CUDA

    Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).

    2.7k GitHub stars~1.5k tokensUpdated 20 days ago
    DevelopmentAuto-check passed

  • Nemoclaw Maintainer Analyze PR Value Stream

    NVIDIA/NemoClaw

    Official

    Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.

    23k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

  • HSB IP Def File Tool

    NVIDIA/skills

    Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.5k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed

More from NVIDIA/Megatron-LM

All 14 skills in this repo

  • Update Megatron Golden Values

    NVIDIA/Megatron-LM

    Official

    Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description.

    18k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Megatron-LM Container and Dependency Setup

    NVIDIA/Megatron-LM

    Official

    Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI.

    18k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Megatron-LM Base Image Bump

    NVIDIA/Megatron-LM

    Official

    Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.

    18k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Megatron-LM CI/CD Guide

    NVIDIA/Megatron-LM

    Official

    Explains Megatron-LM's CI pipeline, PR scope labels, triggering the internal GitLab CI with a dry run first, and investigating CI failures.

    18k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Megatron-LM CI Failure Triage

    NVIDIA/Megatron-LM

    Official

    Investigates a failing GitHub Actions run or job for Megatron-LM, finds the root cause plus the PR and test author involved, and files a structured bug issue.

    18k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Megatron GPT to Hybrid Migration

    NVIDIA/Megatron-LM

    Official

    Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

    18k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Mcore Split PR

What does Mcore Split PR do?

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups. Mcore Split PR is an agent skill from NVIDIA/Megatron-LM, published by the product's own GitHub organization. Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

When should I use Mcore Split PR?

Mcore Split PR fits situations like: development work in your project.

How do I install Mcore Split PR in Claude Code?

Run `npx skills add NVIDIA/Megatron-LM --skill mcore-split-pr -a claude-code`. Or copy the skill folder (skills/mcore-split-pr in NVIDIA/Megatron-LM) into .claude/skills/mcore-split-pr in your project. Claude Code loads it when a task matches its description.

How do I install Mcore Split PR in Codex?

Run `npx skills add NVIDIA/Megatron-LM --skill mcore-split-pr -a codex`. Or copy the skill folder (skills/mcore-split-pr in NVIDIA/Megatron-LM) into .agents/skills/mcore-split-pr in your project. Codex loads it when a task matches its description.

Can I use Mcore Split PR 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/Megatron-LM --skill mcore-split-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcore-split-pr, .gemini/skills/mcore-split-pr, .github/skills/mcore-split-pr and .opencode/skills/mcore-split-pr in your project.

What does Mcore Split PR need to run?

Going by SKILL.md and its folder, Mcore Split PR needs the command-line tools its instructions call (gh and git).

Does Mcore Split PR access the network?

SKILL.md names 1 domain. As links in the text: docs.github.com. This is read from the text; nothing was executed.

Is Mcore Split PR 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 Mcore Split PR use?

Mcore Split PR 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 Mcore Split PR use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Mcore Split PR?

Skills that share tags, products or a category with Mcore Split PR: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Nemoclaw Contributor Update Dependencies (NVIDIA/NemoClaw, 23k stars), Doc Reviewer (NVlabs/alpasim, 1.3k stars) and Refactor Op (CVCUDA/CV-CUDA, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mcore Split PR?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/Megatron-LM, which has 18,078 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

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