Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Split PR by CODEOWNERS Groups · nvidia | DecimalAI

code reviewby nvidia

Split PR by CODEOWNERS Groups

nvidia/mcore-split-pr

Source nvidia/skills ↗License Apache-2.0

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

SkillScore87Maintained

Automatic

Coding pack

Last verified 8/12/2026

What it changes

Passed 17 of 20 test cases with the skill, and 14 of 20 without it.

Without skill70%

With skill87%

Checks it passed that the model alone missed

The response lists answer-first constraints prior to outlining the split plan proposal.
The response requires user confirmation before force-pushing to narrow the original PR.
The response specifies selecting the largest CODEOWNERS file cluster as the primary PR.

and 3 more in the full report

5 fixed15 passed either way2 still failing1 broke

Pass-rate lift: +17 pp
Tokens: +14%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/12/2026v120 of 23 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/nvidia-mcore-split-pr/SKILL.md https://app.decimal.ai/s/nvidia-mcore-split-pr/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nvidia-mcore-split-pr, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/nvidia-mcore-split-pr/ and pins it in .decimal/skills.lock

decimalai skills add nvidia-mcore-split-pr

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nvidia-mcore-split-pr/SKILL.md https://app.decimal.ai/s/nvidia-mcore-split-pr/SKILL.md

Raw file: /s/nvidia-mcore-split-pr/SKILL.md ↗ · machine-readable summary at /s/nvidia-mcore-split-pr.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

If the original Megatron-LM PR needs to be narrowed in scope after creating the split draft PRs, can we immediately force-push the trimmed branch to upstream?

What was checked, without and with the skill
Checked	Without skill	With skill
The response requires user confirmation before force-pushing to narrow the original PR.	Missed	Passed

case-14 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md71 linessingle file

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.
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

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.
Parse .github/CODEOWNERS to build a mapping from file path patterns to owner groups.
For each changed file in the PR, determine which CODEOWNERS groups would be required to review it.
Build a summary table grouped by CODEOWNERS group, showing which files pull in which groups.
Count the total number of distinct reviewer groups the PR currently requires.

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:

Cluster files by their CODEOWNERS groups. Files owned by the same set of groups naturally belong together.

Track record

Benchmark

17 / 20

test cases passed, vs 14 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nvidia / skills

skills/mcore-split-pr/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Split PR by CODEOWNERS Groups

Answer-First Constraints

Workflow

1. Analyze the PR

2. Propose a split that minimizes reviewer groups per PR

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills