Agent skill

Commit And PR

by verl-project in verl-project/verl-omni

verl-omni commit message + PR conventions and the mandatory contribution policy.

Apache-2.0Auto-check passedDevelopment

Install Commit And PR

skills CLI
$ npx skills add verl-project/verl-omni --skill commit-and-pr -a claude-code

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

GitHub CLI
$ gh skill install verl-project/verl-omni commit-and-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/verl-project/verl-omni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/commit-and-pr .claude/skills/commit-and-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
commit-and-pr
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
490 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

verl-omni commit message + PR conventions and the mandatory contribution policy.

  • Works in 4 steps: Why this is not duplicating an existing… → Test commands run and their results. → A clear statement that AI assistance was… → …
  • Tasks that involve Commit messages
  • SKILL.md covers When to Use, Step 0: Contribution policy…, PR title format and Commit messages, plus 3 more sections
  • Calls gh, git and claude

What it does

Commit And PR is an agent skill from verl-project/verl-omni. verl-omni commit message + PR conventions and the mandatory contribution policy. MUST load before any git commit or PR creation -- enforces the [{modules}] {type}: {description} title format, commit trailers, duplicate-work checks, and AI-assistance disclosure.

Its SKILL.md is about 1.4k 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 Commit messages. It works with vLLM. The repository describes itself as: Multimodal RL training framework for diffusion & omni models. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Commit messages

Example prompts

  • “/commit-and-pr”

Requirements

  • Docker

Workflow steps

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

  1. Why this is not duplicating an existing PR (cite your Step 0 checks).
  2. Test commands run and their results.
  3. A clear statement that AI assistance was used.
  4. A note that a human submitter has reviewed every changed line — pure

What it can do on your machine

Read from SKILL.md and the folder at commit 6195598. 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
    • claude

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

  • Network

    No URLs in SKILL.md. Its commands use gh and 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

Commit And PR loads about 1.4k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 490 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
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 verl-project/verl-omni at commit 6195598, republished under its Apache-2.0 licence (© verl-project). 490 words, ~1,422 tokens.

Download SKILL.mdSave it as .claude/skills/commit-and-pr/SKILL.md (or your agent's skills folder).
name
commit-and-pr
description
verl-omni commit message + PR conventions and the mandatory contribution policy. MUST load before any git commit or PR creation -- enforces the [{modules}] {type}: {description} title format, commit trailers, duplicate-work checks, and AI-assistance disclosure.

Commit & PR Conventions

How to commit and open PRs in verl-project/verl-omni. Load this before any commit or PR. The rules here come from AGENTS.md / CLAUDE.md and are enforced by maintainers — breaching them can result in banning.

When to Use

  • Any git commit in this repo.
  • Any PR creation (including delegated/agent commits).
  • Whenever you infer a module/type label for a change.

Step 0: Contribution policy (fail-closed)

Before proposing a PR, run the duplicate-work checks:

bash
gh issue view <issue_number> --repo verl-project/verl-omni --comments
gh pr list --repo verl-project/verl-omni --state open --search "<issue_number> in:body"
gh pr list --repo verl-project/verl-omni --state open --search "<short area keywords>"
  • If an open PR already addresses it → do not open another.
  • If your approach differs materially → explain the difference in the issue.
  • No low-value busywork PRs (single typo, one style tweak, one mutable default). Mechanical cleanups are acceptable only bundled with substantive work.
  • If the work is duplicate/trivial → stop and report what's missing.

PR title format

[{modules}] {type}: {description}
  • modules (comma-separated if several). The gate is tests/special_sanity/check_pr_title.py, not AGENTS.md — it accepts the official AGENTS.md set (vllm_omni, diffusion, omni, rollout, trainer, reward, model, algo, fsdp, ray, worker, data, cfg, ckpt, doc, ci, tests, docker, misc) plus training_utils, single_controller, recipe, perf, env, tool. Prefer the official set; the extras are real (recipe for examples/ work, perf for perf changes). Anything outside the validator's list fails the check.
  • type: feat, fix, refactor, chore, test.
  • [BREAKING] if it breaks any API (CLI args, config, signatures) — placed immediately before the module bracket: [BREAKING][cfg] refactor: ..., not [cfg] [BREAKING] ... (the validator only strips a leading [BREAKING]).
  • For a stacked/multi-part PR series, prefix [N/N] (single digits only), e.g. [1/N][omni] feat: .... Combined with [BREAKING] the order is [N/N][BREAKING][module].
Module inference from changed paths
PathModule
verl_omni/pipelines/diffusion
verl_omni/pipelines/qwen3_omni/omni
verl_omni/trainer/trainer
verl_omni/trainer/config/, */config/cfg
verl_omni/utils/reward_score/, verl_omni/reward_loop/reward
verl_omni/workers/rollout/rollout
verl_omni/workers/worker
verl_omni/models/model
verl_omni/utils/vllm_omni/vllm_omni
docs/doc
tests/tests
.github/, CIci
docker/docker
Title examples
[reward] feat: add pickscore visual reward
[diffusion, cfg] feat: add teacher-anchored distillation losses for OPD
[omni] fix: correct attention mask for Qwen3-Omni text+image inputs
[tests] test: cover qwen-image DPO adapter guidance branching on CPU
[BREAKING][cfg] refactor: rename guidance_scale to cfg_scale

Real history to match style: [trainer, algo, cfg] feat: ..., [diffusion, cfg, tests] feat: ..., [1/N][omni] feat: ....

Show full SKILL.md (188 more words)Show less

Commit messages

Body explains why, not what. Wrap ~72 chars. For AI-assisted commits, add an explicit disclosure line in the body and attribution trailers (this is the actual repo convention — see recent history):

[reward] feat: add pickscore visual reward

Add a PickScore-based scorer routed via default_compute_score_image so
flow-GRPO runs can optimize human-preference reward.

AI assistance (<your tool name>) was used for this change.

Co-authored-by: <your tool name>
Signed-off-by: Your Name <your.email@example.com>

The Co-authored-by trailer names the assisting tool actually used — substitute your own tool name, do not copy Claude Code verbatim unless you are Claude Code. Signed-off-by with a real name/email is required.

PR description (AI-assisted work — mandatory)

The PR body must include:

  1. Why this is not duplicating an existing PR (cite your Step 0 checks).
  2. Test commands run and their results.
  3. A clear statement that AI assistance was used.
  4. A note that a human submitter has reviewed every changed line — pure code-agent PRs are not allowed.

Pre-commit

Ensure hooks pass before committing (pre-commit install once). If you touched config dataclasses, run scripts/generate_trainer_config.sh and commit the regenerated _generated_*.yaml (see config rule).

Common Mistakes

  • ❌ Title with a module not in check_pr_title.py, or an invalid type.
  • ❌ [BREAKING] after the module bracket ([cfg] [BREAKING]) instead of before it.
  • ❌ Opening a PR without the duplicate-work checks.
  • ❌ Omitting the AI-assistance disclosure or trailers.
  • ❌ Committing a stale _generated_*.yaml.

© verl-project, 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

Just SKILL.md in .agents/skills/commit-and-pr of verl-project/verl-omni.

Open the folder on GitHubat commit 6195598

Compare with similar skills

Commit And 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.

Commit And PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Commit And PR this skillverl-project/verl-omni1.2k—~1.4kAutomated safety check: PassApache-2.0
LLM Torch Profiler Analysissgl-project/sglang37k2 repos~6.4kAutomated safety check: PassApache-2.0
Debug Sessionai-dynamo/dynamo8.2k—~1.2kAutomated safety check: PassApache-2.0
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Caveman Commitvishiri/fantasia-archive40913 repos~642Automated safety check: PassGPL-3.0

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
  • Debug Session

    ai-dynamo/dynamo

    Sets up a structured debugging session for a Dynamo bug — pull the report from a Linear ticket, GitHub issue, or pasted text, capture the environment, create a persistent worklog markdown file, and…

    8.2k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Caveman Commit

    vishiri/fantasia-archive

    Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.

    409 GitHub starsUsed in 13 repos~642 tokens
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed

More from verl-project/verl-omni

  • Add Pipeline

    verl-project/verl-omni

    Router for adding a diffusion or omni pipeline to verl-omni.

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Add Reward Score

    verl-project/verl-omni

    Guide for adding a new reward scorer to verl-omni and wiring it into a run.

    1.2k GitHub stars~648 tokensUpdated today
    Auto-check passed
  • Profile

    verl-project/verl-omni

    Route a verl-omni performance investigation to the right tool and capture a usable trace.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Run Cpu Tests

    verl-project/verl-omni

    How to write and run verl-omni CPU tests (testoncpu.py) that exercise adapters, rewards, and configs without a GPU or model weights.

    1.2k GitHub stars~673 tokensUpdated today
    Auto-check passed
  • Self Review

    verl-project/verl-omni

    Review your own verl-omni branch against the project rubric before opening or updating a PR.

    1.2k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Train Infer Consistency

    verl-project/verl-omni

    Route verl-omni training/inference consistency checks through MindStudio's MSProbe collection and root-cause analysis skills.

    1.2k GitHub stars~860 tokensUpdated today
    Auto-check passed

Works with

Questions about Commit And PR

What does Commit And PR do?

verl-omni commit message + PR conventions and the mandatory contribution policy. Commit And PR is an agent skill from verl-project/verl-omni. verl-omni commit message + PR conventions and the mandatory contribution policy.

When should I use Commit And PR?

Commit And PR fits situations like: tasks that involve Commit messages.

How do I install Commit And PR in Claude Code?

Run `npx skills add verl-project/verl-omni --skill commit-and-pr -a claude-code`. Or copy the skill folder (.agents/skills/commit-and-pr in verl-project/verl-omni) into .claude/skills/commit-and-pr in your project. Claude Code loads it when a task matches its description.

How do I install Commit And PR in Codex?

Run `npx skills add verl-project/verl-omni --skill commit-and-pr -a codex`. Or copy the skill folder (.agents/skills/commit-and-pr in verl-project/verl-omni) into .agents/skills/commit-and-pr in your project. Codex loads it when a task matches its description.

Can I use Commit And 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 verl-project/verl-omni --skill commit-and-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/commit-and-pr, .gemini/skills/commit-and-pr, .github/skills/commit-and-pr and .opencode/skills/commit-and-pr in your project.

What does Commit And PR need to run?

Going by SKILL.md and its folder, Commit And PR needs the command-line tools its instructions call (gh, git and claude). Our summary lists: Docker.

Does Commit And PR access the network?

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

Is Commit And 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 Commit And PR use?

Commit And PR is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Commit And PR use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Commit And PR?

Skills that share tags, products or a category with Commit And PR: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Debug Session (ai-dynamo/dynamo, 8.2k stars), Contextual Commit Messages (yamadashy/repomix, 29k stars) and React Router Release Notes Prep (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Commit And PR?

verl-project (a GitHub organization) maintains it in verl-project/verl-omni, which has 1,196 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.

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