Agent skill

Create PR

by openshift-eng in openshift-eng/ai-helpers

Push a completed clean feature branch and create a pull request for a Jira issue.

Apache-2.0Auto-check passedDevelopment

Install Create PR

skills CLI
$ npx skills add openshift-eng/ai-helpers --skill create-pr -a claude-code

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

GitHub CLI
$ gh skill install openshift-eng/ai-helpers create-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/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/openshift-developer/skills/create-pr .claude/skills/create-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
create-pr
GitHub stars
120
Token cost
~949 tokens
SKILL.md length
405 words
Files
1
Skills in repo
118
Repo updated
First seen
Licence
Apache-2.0

At a glance

Push a completed clean feature branch and create a pull request for a Jira issue.

  • Works in 4 steps: Gather context → Compose the PR → Create the PR → …
  • Implementation and required quality gates have succeeded and the branch is ready for delivery
  • SKILL.md covers Name, Synopsis, Description and Implementation, plus 4 more sections
  • Calls git and gh; reaches redhat.atlassian.net; needs ISSUE_KEY

What it does

Create PR is an agent skill from openshift-eng/ai-helpers. Push a completed clean feature branch and create a pull request for a Jira issue. Use when implementation and required quality gates have succeeded and the branch is ready for delivery.

Its SKILL.md is about 950 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 Pull requests and Quality gates. It works with Jira. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.

When your agent uses it

  • Implementation and required quality gates have succeeded and the branch is ready for delivery
  • Tasks that involve Pull requests
  • Tasks that involve Quality gates

Example prompts

  • “/create-pr”

Requirements

  • A credential in ISSUE_KEY

Workflow steps

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

  1. Gather context
  2. Compose the PR
  3. Create the PR
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit a627176. 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
    • gh

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • redhat.atlassian.net

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ISSUE_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create PR loads about 949 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 405 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~949

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 openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 405 words, ~949 tokens.

Download SKILL.mdSave it as .claude/skills/create-pr/SKILL.md (or your agent's skills folder).
name
create-pr
description
Push a completed clean feature branch and create a pull request for a Jira issue. Use when implementation and required quality gates have succeeded and the branch is ready for delivery.

Name

openshift-developer:create-pr

Synopsis

text
/openshift-developer:create-pr <ISSUE_KEY> [--upstream <owner/repo>] [--head <fork-owner>:<branch>]

Description

Creates a pull request from a completed feature branch and links it to a Jira issue. Reads the repo's PR template, inspects the commit log, and generates a well-structured PR title and body. It is the delivery building block selected by jira-solve after the chosen implementation and quality chain succeeds.

Implementation

Step 1: Gather context
  1. Parse arguments:

    • $1 — Jira issue key (required, e.g. OCPBUGS-1234)
    • --upstream — target repository (default: infer from gh repo view --json nameWithOwner)
    • --head — PR head ref in fork-owner:branch format (default: current branch)
  2. Determine the current branch:

    bash
    BRANCH=$(git branch --show-current)
  3. Discover remotes, then determine the base branch:

    bash
    REMOTE=$(git remote | head -1)
    BASE_BRANCH=$(git remote show "$REMOTE" | sed -n 's/.*HEAD branch: //p')

    Fall back to main if detection fails.

  4. Read the commit history for the PR:

    bash
    git log "${BASE_BRANCH}..HEAD" --format="%h %s%n%n%b" --reverse
  5. Read the PR template if it exists:

    bash
    cat .github/PULL_REQUEST_TEMPLATE.md 2>/dev/null || true
Step 2: Compose the PR
  1. Title: Must start with <ISSUE_KEY>: followed by a concise summary derived from the commits.

  2. Body: Structure using the PR template if one exists. Include:

    • A description of the changes based on the commit log
    • A link to the Jira issue: https://redhat.atlassian.net/browse/<ISSUE_KEY>
    • The following footer at the very end:
      text
      Always review AI generated responses prior to use.
      AI-assisted response via openshift-developer plugin
Show full SKILL.md (220 more words)Show less
Step 3: Create the PR

Before pushing, require git status --short to be empty. Refuse to push the default branch or to force-push. Push the current feature branch to the selected remote, unless the caller prohibits external writes. Do not create a PR when the branch was not pushed.

Build and run the gh pr create command:

bash
gh pr create \
  --repo <UPSTREAM> \
  --head <HEAD_REF> \
  --no-maintainer-edit \
  --title '<ISSUE_KEY>: <summary>' \
  --body '<body>'
  • If --upstream was provided, use it as --repo.
  • If --head was provided, use it directly.
  • If neither was provided, omit --repo and --head (defaults to current repo context and current branch).
Step 4: Report

Print the PR URL returned by gh pr create.

Return Value

  • PR URL: the URL of the newly created pull request

Examples

  1. Create a PR for a Jira issue (simple):

    text
    /openshift-developer:create-pr CNTRLPLANE-1234
  2. Create a PR targeting a specific upstream from a fork:

    text
    /openshift-developer:create-pr OCPBUGS-5678 --upstream openshift/hypershift --head hypershift-community:fix/OCPBUGS-5678

Arguments

  • $1 — Jira issue key (required)
  • --upstream — target repository in owner/repo format (optional)
  • --head — PR head ref in fork-owner:branch format (optional)

Guidelines

  • Discover remotes first (e.g. git remote or git branch -vv) before selecting one
  • Always include the Jira issue key prefix in the PR title
  • Always include the AI-generated footer at the end of the PR body
  • Use the repo's PR template when available
  • Derive the PR description from the actual commit log, not from assumptions

© openshift-eng, 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 plugins/openshift-developer/skills/create-pr of openshift-eng/ai-helpers.

Open the folder on GitHubat commit a627176

Compare with similar skills

Create 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.

Create PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create PR this skillopenshift-eng/ai-helpers120—~949Automated safety check: PassApache-2.0
PlotJuggler Ship CheckPlotJuggler/PlotJuggler6.2k—~1.3kAutomated safety check: PassMPL-2.0
Pull Requestnoh-rs/nohrs156—~4.1kAutomated safety check: PassMIT
Compound Engineering Code ReviewEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Sonarcloud Reviewlucasvieirasilva/nx-plugins153—~2.7kAutomated safety check: NotesMIT
PR Preflight Checkliaohch3/claude-tap3.3k—~615Automated safety check: PassMIT

Similar skills

  • PlotJuggler Ship Check

    PlotJuggler/PlotJuggler

    Runs a gated finish-line checklist before committing a PlotJuggler PJ4 change: build proof, red-test triage, hooks, docs freshness and a diff self-review.

    6.2k GitHub stars~1.3k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Pull Request

    noh-rs/nohrs

    Take a change from working tree to a merge-ready pull request, then keep iterating until the CI checks and AI reviewers (CodeRabbit, cubic) all pass.

    156 GitHub stars~4.1k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Compound Engineering Code Review

    EveryInc/compound-engineering-plugin

    Runs a staged pull request or diff review using selected reviewer personas, checking the change against its stated intent and project standards before producing findings.

    25k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Sonarcloud Review

    lucasvieirasilva/nx-plugins

    Fetches and triages SonarCloud findings (issues, security hotspots, quality gate) for the current pull request or branch of this repository via the SonarCloud Web API, summarizes them in a markdown…

    153 GitHub stars~2.7k tokensUpdated 9 days ago
    DevelopmentAuto-check: notes
  • PR Preflight Check

    liaohch3/claude-tap

    Runs a single merge-readiness check on a pull request: metadata, GitHub Actions status, local lint, format and test gates, and PR body rules, ending in READY or NOT_READY.

    3.3k GitHub stars~615 tokensUpdated 15 days ago
    DevelopmentAuto-check passed
  • Submit PR

    FutureTense/keymaster

    Procedure for preparing and submitting pull requests in keymaster, enforcing the required PR template (.github/PULLREQUESTTEMPLATE.md), checklist validation, and quality gates.

    349 GitHub stars~830 tokensUpdated today
    DevelopmentAuto-check passed

More from openshift-eng/ai-helpers

All 118 skills in this repo
  • Investigate CI Reliability

    openshift-eng/ai-helpers

    Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Address Review PR

    openshift-eng/ai-helpers

    Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.

    120 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Categorize Activity Types

    openshift-eng/ai-helpers

    Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.

    120 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Has Review Work

    openshift-eng/ai-helpers

    Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Must Gather Analyzer

    openshift-eng/ai-helpers

    Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.

    120 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Payload Autodl JSON

    openshift-eng/ai-helpers

    Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file

    120 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Create PR

What does Create PR do?

Push a completed clean feature branch and create a pull request for a Jira issue. Create PR is an agent skill from openshift-eng/ai-helpers. Push a completed clean feature branch and create a pull request for a Jira issue.

When should I use Create PR?

Create PR fits situations like: implementation and required quality gates have succeeded and the branch is ready for delivery; tasks that involve Pull requests; tasks that involve Quality gates.

How do I install Create PR in Claude Code?

Run `npx skills add openshift-eng/ai-helpers --skill create-pr -a claude-code`. Or copy the skill folder (plugins/openshift-developer/skills/create-pr in openshift-eng/ai-helpers) into .claude/skills/create-pr in your project. Claude Code loads it when a task matches its description.

How do I install Create PR in Codex?

Run `npx skills add openshift-eng/ai-helpers --skill create-pr -a codex`. Or copy the skill folder (plugins/openshift-developer/skills/create-pr in openshift-eng/ai-helpers) into .agents/skills/create-pr in your project. Codex loads it when a task matches its description.

Can I use Create 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 openshift-eng/ai-helpers --skill create-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/create-pr, .gemini/skills/create-pr, .github/skills/create-pr and .opencode/skills/create-pr in your project.

What does Create PR need to run?

Going by SKILL.md and its folder, Create PR needs the command-line tools its instructions call (git and gh) and credentials named ISSUE_KEY. Our summary lists: A credential in ISSUE_KEY.

Does Create PR access the network?

SKILL.md names 1 domain. In commands or code: redhat.atlassian.net; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Create 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 Create PR use?

Create 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 Create PR use?

About 949 tokens (SKILL.md is roughly 3.8k 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 Create PR?

Skills that share tags, products or a category with Create PR: PlotJuggler Ship Check (PlotJuggler/PlotJuggler, 6.2k stars), Pull Request (noh-rs/nohrs, 156 stars), Compound Engineering Code Review (EveryInc/compound-engineering-plugin, 25k stars) and Sonarcloud Review (lucasvieirasilva/nx-plugins, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create PR?

openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.

Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.