메뉴
Create a pull request (or merge request) with Conventional Commits formatting. Works with GitHub, GitLab, and Azure DevOps. Use when the user asks to create a PR or merge request.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | pr |
| description | Create a pull request (or merge request) with Conventional Commits formatting. Works with GitHub, GitLab, and Azure DevOps. Use when the user asks to create a PR or merge request. |
| argument-hint | ["base-branch"] |
| disable-model-invocation | true |
Create a pull request (or merge request) with Conventional Commits formatting. Works with GitHub, GitLab, and Azure DevOps.
/pr [base-branch]
base-branch (optional): Target branch for the PR/MR. Defaults to main (trunk-based workflow).When invoked, the command will:
Detect platform - Run git remote -v and identify:
github.com -> GitHub (use gh pr create)gitlab.com or gitlab.* -> GitLab (use glab mr create)dev.azure.com or *.visualstudio.com -> Azure DevOps (use az repos pr create)Analyze commits - Run git log to see all commits on current branch vs base
Determine PR type - Based on commits, select appropriate type:
feat: New feature or capabilityfix: Bug fixdocs: Documentation onlychore: Maintenance, dependencies, configsrefactor: Code change without behavior changetest: Adding/fixing testsci: CI/CD changesperf: Performance improvementstyle: Formatting, no code changeGenerate title - Format: <type>: <concise description>
Generate body - Include:
## Summary - 2-4 bullet points of what changed## Changes - Organized by category with file paths## Test Plan - Checklist of verification stepsCreate PR/MR - Use the appropriate CLI based on detected platform
Fallback - If CLI not available, output the title and body for manual copy/paste
| URL Pattern | Platform | CLI Tool |
|---|---|---|
github.com | GitHub | gh |
gitlab.com or gitlab.* | GitLab | glab |
dev.azure.com | Azure DevOps | az repos |
*.visualstudio.com | Azure DevOps | az repos |
| Platform | Create Command |
|---|---|
| GitHub | gh pr create --base <target> --title "<title>" --body "<body>" |
| GitLab | glab mr create --target-branch <target> --title "<title>" --description "<body>" |
| Azure DevOps | az repos pr create --target-branch <target> --title "<title>" --description "<body>" |
/pr
/pr main
/pr develop
/pr master
If the platform CLI is not installed, output for manual copy/paste:
PR READY FOR MANUAL CREATION
Platform: [GitHub/GitLab/Azure DevOps]
Target branch: [base-branch]
Source branch: [current-branch]
TITLE: <type>: <description>
BODY:
## Summary
...
## Changes
...
## Test Plan
...
CREATE AT: [URL to create PR/MR on the platform]
main branch (trunk-based / GitHub Flow)develop branch, the pr-manager agent will auto-detect and target accordinglypr-writing skill for formatting conventionsSQL engineering standards for writing correct, safe, cross-dialect SQL across PostgreSQL, MySQL, SQL Server, SQLite, DuckDB, and Oracle. Use when writing SQL queries, exploring schemas, running migrations, optimizing queries, transpiling between dialects, or connecting to databases via native CLIs.
MongoDB engineering standards for querying collections, building aggregation pipelines, designing document schemas, managing indexes, and administering deployments via mongosh. Use when writing MongoDB queries, exploring collections, designing schemas, optimizing performance, or managing replica sets and sharding.
Engineering planning standards for creating design docs, DRI working docs, ADRs, and weekly updates. Use when planning projects, writing design docs, creating RFCs, tracking risks, writing status updates, or reviewing engineering plans. Covers structure, operational tracking, context engineering, and scaling from startup to enterprise.
Multi-agent PR review that spawns parallel domain-specific subagents (python-expert, rust-expert, dbt-expert, dotnet-expert, kedro-expert, d2-tala-expert, ui-designer) based on changed file types, posts inline review comments on GitHub, GitLab, and Azure DevOps.
dbt engineering standards for building clean, modular, well-tested data transformations. Use when writing dbt models, configuring sources, designing project structure, writing tests, managing materializations, or preparing for dbt Fusion. Covers dbt Core 1.8–1.11, Fusion v2.0, SQL style, testing, governance, and deployment.
Langfuse observability platform standards for querying traces, managing prompts, debugging LLM applications, and accessing Langfuse data programmatically. Use when interacting with Langfuse, querying traces or sessions, managing prompts, instrumenting applications, or looking up Langfuse documentation. Covers CLI-based API access (via npx) and documentation retrieval.