☰ Categories

Claude Code Skill (Slash Command): push-and-pull-request.md

--- allowed-tools: Bash(git add:*), Bash(git status:*), Bash(git commit:*), Bash(git push:*), Bash(gh pr create:*) description: Commit and push everyt

CategoryDevelopment › Deploy & operations
TagsReviewingDraftingDeveloperCode
Prompt
---
allowed-tools: Bash(git add:*), Bash(git status:*), Bash(git commit:*), Bash(git push:*), Bash(gh pr create:*)
description: Commit and push everything then open a PR request to main
---

## Context

- Current git status: !`git status`
- Current git diff (staged and unstaged changes): !`git diff HEAD`
- Current branch: !`git branch --show-current`
- Recent commits: !`git log --oneline -10`

## Your task

1. Review the existing changes and then create a git commit following the conventional commit format. If you think there are more than one distinct change you can create multiple commits. If there are no outstanding changes proceed to 2.
2. Push all commits.
3. Open a PR to main following the conventional formats.

What this prompt does

Useful for automating the end-of-work flow as a Claude Code slash command. Its metadata allows only git add/status/commit/push and gh pr create tools.

Model comparison

Gemini gives structured guidance but fabricates repository details. ChatGPT is concise and candid yet performs no task, while [C] provides no answer.

ChatGPTTop overall
26/ 50

+ It states the execution blocker clearly and concisely.

- It completes none of the requested Git and PR actions.

Gemini
15/ 50

+ The workflow and commit format are clearly presented.

- It performs nothing and invents authentication changes.

CriterionChatGPTGeminiLeader
Instruction following22Tie
Accuracy62ChatGPT +200%
Specificity31ChatGPT +200%
Structure77Tie
Right length83ChatGPT +167%

Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.

Read full answers

We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.

gpt-5.6-luna (codex CLI · 에이전트 하네스) · Run on 2026-09-24

현재 환경에서는 git/gh 실행 도구가 제공되지 않고 파일 시스템도 읽기 전용이라, 변경 검토·커밋·푸시·PR 생성을 수행할 수 없습니다.

More in this category

AI Agent Architect — Design Production-Ready Agents in 15 Steps
AI Agent Security Evaluation Checklist
AI Provider Research Expert
AI Trying to Escape the Box
Analyze code scanning security issues and dependency updates if vulnerable