cp

Commit & Push Skill

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "cp" with this command: npx skills add october-academy/agent-plugins/october-academy-agent-plugins-cp

Commit & Push Skill

Streamlined git workflow: stage, commit, and push in one command.

Usage

Basic

/cp # Auto-generate commit message /cp "fix: resolve bug" # Use provided message

Korean Triggers

  • "커밋하고 푸시"

  • "커밋 푸시"

  • "변경사항 올려줘"

Workflow

  1. Analyze Changes

git status # See all changes git diff --staged # Staged changes git diff # Unstaged changes git log -3 --oneline # Recent commits for context

  1. Generate Commit Message

If no message provided, analyze changes and generate following Conventional Commits:

Prefix Use Case

feat:

New feature

fix:

Bug fix

docs:

Documentation

refactor:

Code restructuring

style:

Formatting (no logic change)

test:

Adding tests

chore:

Maintenance tasks

  1. Stage Files

Prefer specific files over git add -A :

git add src/component.tsx src/utils.ts

Never stage:

  • .env files

  • Credentials or secrets

  • Large binary files (unless intentional)

  1. Commit

Use HEREDOC for proper formatting:

git commit -m "$(cat <<'EOF' type: concise description

Optional body with more details.

Co-Authored-By: Claude <noreply@anthropic.com> EOF )"

  1. Push

git push origin <current-branch>

If upstream not set:

git push -u origin <current-branch>

Safety Checks

Before committing:

  • No secrets: Scan for API keys, passwords, tokens

  • Correct branch: Verify not pushing to protected branch accidentally

  • Clean diff: Review what's being committed

Error Handling

Error Solution

"Nothing to commit" No changes detected, inform user

"Push rejected" Run git pull first, then retry

"Pre-commit hook failed" Fix issues, stage again, create NEW commit

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

sync

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

ship

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

interview-spec

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

perf

No summary provided by upstream source.

Repository SourceNeeds Review