yeet

Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.

685 stars

Best use case

yeet is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.

Teams using yeet should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/yeet/SKILL.md --create-dirs "https://raw.githubusercontent.com/openai/plugins/main/plugins/github/skills/yeet/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/yeet/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How yeet Compares

Feature / AgentyeetStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# GitHub Publish Changes

## Overview

Use this skill only when the user explicitly wants the full publish flow from the local checkout: branch setup if needed, staging, commit, push, and opening a pull request.

This workflow is hybrid:

- Use local `git` for branch creation, staging, commit, and push.
- Prefer the GitHub app from this plugin for pull request creation after the branch is on the remote.
- Use `gh` as a fallback for current-branch PR discovery, auth checks, or PR creation when the connector path cannot infer the repository or head branch cleanly.

## Prerequisites

- Require GitHub CLI `gh`. Check `gh --version`. If missing, ask the user to install `gh` and stop.
- Require authenticated `gh` session. Run `gh auth status`. If not authenticated, ask the user to run `gh auth login` (and re-run `gh auth status`) before continuing.
- Require a local git repository with a clean understanding of which changes belong in the PR.

## Naming conventions

- Branch: `codex/{description}` when starting from main/master/default.
- Commit: `{description}` (terse).
- PR title: `[codex] {description}` summarizing the full diff.

## Workflow

1. Confirm intended scope.
   - Run `git status -sb` and inspect the diff before staging.
   - If the working tree contains unrelated changes, do not default to `git add -A`. Ask the user which files belong in the PR.
2. Determine the branch strategy.
   - If on `main`, `master`, or another default branch, create `codex/{description}`.
   - Otherwise stay on the current branch.
3. Stage only the intended changes.
   - Prefer explicit file paths when the worktree is mixed.
   - Use `git add -A` only when the user has confirmed the whole worktree belongs in scope.
4. Commit tersely with the confirmed description.
5. Run the most relevant checks available if they have not already been run.
   - If checks fail due to missing dependencies or tools, install what is needed and rerun once.
6. Push with tracking: `git push -u origin $(git branch --show-current)`.
7. Open a draft PR.
   - Prefer the GitHub app from this plugin for PR creation after the push succeeds.
   - Derive `repository_full_name` from the remote, for example by normalizing `git remote get-url origin` or by using `gh repo view --json nameWithOwner`.
   - Derive `head_branch` from `git branch --show-current`.
   - Derive `base_branch` from the user request when specified; otherwise use the remote default branch, for example via `gh repo view --json defaultBranchRef`.
   - If the branch is being pushed from a fork or the PR target differs from the remote that was just pushed, prefer `gh pr create` fallback because the connector PR creation flow expects one repository target and may not encode cross-repo head semantics cleanly.
   - If connector-based PR creation cannot infer the repository or branch cleanly, fall back to `gh pr create --draft --fill --head $(git branch --show-current)`.
   - Write the PR body to a temp file with real newlines when using CLI fallback so the markdown renders cleanly.
8. Summarize the result with branch name, commit, PR target, validation, and anything the user still needs to confirm.

## Write Safety

- Never stage unrelated user changes silently.
- Never push without confirming scope when the worktree is mixed.
- Default to a draft PR unless the user explicitly asks for a ready-for-review PR.
- If the repository does not appear to be connected to an accessible GitHub remote, stop and explain the blocker before making assumptions.

## PR Body Expectations

The PR description should use real Markdown prose and cover:

- what changed
- why it changed
- the user or developer impact
- the root cause when the PR is a fix
- the checks used to validate it

Related Skills

workflow

685
from openai/plugins

Vercel Workflow DevKit (WDK) expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.

verification

685
from openai/plugins

Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.

vercel-storage

685
from openai/plugins

Vercel storage expert guidance — Blob, Edge Config, and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.

vercel-services

685
from openai/plugins

Vercel Services — deploy multiple services within a single Vercel project. Use for monorepo layouts or when combining a backend (Python, Go) with a frontend (Next.js, Vite) in one deployment.

vercel-sandbox

685
from openai/plugins

Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.

vercel-queues

685
from openai/plugins

Vercel Queues guidance (public beta) — durable event streaming with topics, consumer groups, retries, and delayed delivery. $0.60/1M ops. Powers Workflow DevKit. Use when building async processing, fan-out patterns, or event-driven architectures.

vercel-functions

685
from openai/plugins

Vercel Functions expert guidance — Serverless Functions, Edge Functions, Fluid Compute, streaming, Cron Jobs, and runtime configuration. Use when configuring, debugging, or optimizing server-side code running on Vercel.

vercel-flags

685
from openai/plugins

Vercel Flags guidance — feature flags platform with unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters. Use when implementing feature flags, experimentation, or staged rollouts.

vercel-firewall

685
from openai/plugins

Vercel Firewall and security expert guidance. Use when configuring DDoS protection, WAF rules, rate limiting, bot filtering, IP allow/block lists, OWASP rulesets, Attack Challenge Mode, or any security configuration on the Vercel platform.

vercel-cli

685
from openai/plugins

Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, managing domains, or interacting with the Vercel platform from the command line.

vercel-api

685
from openai/plugins

Vercel MCP and REST API expert guidance. Use when the agent needs live access to Vercel projects, deployments, environment variables, domains, logs, or documentation through the MCP server or REST API.

vercel-agent

685
from openai/plugins

Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.