github

$npx mdskill add openai/plugins/github

Triages GitHub repositories, pull requests, and issues to route tasks to specialized workflows or provide summaries.

  • Helps users get general GitHub assistance, PR or issue summaries, and repository context.
  • Integrates with the GitHub app for most workflows and uses local git and gh tools for specific tasks.
  • Decides based on intent whether to handle triage or hand off to a specialist skill.
  • Presents results through repository orientation, metadata summaries, and patch inspections.

SKILL.md

.github/skills/githubView on GitHub ↗
---
name: github
description: Triage and orient GitHub repository, pull request, and issue work through the connected GitHub app. Use when the user asks for general GitHub help, wants PR or issue summaries, or needs repository context before choosing a more specific GitHub workflow.
---

# GitHub

## Overview

Use this skill as the umbrella entrypoint for general GitHub work in this plugin. It should decide whether the task stays in repo and PR triage or should be handed off to a more specific review, CI, or publish workflow.

This plugin is intentionally hybrid:

- Prefer the GitHub app from this plugin for repository, issue, pull request, comment, label, reaction, and PR creation workflows.
- Use local `git` and `gh` only when the connector does not cover the job well, especially for current-branch PR discovery, branch creation, commit and push, `gh auth status`, and GitHub Actions log inspection.
- Keep connector state and local checkout context aligned. If the request is about the current branch, resolve the local repo and branch before acting.

Once the intent is clear, route to the specialist skill immediately and do not keep broad GitHub triage in scope longer than needed.

## Connector-First Responsibilities

Handle these directly in this skill when the request does not need a narrower specialist workflow:

- repository orientation once the repo, PR, issue, or local checkout is identified
- recent PR or issue triage
- PR metadata summaries
- PR patch inspection
- PR comments, labels, and reactions
- issue lookup and summarization
- PR creation after a branch is already pushed

Prefer the GitHub app from this plugin for those flows because it provides structured PR, issue, and review-adjacent data without depending on a local checkout. If the repository is not already identifiable from the user request or local git context, ask for the repo instead of pretending there is a repo-search flow that may not exist.

## Routing Rules

1. Resolve the operating context first:
   - If the user provides a repository, PR number, issue number, or URL, use that.
   - If the request is about "this branch" or "the current PR", resolve local git context and use `gh` only as needed to discover the branch PR.
   - If the repository is still ambiguous after local inspection, ask for the repo identifier.
2. Classify the request before taking action:
   - `repo or PR triage`: summarize PRs, issues, patches, comments, labels, reactions, or repository state
   - `review follow-up`: unresolved review threads, requested changes, or inline review feedback
   - `CI debugging`: failing checks, Actions logs, or CI root-cause analysis
   - `publish changes`: create or switch branches, stage changes, commit, push, and open a draft PR
3. Route to the specialist skill as soon as the category is clear:
   - Review comments and requested changes: `../gh-address-comments/SKILL.md`
   - Failing GitHub Actions checks: `../gh-fix-ci/SKILL.md`
   - Commit, push, and open PR: `../yeet/SKILL.md`
4. Keep the hybrid model consistent after routing:
   - connector first for PR and issue data
   - local `git` and `gh` only for the specific gaps the connector does not cover

## Default Workflow

1. Resolve repository and item scope.
2. Gather structured PR or issue context through the GitHub app from this plugin.
3. Decide whether the task stays in connector-backed triage or needs a specialist skill.
4. Route immediately when the work becomes review follow-up, CI debugging, or publish workflow.
5. End with a clear summary of what was inspected, what changed, and what remains.

## Output Expectations

- For triage requests, return a concise summary of the repository, PR, or issue state and the next likely action.
- For mixed requests, tell the user which specialist path you are taking and why.
- For connector-backed write actions, restate the exact PR, issue, label, or reaction target before applying the change.
- Never imply that GitHub Actions logs are available through the connector alone. That remains a `gh` workflow.

## Examples

- "Use GitHub to summarize the open PRs in this repo and tell me what needs attention."
- "Help with this PR."
- "Review the latest comments on PR 482 and tell me what is actionable."
- "Debug the failing checks on this branch."
- "Commit these changes, push them, and open a draft PR."

More from openai/plugins

SkillDescription
accessibility-and-inclusive-visualizationMake data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.
agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
agent-browser-verifyAutomated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
agents-sdkBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
ai-elementsAI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.
ai-gatewayVercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.
ai-generation-persistenceAI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
ai-sdkVercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
aiq-deploy|
aiq-research|