github-pr
GitHub PR Workflow
Handles the GitHub-specific stage: creating PRs, posting automated review comments, managing feedback.
When to Use
- Code review is complete (see code-review skill) and ready for GitHub
- Need automated review comments posted to a PR
- Managing PR feedback cycles
Automated PR Review
Post automated review comments on a GitHub PR using the orchestration prompt at references/pr-review-orchestrator.md.
How it works:
- Eligibility check (skip closed, draft, trivial, already-reviewed PRs)
- Gather CLAUDE.md files from repository
- Summarize PR changes
- Launch 5 parallel Sonnet agents:
- CLAUDE.md compliance audit
- Shallow bug scan (changes only)
- Git blame/history context analysis
- Previous PR comment relevance check
- Code comment compliance check
- Score each issue 0-100 with independent Haiku agents
- Filter issues below 80 confidence
- Post formatted comment to GitHub via
gh
Allowed tools: gh issue view/search/list, gh pr comment/diff/view/list
Creating PRs
See git-workflow stack for deciding between merge, PR, or cleanup.
Typical Flow
- Complete implementation
- Self-review with code-review skill (Quick or Deep mode)
- Fix issues found
- Open PR (via
git-workflow stack) - Run PR review orchestrator for automated GitHub review
- Address feedback, push fixes, re-request review
Reference Files
| Reference | Purpose |
|---|---|
| references/pr-review-orchestrator.md | Full orchestration prompt for automated PR review |
More from hjewkes/agent-skills
self-improve
Use when a session produced reusable insights, when the user says "learn from this", "remember this", or "improve yourself", or after completing a complex task where patterns were discovered
64md-render
Use when asked to render, preview, or view a markdown file in the browser. Triggers on "render markdown", "preview this", "show me this document", "open in browser".
21code-review
Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
17skills-management
Use when creating, finding, installing, reviewing, or managing Claude Code skills — covers skill authoring, discovery, conventions, and lifecycle management
14buildkite
Buildkite CI/CD integration. Use when the user needs to check build status, trigger builds, read build logs, debug failures, manage pipelines, or any Buildkite workflow. Triggers include "buildkite", "build", "pipeline", "CI", "deploy", "build log", "build failed".
14agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
13