github-pr

GitHub PR workflow — creating PRs, posting automated review comments, managing PR feedback cycles. Use when code is reviewed and ready for GitHub.

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 "github-pr" with this command: npx skills add hjewkes/agent-skills/hjewkes-agent-skills-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:

  1. Eligibility check (skip closed, draft, trivial, already-reviewed PRs)
  2. Gather CLAUDE.md files from repository
  3. Summarize PR changes
  4. 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
  5. Score each issue 0-100 with independent Haiku agents
  6. Filter issues below 80 confidence
  7. 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

  1. Complete implementation
  2. Self-review with code-review skill (Quick or Deep mode)
  3. Fix issues found
  4. Open PR (via git-workflow stack)
  5. Run PR review orchestrator for automated GitHub review
  6. Address feedback, push fixes, re-request review

Reference Files

ReferencePurpose
references/pr-review-orchestrator.mdFull orchestration prompt for automated PR review

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.

Coding

code-review

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

managing-github-issues

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

subagent-driven-development

No summary provided by upstream source.

Repository SourceNeeds Review