From aide
Load PR comments and feedback for code review. Use when the user wants to see reviewer feedback, check for unresolved comments, understand what changes are requested, or review discussion on a PR.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aide:pr-commentsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fetch PR comments to review feedback from reviewers.
Fetch PR comments to review feedback from reviewers.
Run:
aide pr comments [--pr <id|url>] [options]
| Flag | Description |
|---|---|
--pr | PR ID or URL (auto-detected from branch if omitted) |
--latest | Limit to N most recent comments |
--thread-status | Filter by thread status: active, fixed, closed |
--author | Filter by reviewer email or name |
--include-system | Include system-generated comments (default: false) |
--format | Output format: text, json, markdown |
Comments organized by:
--thread-status active to focus on unresolved feedback--latest N to see most recent discussion--author to see specific reviewer's feedback--format json for structured processing# View all active (unresolved) threads
aide pr comments --thread-status active
# Get latest 10 comments
aide pr comments --latest 10
# See specific reviewer's feedback
aide pr comments --author "[email protected]"
# Get structured data for analysis
aide pr comments --format json
After loading comments:
After reviewing comments:
npx claudepluginhub rlcurrall/aide --plugin aideFetches, organizes, and presents GitHub PR comments—issue-level, review bodies, inline—grouped by human/bot with extracted must-fix/optional actionable items.
Fetches unresolved GitHub PR review comments, filtered by author/reviewer role and recency (last-review or date). Use to address feedback, check resolutions, or resume PR work.
Fetches and filters PR review comments, extracts outside-diff-range feedback from review bodies, and resolves threads with proper attribution. Useful when addressing CodeRabbit, Cursor, or human reviewer feedback.