pr-feedbacklisted

Address PR review feedback including inline threads, general comments, bot-generated reviews, PR description findings, check run annotations (inline lint/type/security findings shown in the Files changed tab), code scanning alerts, and CI failures. Use when asked to handle, address, resolve, respond to, or work through PR review comments, review feedback, inline findings, or CI check failures. Triggers on requests like "address PR comments", "handle review feedback", "resolve PR reviews", "fix review comments", "go through PR feedback", "check CI failures", "fix the inline findings on the PR".
dversoza/claude-skills · ★ 2 · AI & Automation · score 66

Install: claude install-skill dversoza/claude-skills

# PR Feedback Fetch all review feedback and CI status from the PR associated with the current branch, triage each item, implement fixes, and propose responses. All commands auto-detect the repository and PR from the current branch. ## Step 1: Fetch All Review Feedback Run all four fetch commands to collect every feedback surface: ```bash python3 ~/.claude/skills/pr-feedback/scripts/pr_feedback.py threads # unresolved inline review threads python3 ~/.claude/skills/pr-feedback/scripts/pr_feedback.py ci # CI check status and failures python3 ~/.claude/skills/pr-feedback/scripts/pr_feedback.py comments # general PR comments, review bodies, PR description python3 ~/.claude/skills/pr-feedback/scripts/pr_feedback.py annotations # check run annotations and code scanning alerts ``` If any fails (no PR for current branch, auth issues), report the error and stop. `threads` returns `unresolved_threads` with thread_id, path, line, and comments (each with node_id, database_id, diff_hunk). `ci` returns `ci_summary` (pass/fail/pending counts) and `failed_checks` (with run_id, job_id for log fetching). On a failed fetch it returns empty counts plus an `error` field -- see Step 4. `comments` returns `pr_body` (may contain bot-appended review content), `pr_comments` (each with node_id, database_id), `review_bodies` (top-level bodies of submitted reviews -- where CodeRabbit, Copilot and similar bots post their summary), and `pr_author`. `annotations` returns `annota