fix-coderabbit-review
End-to-end remediation workflow for PR review feedback by PR number. Use when Codex must export CodeRabbit issues for a PR, fix every issue completely, commit all fixes in a single commit, and resolve GitHub review threads afterward. Don't use for general PR reviews unrelated to CodeRabbit, draft PRs without review threads, or merge-strategy decisions.
- License 许可
- MIT
- 最近更新
- 2026-07-16
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- fix-coderabbit-review
- metadata
- { "author": "Pedro Nauck", "github": "https://github.com/pedronauck", "repository": "https://github.com/pedronauck/skills" }
- description
- End-to-end remediation workflow for PR review feedback by PR number. Use when Codex must export CodeRabbit issues for a PR, fix every issue completely, commit all fixes in a single commit, and resolve GitHub review threads afterward. Don't use for general PR reviews unrelated to CodeRabbit, draft PRs without review threads, or merge-strategy decisions.
02 资源文件 5
- 参考文档agents/openai.yaml289 B
- 脚本scripts/pr_review.py35.4 KB
- 脚本scripts/pr-review.ts37.8 KB
- 脚本scripts/resolve_pr_issues.py7.6 KB
- 脚本scripts/resolve_pr_issues.sh6.1 KB
03 SKILL.md 正文
Fix CodeRabbit Review
Execute PR review remediation in a strict sequence: export issues, fix all issues, commit once, resolve threads.
Core principle: evaluate each review item technically before changing code. Do not apply suggestions blindly.
Required Inputs
- PR number (integer).
GITHUB_TOKENin environment.ghauthenticated for the target repository.
Workflow
- Export review issues for the PR.
- Triage and validate every unresolved issue.
- Fix every validated issue completely.
- Commit all remediation changes together in one commit.
- Resolve review threads and mark exported issues resolved.
Run commands from repository root.
Step 1: Export CodeRabbit Issues
Use bundled exporter script:
PR_NUMBER=<pr-number>
uv run .claude/skills/fix-coderabbit-review/scripts/pr_review.py "$PR_NUMBER" --hide-resolved
Read generated files in:
ai-docs/reviews-pr-<PR_NUMBER>/_summary.mdai-docs/reviews-pr-<PR_NUMBER>/issues/*.md
If _summary.md shows unresolved issues, continue until all are addressed in code.
Step 2: Triage and Validate Issues
Review each unresolved issue file before implementation.
For each issue:
- Restate the concrete technical change required.
- Verify against current codebase behavior and tests.
- Decide one of:
VALID: suggestion is correct and should be implemented.INVALID: suggestion is incorrect or not actionable for this codebase.
Rules:
- If an issue is ambiguous, treat it as
INVALID, document rationale and assumptions in the issue file, and continue execution. - If an issue is
INVALID, document technical rationale directly in the issue file and do not force a bad change. - Prefer technical evidence over agreement language.
Step 3: Fix Issues Completely
Process all unresolved issue files under ai-docs/reviews-pr-<PR_NUMBER>/issues/.
- Implement production-quality fixes in source code.
- Add or update tests so each fix is verified.
- Execute fixes one issue at a time and validate each before moving to the next.
- Do not leave partial fixes.
- Do not skip issues unless they are invalid; for invalid issues, keep rationale in the issue file.
After finishing all issue fixes, run full verification before commit:
pnpm run lint
pnpm run typecheck
pnpm run test
Step 4: Commit All Fixes Together
Create exactly one remediation commit containing all related code, test, and issue-tracking changes.
git add -A
git commit -m "fix(repo): resolve PR #<PR_NUMBER> review issues"
Do not split fixes across multiple commits.
Step 5: Resolve Review Threads
After the single commit is created, resolve exported issue threads.
Determine the issue range from issue files (example: 001 to 018) and run:
uv run .claude/skills/fix-coderabbit-review/scripts/resolve_pr_issues.py \
--pr-dir ai-docs/reviews-pr-<PR_NUMBER> \
--from <first-issue-number> \
--to <last-issue-number>
Re-open ai-docs/reviews-pr-<PR_NUMBER>/_summary.md and confirm unresolved count is 0.
If thread resolution fails for specific IDs, keep those issues marked unresolved and report exact failures instead of claiming completion.
Output Contract
Deliver:
- One commit containing all remediation changes.
- Per-issue technical disposition (
VALIDorINVALID) recorded during triage. - Updated
ai-docs/reviews-pr-<PR_NUMBER>/issues/*.mdstatuses. - Updated
ai-docs/reviews-pr-<PR_NUMBER>/_summary.mdcounts/checklist. - Resolved review threads for addressed issues.
04 同仓库更多 Skills
to-prompt-opus
Use when preparing or rewriting prompts for Claude Opus 4.8, Anthropic API agents, XML-structured prompts, long-context document work, coding agents, research synthesis, frontend/design tasks, or model-specific prompt optimization. Do not use for GPT/OpenAI prompts or raw context packaging without Opus-specific tuning.
to-prompt-gpt
Use when preparing or rewriting prompts for GPT-5.5, OpenAI API agents, Responses workflows, coding agents, research synthesis, support assistants, or model-specific prompt optimization. Do not use for Claude/Opus prompts or raw context packaging without GPT-specific tuning.
plan-refactor-qa
Plans and runs qa-report before executing Compozy refactor tasks. Use when the user provides a refactor or issue slug and wants Codex to inspect the matching .compozy/tasks directory, related PRD/TechSpec/ADR/task artifacts, affected code, and existing tests, then invoke $qa-report with a repository-grounded prompt. Do not use to run tests, execute qa-execution, implement code, or perform post-refactor verification.
multi-tool-branch-review
Orchestrates a multi-tool branch review of the current git branch against a base branch. By default it runs two independent thermo-nuclear maintainability audits, one on Codex GPT-5.5 xhigh and one on Claude Opus xhigh, then consolidates the findings into a single remediation plan via writing-plans. If the user explicitly asks for native reviews, it can add the Claude native review pass, the Codex native review pass, or both. Use when the user wants a deep cross-model review of a branch or PR before merge, or asks to review this branch with multiple tools or models. Encodes known infra failure modes and their fixes (missing Claude ACP adapter, Codex MCP auth hangs, false-positive report files, long jobs orphaned inside subagents). Do not use for reviewing a single uncommitted snippet, for non-git work, for running only one reviewer, or when the user only wants a quick lint or test run.
create-pr-with-template
Create a GitHub Pull Request with gh CLI and prefer repository PR templates automatically. Use this whenever the user asks to open/create a PR, especially when template compliance is needed. If multiple templates exist, ask the user which template to use.
ui-craft
Provides guardrails for user-facing UI work: usability heuristics, accessibility floors, design-system discipline, component states, microcopy, motion, dark mode, responsive behavior, and human-AI UX. Use when designing, generating, reviewing, or refactoring visible product surfaces such as components, pages, dashboards, forms, dialogs, loading/empty/error states, or AI interfaces. Do not use for backend-only work, infrastructure, CLI/TUI design, or pure documentation editing.