Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计提醒

fix-coderabbit-review修复 Coderabbit 审查

Agent Skill

fix-coderabbit-review 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,681

周安装

68

GitHub Stars

323

下载量

528
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:fix-coderabbit-review(修复 Coderabbit 审查)
来源仓库:https://github.com/pedronauck/skills
仓库路径:skills/fix-coderabbit-review
安装命令:
npx skills add https://github.com/pedronauck/skills --skill fix-coderabbit-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/pedronauck/skills --skill fix-coderabbit-review

简介

fix-coderabbit-review 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定仓库安装,需确认权限与维护状态。
  • 使用前应核实是否会触发联网、命令执行或文件读写操作。
  • 建议结合原始 README 进一步核验具体用法和功能边界。

SKILL.md

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_TOKEN in environment.
  • gh authenticated for the target repository.

Workflow

  1. Export review issues for the PR.
  2. Triage and validate every unresolved issue.
  3. Fix every validated issue completely.
  4. Commit all remediation changes together in one commit.
  5. 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.md
  • ai-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:

  1. Restate the concrete technical change required.
  2. Verify against current codebase behavior and tests.
  3. 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 (VALID or INVALID) recorded during triage.
  • Updated ai-docs/reviews-pr-<PR_NUMBER>/issues/*.md statuses.
  • Updated ai-docs/reviews-pr-<PR_NUMBER>/_summary.md counts/checklist.
  • Resolved review threads for addressed issues.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.22%
按下载量换算191

Claude

27.05%
按下载量换算143

Cursor

19.51%
按下载量换算103

Gemini CLI

8%
按下载量换算42

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills