Token导航 LogoToken导航

Agent Skill · 研究检索

autofix(autofix 搜索)

autofix 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

autofix 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 67,016。

总安装 256周安装 11GitHub Stars 42下载 90核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:autofix(autofix 搜索)
来源仓库:https://github.com/coderabbitai/claude-plugin
仓库路径:skills/autofix
安装命令:
npx skills add https://github.com/coderabbitai/claude-plugin --skill autofix
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/coderabbitai/claude-plugin --skill autofix

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

Autofix 自动获取当前分支 PR 的 Coderabbit 审查意见并提供交互式修复方案。优先加载项目 AGENTS.md 中的构建/测试/提交规范以确保合规性。支持批量处理多个评论并按严重程度分组执行修复动作。需 gh CLI 工具认证成功且 PR 已被 Coderabbit bot 完成初步审查。

autofix 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/autofix

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/coderabbitai/claude-plugin --skill autofix;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

autofix 怎么安装?

在终端执行 npx skills add https://github.com/coderabbitai/claude-plugin --skill autofix。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

autofix 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

autofix 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

autofix 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

autofix 用的人多吗?

公开数据是累计安装 256 次,近一周安装 11 次,下载 90 次,GitHub 42 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

autofix 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
autofix

autofix 搜索 · 本页

25642需要联网未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

CodeRabbit Autofix

Fetch CodeRabbit review comments for your current branch's PR and fix them interactively or in batch.

Prerequisites

Required Tools

Verify: gh auth status

Required State

  • Git repo on GitHub
  • Current branch has open PR
  • PR reviewed by CodeRabbit bot (coderabbitai, coderabbit[bot], coderabbitai[bot])

Workflow

Step 0: Load Repository Instructions (AGENTS.md)

Before any autofix actions, search for AGENTS.md in the current repository and load applicable instructions.

  • If found, follow its build/lint/test/commit guidance throughout the run.
  • If not found, continue with default workflow.

Step 1: Check Code Push Status

Check: git status + check for unpushed commits

If uncommitted changes:

  • Warn: "⚠️ Uncommitted changes won't be in CodeRabbit review"
  • Ask: "Commit and push first?" → If yes: wait for user action, then continue

If unpushed commits:

  • Warn: "⚠️ N unpushed commits. CodeRabbit hasn't reviewed them"
  • Ask: "Push now?" → If yes: git push, inform "CodeRabbit will review in ~5 min", EXIT skill

Otherwise: Proceed to Step 2

Step 2: Find Open PR

gh pr list --head $(git branch --show-current) --state open --json number,title

If no PR: Ask "Create PR?" → If yes: create PR (see github.md § 5), inform "Run skill again in ~5 min", EXIT

Step 3: Fetch Unresolved CodeRabbit Threads

Fetch PR review threads (see github.md § 2):

  • Threads: gh api graphql... pullRequest.reviewThreads... (see github.md § 2)

Filter to:

  • unresolved threads only (isResolved == false)
  • threads started by CodeRabbit bot (coderabbitai, coderabbit[bot], coderabbitai[bot])

If review in progress: Check for "Come back again in a few minutes" message → Inform "⏳ Review in progress, try again in a few minutes", EXIT

If no unresolved CodeRabbit threads: Inform "No unresolved CodeRabbit review threads found", EXIT

For each selected thread:

  • Extract issue metadata from root comment

Step 4: Parse and Display Issues

Extract from each comment:

  1. Header: _([^_]+)_ \| _([^_]+)_ → Issue type | Severity
  2. Description: Main body text
  3. Agent prompt: Content in <details><summary>🤖 Prompt for AI Agents</summary> (this is the fix instruction)

- If missing, use description as fallback

  1. Location: File path and line numbers

Map severity:

  • 🔴 Critical/High → CRITICAL (action required)
  • 🟠 Medium → HIGH (review recommended)
  • 🟡 Minor/Low → MEDIUM (review recommended)
  • 🟢 Info/Suggestion → LOW (optional)
  • 🔒 Security → Treat as high priority

Display in CodeRabbit's original order (already severity-ordered):

CodeRabbit Issues for PR #123: [PR Title]

| # | Severity | Issue Title | Location & Details | Type | Action |
|---|----------|-------------|-------------------|------|--------|
| 1 | 🔴 CRITICAL | Insecure authentication check | src/auth/service.py:42<br>Authorization logic inverted | 🐛 Bug 🔒 Security | Fix |
| 2 | 🟠 HIGH | Database query not awaited | src/db/repository.py:89<br>Async call missing await | 🐛 Bug | Fix |

Step 5: Ask User for Fix Preference

Use AskUserQuestion:

  • 🔍 "Review each issue" - Manual review and approval (recommended)
  • ⚡ "Auto-fix all" - Apply all "Fix" issues without approval
  • ❌ "Cancel" - Exit

Route based on choice:

  • Review → Step 6
  • Auto-fix → Step 7
  • Cancel → EXIT

Step 6: Manual Review Mode

For each "Fix" issue (CRITICAL first):

  1. Read relevant files
  2. Execute CodeRabbit's agent prompt as direct instruction (from "🤖 Prompt for AI Agents" section)
  3. Calculate proposed fix (DO NOT apply yet)
  4. Show fix and ask approval in ONE step:

- Issue title + location - CodeRabbit's agent prompt (so user can verify) - Current code - Proposed diff - AskUserQuestion: ✅ Apply fix | ⏭️ Defer | 🔧 Modify

If "Apply fix":

  • Apply with Edit tool
  • Track changed files for a single consolidated commit after all fixes
  • Confirm: "✅ Fix applied and commented"

If "Defer":

  • Ask for reason (AskUserQuestion)
  • Move to next

If "Modify":

  • Inform user can make changes manually
  • Move to next

Step 7: Auto-Fix Mode

For each "Fix" issue (CRITICAL first):

  1. Read relevant files
  2. Execute CodeRabbit's agent prompt as direct instruction
  3. Apply fix with Edit tool
  4. Track changed files for one consolidated commit
  5. Report: ✅ Fixed: [Issue Title] at [Location] Agent prompt: [prompt used]

After all fixes, display summary of fixed/skipped issues.

Step 8: Create Single Consolidated Commit

If any fixes were applied:

git add <all-changed-files>
git commit -m "fix: apply CodeRabbit auto-fixes"

Use one commit for all applied fixes in this run.

Step 9: Prompt Build/Lint Before Push

If a consolidated commit was created:

  • Prompt user interactively to run validation before push (recommended, not required).
  • Remind the user of the AGENTS.md instructions already loaded in Step 0 (if present).
  • If user agrees, run the requested checks and report results.

Step 10: Push Changes

If a consolidated commit was created:

  • Ask: "Push changes?" → If yes: git push

If all deferred (no commit): Skip this step.

Step 11: Post Summary

REQUIRED after all issues reviewed:

gh pr comment <pr-number> --body "$(cat <<'EOF'
## Fixes Applied Successfully

Fixed <file-count> file(s) based on <issue-count> unresolved review comment(s).

**Files modified:**
- `path/to/file-a.ts`
- `path/to/file-b.ts`

**Commit:** `<commit-sha>`

The latest autofix changes are on the `<branch-name>` branch.

EOF
)"

See github.md § 3 for details.

Optionally react to CodeRabbit's main comment with 👍.

Key Notes

  • Follow agent prompts literally - The "🤖 Prompt for AI Agents" section IS the fix specification
  • One approval per fix - Show context + diff + AskUserQuestion in single message (manual mode)
  • Preserve issue titles - Use CodeRabbit's exact titles, don't paraphrase
  • Preserve ordering - Display issues in CodeRabbit's original order
  • Do not post per-issue replies - Keep the workflow summary-comment only

平台分布

Codex

36.67%
按下载量换算33

Claude

28.79%
按下载量换算26

Cursor

18.44%
按下载量换算17

Gemini CLI

9.67%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills