Token导航 LogoToken导航

Agent Skill · 待分类

review-response(审查回复)

review-response 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。

review-response 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在待分类类的 11,209 个 Skill 里排第 4,844。

总安装 661周安装 27GitHub Stars 66下载 212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:review-response(审查回复)
来源仓库:https://github.com/indranilbanerjee/digital-marketing-pro
仓库路径:skills/review-response
安装命令:
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill review-response
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/indranilbanerjee/digital-marketing-pro --skill review-response

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

review-response 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合围绕仓库状态和代码变更进行整理。适用于需要同步项目进展、跟踪协作事项或分析代码变更的待分类场景。通过调用可获取仓库元数据、Issue 内容和 PR 详情等信息。

安装前需确认权限范围和维护状态,注意是否会触发网络请求或文件操作。可通过 npx skills add 命令从指定 GitHub 仓库安装使用。

来源仓库内路径:skills/review-response

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/indranilbanerjee/digital-marketing-pro --skill…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

review-response 怎么安装?

在终端执行 npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill review-re…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

review-response 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。

review-response 需要什么权限?

权限级别是只读。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。

review-response 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。

review-response 用的人多吗?

公开数据是累计安装 661 次,近一周安装 27 次,下载 212 次,GitHub 66 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。

review-response 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

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。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
review-response

审查回复 · 本页

66166只读未明确通过

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

/dm:review-response

Purpose

Generate professional, brand-aligned review responses for positive, neutral, and negative reviews across any platform. Ensures every response maintains brand voice, addresses the reviewer's specific points, and follows best practices for reputation management and customer recovery.

Input Required

The user must provide (or will be prompted for):

  • Review text: The full text of the review to respond to
  • Rating: Star rating (1-5 stars)
  • Platform: Where the review was posted (Google, Yelp, G2, Capterra, Trustpilot, Amazon, TripAdvisor, App Store, etc.)
  • Reviewer name: Display name of the reviewer (optional — for personalization)
  • Specific issue mentioned: Key complaint, praise, or topic raised in the review (optional — for targeted response)
  • Business context: Any internal context about the situation — was the issue resolved, is there a known product bug, was there a service failure (optional — helps craft an accurate response)
  • Batch mode: If responding to multiple reviews, provide them as a set for consistent tone and varied language
  • Response speed requirement: Whether the review needs an urgent response (crisis situation) or standard turnaround
  • Internal resolution status: Whether the issue has been fixed, is in progress, or is unresolved (for negative reviews — helps determine what to promise)

Process

  1. Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/dm:brand-setup)?" — or proceed with defaults.
  2. Apply brand voice settings: Load voice-and-tone guidelines and any channel-specific style rules for the review platform — review responses often require a warmer, more personal tone than other brand communications
  3. Classify review sentiment and severity: Categorize as positive (4-5 stars), neutral (3 stars), or negative (1-2 stars) — further classify negative reviews by severity level: minor complaint, service failure, product defect, or safety/legal issue
  4. For negative reviews: Acknowledge the specific concern by name, express genuine empathy without generic platitudes, take responsibility where appropriate, offer a concrete resolution path with specifics, and move the conversation offline with a direct contact method (email or phone)
  5. For positive reviews: Express sincere gratitude, reinforce the specific aspect the reviewer praised, add a personal or humanizing touch, and encourage continued engagement — mention related products, services, or referral programs where natural
  6. For neutral reviews: Acknowledge the balanced feedback, address any specific concerns raised with actionable detail, highlight relevant brand strengths without being defensive or dismissive, and invite further dialogue to improve their experience
  7. Check brand guidelines for approved response language: Verify the response against any restricted terms, required disclosures, legal disclaimers, or mandated response elements in the brand guidelines
  8. Apply platform conventions: Adjust response length, formatting, and tone for platform norms — Google (concise), Yelp (conversational), G2 (professional), TripAdvisor (hospitality-focused), etc.
  9. Score response for brand voice alignment: Evaluate the drafted response against brand voice parameters — tone, formality, warmth, and personality — and adjust until the response sounds authentically on-brand
  10. Check for common pitfalls: Ensure the response avoids defensiveness, blame-shifting, over-promising, disclosing private information, or using repetitive language across multiple review responses
  11. Optimize for SEO where applicable: On platforms where responses are indexed (Google, Yelp), naturally incorporate relevant keywords and business name without sounding forced
  12. Generate batch variations: If responding to multiple similar reviews, vary the language, structure, and opening to avoid templated-sounding responses that damage authenticity

Output

A structured review response package containing:

  • Ready-to-post review response: Primary response tailored to the platform's character limits, conventions, and audience expectations
  • Alternative versions: Formal and casual variants for flexibility, plus a shorter version if the primary response exceeds platform norms
  • Response guidelines: Platform-specific best practices applied — recommended length, optimal tone, ideal response timing, and SEO considerations
  • Escalation recommendation: For negative reviews — whether this requires manager involvement, legal review, product team notification, or immediate offline outreach
  • Response quality score: Brand voice alignment rating and checklist of best practices applied
  • Follow-up note: Suggested internal action items if the review reveals a systemic issue worth addressing
  • SEO keywords applied: For indexed platforms, keywords naturally incorporated into the response
  • Tone analysis: Breakdown of the response tone (empathetic, grateful, professional, warm) matched against brand voice settings
  • Response timing recommendation: Optimal window for posting the response based on platform algorithms and customer expectations
  • Template extraction: If the response is strong, a generalized template version saved for future similar reviews

Agents Used

  • content-creator — Response copywriting, tone calibration, personalization, platform-appropriate language, alternative version drafting
  • brand-guardian — Voice consistency enforcement, guideline compliance, restricted language checks, escalation assessment, legal sensitivity review

平台分布

Codex

35.02%
按下载量换算74

Claude

31.04%
按下载量换算66

Cursor

20.15%
按下载量换算43

Gemini CLI

9.65%
按下载量换算20

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。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