review-response

GitHub

用于撰写客户评论回复的AI技能,支持正面、负面及混合评价。提供个性化回复、简短版本及通用模板,旨在维护品牌形象、安抚客户并吸引潜在买家,同时确保语气得体且不泄露隐私。

exports/openclaw/review-response/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

回复客户评论 处理差评或1星评价 管理线上店铺评价 生成回复模板

Install

npx skills add mohitagw15856/pm-claude-skills --skill review-response -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/review-response -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@review-response

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill review-response -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "review-response",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/review-response.html",
    "metadata": {
        "openclaw": {
            "emoji": "🛒"
        }
    },
    "description": "Write the right reply to a customer review — positive, negative, or mixed. Use when asked to respond to a review, reply to a bad\/1-star review, handle online reviews, or write review-response templates. Produces tailored, on-brand responses that thank advocates, de-escalate and resolve complaints, and read well to the *future* shopper who's reading them — plus reusable templates."
}

Review Response Skill

Reviews are read by the next buyer, not just the reviewer — so a reply is public customer service and marketing at once. A good response thanks genuinely, takes ownership without being defensive, moves the heat to a private channel, and shows future shoppers you're a business that cares. This skill writes that reply for the review in front of you, and gives you templates for next time.

Working from a brief

Given a review (or just "reply to a 1-star about late delivery"), write the full response anyway — infer a reasonable, on-brand reply and a fair resolution, marking specifics (confirm/insert) (order details, the exact remedy). Never invent facts about what happened; never argue with the customer in public.

Required Inputs

Ask for these only if they aren't already provided (else infer and label):

  • The review — the text, the rating, and where it's posted (Google, Amazon, Trustpilot, app store…).
  • What happened — your side/context if known, and whether it's resolved.
  • Brand voice — warm/formal/playful, and the name you sign off with.
  • What you can offer — any remedy you're willing to make (refund, replacement, discount, fix).

Output Format

Review Response

  • Read — a one-line read of the review: sentiment, the real issue, and whether it's fixable.
  • The reply — a ready-to-post response that:
    • Opens by addressing them by name and thanking them for the feedback.
    • For positive: echoes the specific thing they loved, adds a little brand warmth, and invites them back (no hard sell).
    • For negative/mixed: acknowledges the specific problem, takes ownership (no excuses/blame), apologises sincerely, states what you'll do, and moves to a private channel for resolution.
    • Closes human and signed.
  • Short version — a tighter variant for platforms with length limits.
  • Templates — reusable patterns for the common cases (5★ thanks, shipping issue, product fault, sizing/fit, wrong expectations) with [brackets] to fill.

Keep negative replies calm and brief — the audience is the next shopper.

Quality Checks

  • Addresses the reviewer by name and references the specific point they raised
  • Negative replies take ownership without excuses or blaming the customer
  • Complaints are moved to a private channel for the actual resolution
  • Tone matches the brand and stays calm — never defensive or sarcastic
  • Positive replies add warmth without a pushy upsell
  • No private data is exposed; invented specifics are flagged to confirm

Anti-Patterns

  • Do not get defensive or argue facts in public — you're writing for the next shopper, not to win
  • Do not paste an identical canned reply on every review — personalise to the specific point
  • Do not expose order numbers, emails, or other private details in a public reply
  • Do not over-apologise or grovel on a minor issue, or under-respond on a serious one — match the severity
  • Do not bribe for removal or incentivise changing the review in ways the platform forbids

Based On

Online reputation & customer-service practice — specific, ownership-led public responses, private-channel resolution, and audience-aware (next-shopper) tone.

Version History

  • 54fad50 Current 2026-07-19 12:31

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
92c722fe
Indexed
2026-07-19 12:31

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 16:58
浙ICP备14020137号-1 $방문자$