Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Review Manager

ASecurity

Manage online reviews — generation strategies, response playbooks, reputation monitoring, and turning reviews into growth.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgodocumentation

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill review-manager --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review Manager?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Review Manager
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-review-manager/badge)](https://www.skillsdirectory.com/skills/aicodedecode-review-manager)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: review-manager
description: Manage online reviews — generation strategies, response playbooks, reputation monitoring, and turning reviews into growth.
category: business-marketing
---

## Overview

Reviews are modern word-of-mouth: they drive local SEO, purchase decisions, and trust. This skill covers the full review practice — generating authentic reviews at scale, responding to positive and negative reviews, monitoring reputation across platforms, and using review insights to improve the business.


Reviews are the new word-of-mouth at scale: 90%+ of buyers read them, and star ratings directly move conversion. Review management is both defensive (responding to negatives, catching fake reviews) and offensive (generating authentic positives systematically). It is a compounding asset — every review works for you indefinitely.
## When to use

- Increasing review volume and ratings
- Responding to negative reviews
- Building a review generation system
- Monitoring brand reputation
- Improving local search via reviews
- Turning reviews into marketing assets

- Recovering from a negative review crisis
- Building review generation into the customer journey
- Monitoring brand sentiment across platforms
- Managing reviews across 100+ locations
- Responding to viral negative incidents
- Building review programs for B2B services
## Core concepts

**The review funnel.** Ask → make it easy → follow up → respond → showcase. Most happy customers never review unless asked; most unhappy ones review unprompted. Systematic asking corrects the negativity bias.

**Asking well.** Timing (right after positive moments: delivery, successful support, 5-star NPS), channel (email, SMS, in-app, in-person with QR codes), and simplicity (direct links to the right platform, no multi-step processes). Never incentivize with payments for positive reviews — it's against most platforms' policies and often illegal; you can incentivize honest reviews in some contexts, but check platform rules first.

**Response playbook.** Positive: thank personally, mention specifics, invite back. Negative: respond quickly (24–48h), empathize publicly, take resolution offline, follow up publicly when resolved. Never argue, never be defensive, never fake.

**Platform strategy.** Prioritize where your customers look: Google (local SEO + trust), industry-specific (e.g., G2/Capterra for software, TripAdvisor for hospitality), then secondary. Claim and complete every profile — unclaimed profiles collect unanswered complaints.

**Reputation monitoring.** Alerts for new reviews and mentions, sentiment tracking over time, competitor review benchmarking. Speed matters — a negative review unanswered for weeks signals indifference.

**Reviews as assets.** Showcase top reviews on site/social/ads (with permission where needed), mine reviews for messaging (customer language is copy gold), and feed recurring complaints to product/ops as improvement priorities.


**The review request moment.** Ask when satisfaction peaks: after delivery confirmation, after a resolved support ticket, after a milestone achieved in-product. Never ask after a complaint or a failed interaction. In-product prompts at the moment of delight convert 5–10x better than post-purchase emails.

**Responding to negatives (the HEARD method):** Hear them out (acknowledge specifically) → Empathize (genuine, not scripted) → Apologize where warranted → Resolve (offer a path forward) → Diagnose (fix the root cause). A thoughtful response to a 1-star review influences every future reader more than the review itself.

**Platform strategy.** Google (dominant for local), Yelp (influential, filtered aggressively), Facebook (social proof), industry-specific (TripAdvisor, Healthgrades, G2).
Prioritize by where your customers actually decide — not all platforms matter equally per vertical.
Claim and complete profiles everywhere relevant; optimize effort toward the top 2–3.
**Review velocity.** Steady streams beat bursts: 5–10 new reviews monthly per location sustains rankings and trust.
Systematize asks (post-transaction triggers) rather than campaigning sporadically.
Monitor velocity per location; stalled locations need intervention.
**Sentiment analysis.** Categorize feedback themes (service, product, price, staff) → track trends → route insights to operations.
Reviews are free market research — aggregate them into operational improvements.
Share positive themes with teams; recognition reinforces what works.
## Practical workflow

1. **Audit.** Current ratings per platform, review velocity, response rate and time, sentiment themes, competitor comparison. Find the gaps.
2. **Claim and optimize profiles.** Every relevant platform: complete info, photos, accurate hours/services, correct categories. Unclaimed profiles are reputation liabilities.
3. **Build generation systems.** Post-transaction email/SMS sequences (ask happy customers at the right moment), in-store QR codes, staff training (ask in person — highest conversion), and review links in receipts/follow-ups. Target steady velocity, not bursts.
4. **Respond systematically.** Daily monitoring, response SLA (24–48h), templates as starting points (personalize every response), escalation path for serious complaints, and a process for flagging fake/defamatory reviews.
5. **Showcase and leverage.** Review widgets on site, top reviews in ads and social, case studies from detailed reviews, and "you asked, we fixed" posts when reviews drive improvements.
6. **Analyze and improve.** Monthly: rating trends, sentiment themes, response metrics, competitor movement. Quarterly: feed top complaint themes to operations with data.

**Negative review response template:** acknowledge specifically → empathize genuinely → take it offline (name + direct contact) → resolve → follow up publicly. "We're sorry to hear about [specific issue]. This isn't the experience we want. I'm [name], [title] — please reach me at [contact] so I can make this right."


**Review generation system:** map the customer journey → identify 2–3 peak-satisfaction moments → build asks into those moments (in-product, email, SMS) → make leaving a review frictionless (direct links, no account creation) → thank reviewers personally → showcase reviews in marketing. Measure: review velocity, average rating trend, response rate, and response time.

**Crisis protocol:** negative review velocity spike → assess validity (real issue or attack?) → respond publicly with HEARD → fix root cause → follow up privately → if fake/coordinated, report with evidence. Never offer incentives for removing negative reviews — it violates most platforms' policies.

**Multi-location program:** centralized platform (monitoring, response templates, analytics) → location-level ownership (managers respond within 24h) → escalation paths (serious complaints to senior staff) → monthly scorecards per location.
Balance central efficiency with local authenticity — templated responses to everything feel robotic.
**Viral incident response:** assess scope and validity → respond publicly (acknowledge, empathize, commit to action) → take detailed discussion private → implement fixes → follow up publicly with resolution.
Speed matters, but accuracy matters more — verify facts before responding publicly.
## Common pitfalls

- **Never asking.** Relying on organic reviews guarantees negativity bias. Ask systematically.
- **Fake or incentivized positives.** Platform penalties, legal risk, and destroyed trust when exposed. Earn reviews honestly.
- **Arguing with reviewers.** Public defensiveness amplifies damage. Empathize and move offline.
- **Ignoring reviews.** Unanswered reviews — especially negative — signal you don't care. Respond to all negative, many positive.
- **Review gating.** Only soliciting from happy customers (against most platforms' policies). Ask everyone; fix what you learn.
- **Burst campaigns.** 50 reviews in a week then silence looks manipulated. Steady velocity wins.
- **Not acting on feedback.** Reviews revealing the same complaint for months with no fix. Close the loop operationally.
- **Incentivizing only positive reviews.** Asking only happy customers skews ratings and violates FTC/platform rules. Ask everyone; earn the positives.
- **Ignoring reviews.** Unanswered negatives signal indifference. Respond to 100% of negatives and a sample of positives.
- **Fighting fake reviews emotionally.** Public accusations backfire. Report through proper channels with documentation; respond professionally regardless.
- **Fake review panic.** Obsessing over competitors' suspicious reviews. Report with evidence, then focus on earning genuine reviews — authenticity wins long-term.
- **Ignoring positive reviews.** Only responding to negatives. Thanking positive reviewers builds loyalty and encourages more reviews.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →