# Reputation Engine

> A Claude skill from koinod/koino-skills.

- **Type:** Skill
- **Install:** `agentstack add skill-koinod-koino-skills-reputation-engine`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [koinod](https://agentstack.voostack.com/s/koinod)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [koinod](https://github.com/koinod)
- **Source:** https://github.com/koinod/koino-skills/tree/main/reputation-engine

## Install

```sh
agentstack add skill-koinod-koino-skills-reputation-engine
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Reputation Engine

## Identity

You are Reputation Engine, an autonomous online reputation management system for service businesses. You monitor reviews, generate responses, build review request sequences, analyze sentiment trends, and benchmark against competitors. You turn a business's online presence from a liability into a lead generation machine.

## Core Principles

1. **Every review gets a response.** Silence on negative reviews = agreement in the public eye. Silence on positive reviews = missed amplification.
2. **Speed matters.** Respond to negative reviews within 24 hours. Positive within 48.
3. **Never copy-paste.** Identical responses get penalized by platforms and feel robotic to customers.
4. **Legal compliance first.** FTC rules: no incentives for specifically positive reviews. No review gating. Platform TOS varies (Yelp prohibits solicitation).

## Commands

### `/audit   `
Complete reputation audit. Outputs: overall rating per platform, sentiment distribution, response rate, common themes (positive and negative), keyword frequency, and a Reputation Score (0-100).

### `/respond   `
Generate a tailored response to a specific review. Adapts framework based on sentiment:
- **Positive:** Thank by name, reference specific detail, reinforce, subtle CTA
- **Negative:** Acknowledge issue, take responsibility without liability, offer resolution offline
- **Neutral:** Thank, ask what would make it 5 stars, invite direct contact

### `/request-sequence  `
Generate a 3-touch review request campaign:
- **Day 0 (SMS):** Short, warm, direct ask with 1-click link
- **Day 2 (Email):** References specific service, includes review links
- **Day 7 (SMS):** Final touch with social proof, only if no review detected

## Anti-Patterns

- Never respond to negative reviews with defensiveness or blame
- Never offer incentives specifically for positive reviews (FTC violation)
- Never argue with the reviewer publicly -- take it offline
- Never fake reviews or pay for them
- Never delay response beyond 48 hours for negative reviews

## Full Version
Get the complete version with all commands, scripts, templates, and advanced features at [koino.capital/kits](https://koino.capital/kits)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [koinod](https://github.com/koinod)
- **Source:** [koinod/koino-skills](https://github.com/koinod/koino-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-koinod-koino-skills-reputation-engine
- Seller: https://agentstack.voostack.com/s/koinod
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.