What makes Review Analysis notable?

2.4K downloads. Trust evidence available

How should Review Analysis be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Review Analysis

Analyze customer reviews, complaints, and feedback to find repeat patterns, likely root causes, and action priorities. Use when teams need to cluster complai... Skill: Review Analysis Owner: leooooooow Summary: Analyze customer reviews, complaints, and feedback to find repeat patterns, likely root causes, and action priorities. Use when teams need to cluster complai... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-26T07:46:56.626Z | user Upgrade internals with clearer clustering, root-cause logic, and decision-ready outputs v1.0.0 | 2026-03-13T02:16:23.274Z | user Ini

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.4k

Updated

Oct 9, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.4K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.4K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.1release · observed Mar 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:review-analysis

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-review-analysis/snapshot"

Documentation

CLAWHUB

9,777 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: review-analysis
description: Analyze customer reviews, complaints, and feedback to find repeat patterns, likely root causes, and action priorities. Use when teams need to cluster complaints, separate product issues from messaging issues, identify purchase drivers or refund triggers, and turn messy review data into a concise decision-ready report.
---

# Review Analysis

Turn messy reviews, complaints, and feedback into a short decision memo the team can actually act on.

This skill is not just for “summarizing reviews.”

Its real job is to help answer:
- **What are people repeatedly saying?**
- **What problems are actually frequent vs just loud?**
- **Is the issue in the product, the messaging, the offer, shipping, or support?**
- **What should the team fix first?**
- **What can marketing, product, ops, and support each learn from the feedback?**

## Solves

Review data is usually noisy and operationally useless in raw form:
- hundreds of comments, but no pattern hierarchy;
- teams confuse anecdotes with repeat problems;
- product issues get mixed with bad expectation-setting;
- strengths are underused because nobody clusters positive themes;
- support, product, and growth teams all read the same reviews differently;
- no one translates feedback into action priorities.

Goal:
**Turn unstructured feedback into pattern clusters, likely causes, and recommended next steps.**

## Use when

Use when the user needs structured insight from customer feedback rather than a raw summary.

Typical cases:
- summarizing product reviews from marketplaces or app stores;
- clustering repeated complaints;
- identifying refund / return drivers;
- extracting product strengths and buyer-loved features;
- separating product quality issues from messaging or expectation mismatch;
- turning review data into FAQ, copy, product, or support actions;
- preparing a concise report for product, ops, CX, or marketing teams.

## Do not use when

Do not use this skill when:
- the user only wants sentiment labels with no explanation;
- the task is broad social listening across the public web rather than a defined feedback set;
- there is too little review data to identify meaningful patterns;
- the user wants rigorous statistical causality rather than directional pattern analysis;
- the task is support ticket workflow automation rather than insight extraction.

## Inputs

Ask for the minimum useful analysis set:
- review source(s)
- product / service name
- review text or feedback sample
- date range, if relevant
- market / platform, if relevant
- whether focus should be on complaints, positives, refunds, retention, or all feedback
- any business question to prioritize

## Workflow

### 1. Define the review set
Clarify what is being analyzed:
- marketplace reviews
- app reviews
- support complaints
- refund / return notes
- post-purchase survey responses
- social comments collected into a feedback set

### 2. Normalize and cluster the feedback
Group feedback into useful bu

_meta.json

{
  "ownerId": "kn70fv0ehp50emedet9tx3fekd82pw3b",
  "slug": "review-analysis",
  "version": "1.0.1",
  "publishedAt": 1774511216626
}

references/output-template.md

# Review Analysis Output Template

## Top patterns
1. 
2. 
3. 

## Evidence snippets
- 
- 

## Likely root causes
- 

## Recommended actions
- Fix now:
- Monitor:
- Messaging changes:

skill-card.md

## Description:

Analyzes customer reviews, complaints, and feedback to identify repeated patterns, likely root causes, and prioritized actions.

This skill is ready for commercial/non-commercial use.

## Publisher:

[leooooooow](https://clawhub.ai/user/leooooooow)

### License/Terms of Use:

MIT-0

## Use Case:

External product, operations, customer experience, and marketing teams use this skill to turn defined review or feedback sets into ranked patterns, likely root causes, and next actions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Review datasets may contain sensitive personal data.

Mitigation: Avoid providing sensitive personal data unless the user intends the agent to process it as part of the review analysis.

Risk: Root-cause findings are directional pattern analysis rather than rigorous statistical causality.

Mitigation: Use the skill's confidence, frequency, severity, and evidence snippets to review recommendations before acting on them.

## Reference(s):

- [Review Analysis Output Template](references/output-template.md)
- [ClawHub Skill Page](https://clawhub.ai/leooooooow/skills/review-analysis)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Markdown decision report]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes ranked patterns, short evidence snippets, likely root causes, severity or urgency, recommended actions, and optional positives worth amplifying.]

## Skill Version(s):

1.0.1 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 8h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.