An automated AI agent skill that aggregates and analyzes user feedback across platforms to extract actionable product improvement signals.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install user-feedback-claw
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install user-feedback-claw using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
User Feedback Claw is a professional-grade analytical tool designed for product managers and customer success teams to transform raw, fragmented customer voices into strategic insights. As a specialized component within the Openclaw Skills ecosystem, it bridges the gap between customer noise and product roadmaps by using advanced NLP to categorize issues, evaluate sentiment, and prioritize development tasks based on empirical evidence.
This skill excels at processing large volumes of data from App Stores, e-commerce platforms, and internal support systems. By synthesizing unstructured feedback into structured reports, it helps teams identify high-impact pain points and validate product decisions with actual user data, ensuring that every improvement is backed by the voice of the customer.
To deploy this skill within your environment, ensure you have the necessary reference taxonomies configured.
# Navigate to your agent's skills directory
cd openclaw-agent/skills
# Clone or download the user-feedback-claw repository
git clone https://github.com/openclaw/user-feedback-claw.git
# Ensure your references folder contains the required lexicons
# references/sentiment-lexicon.md
# references/issue-taxonomy.md
# references/improvement-templates.md
Once installed, you can trigger the analysis by providing a data file and asking your agent to perform a feedback audit using Openclaw Skills capabilities.
The skill organizes processed feedback into a structured taxonomy to ensure consistent reporting across different data sources.
| Attribute | Description | Data Type |
|---|---|---|
| feedback_content | The primary raw text provided by the user | String |
| sentiment_intensity | Calculated strength of positive or negative emotion | Float |
| issue_category | Classification (e.g., Quality, Logistics, CS, Price, UX) | Enum |
| priority_score | Weighted score (Frequency x Sentiment x Rating Impact) | Decimal |
| user_segment | Labels for high-value users, KOLs, or VIPs if available | String |
| action_item | Automatically generated improvement suggestion | Markdown |
Loading
A decisive AI dining companion that automates meal planning and restaurant discovery through smart logic and map integrations.

A powerful batch video transcription tool supporting over 1000 websites with GPU-accelerated speech-to-text and structured note generation.

A sophisticated memory assistant designed to organize, store, and recall vital information through a networked knowledge base.

An AI-powered assistant for developing, backtesting, and optimizing quantitative trading strategies using Python and industry-standard frameworks.

A comprehensive tool designed to help developers manage profiles, bid on projects, and secure remote work opportunities on the Proginn platform.

An AI-powered video marketing framework for coaching firms and L&D consultants to create high-authority content that converts enterprise decision-makers.








































