An automated system for capturing user feedback and refining AI behavior based on task performance.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feedback-collector
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install feedback-collector using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Feedback Collector?
The Feedback Collector is a vital component of the Openclaw Skills ecosystem, designed to bridge the gap between AI execution and user satisfaction. By systematically prompting users for feedback after critical tasks—such as file operations, content generation, or configuration changes—it ensures that the agent learns from every interaction.
This skill transforms raw user reactions into actionable intelligence. It categorizes responses into success, improvement, or failure logs, allowing the AI to reinforce high-value patterns and pivot away from inefficient behaviors. It is an essential tool for developers and power users looking to build a truly adaptive and self-improving AI assistant.
Feedback Collector Use Cases
- Post-execution validation of complex file manipulations or directory restructuring.
- Quality assurance for AI-generated copy, code, or documentation.
- Verifying user satisfaction after the installation or configuration of new Openclaw Skills.
- Identifying recurring issues in agent logic to prioritize debugging and workflow refinement.
How Feedback Collector Works
- The skill triggers automatically upon the completion of significant tasks like file edits or system updates.
- It presents the user with a streamlined choice (A: Satisfied, B: Needs Improvement, C: Unsatisfied).
- If the user selects B or C, the collector triggers a secondary detailed survey to pinpoint specific issues (e.g., response length, incorrect execution).
- Successes are logged to a success pattern file to reinforce the current behavioral model.
- Failures or improvement suggestions are logged to error or preference files to prevent future mistakes.
- The system periodically analyzes these logs to generate trend reports and improvement strategies.
Feedback Collector Setup
To enable the Feedback Collector within your environment, ensure your agent has access to the memory directory and add the following configuration:
# Install the skill into your Openclaw directory
openclaw install feedback-collector
# Ensure the memory directory exists for logging
mkdir -p memory/
touch memory/feedback-log.md memory/error-log.md
Feedback Collector Data Schema & Taxonomy
The Feedback Collector organizes data chronologically to facilitate trend analysis and learning within Openclaw Skills.
| File Path | Purpose | Data Captured |
|---|---|---|
memory/feedback-log.md |
Success & Improvement Log | Timestamps, task type, satisfaction status, and adjustment notes. |
memory/error-log.md |
Failure Repository | Critical failures, path errors, and formal apologies/remediation steps. |
memory/user-preferences.md |
Behavioral Model | Refined settings like 'short mode' or 'pre-execution confirmation'. |
Feedback Collector Advanced Features
- Weekly automated feedback analysis reports focusing on satisfaction trends and common pain points.
- Contextual preference updating that automatically modifies agent system prompts based on user 'Needs Improvement' triggers.
- Multi-agent memory sharing, allowing different Openclaw Skills to benefit from a centralized feedback loop.
- Support for custom feedback templates tailored to specific technical workflows.
SKILL.md
Loading
Related Openclaw Skills
Memory Landscape Review
A specialized tool for auditing AI memory layers to ensure context clarity and promote durable project instructions.
Tomba Contact Intelligence
Automate contact discovery, email verification, and company research directly within your AI agent workflows.
WeShop AI Image & Fashion Generation
A professional AI-driven suite for e-commerce image generation, featuring model replacement, virtual try-ons, and product background editing.
cyber-taoist
An evolutionary analysis framework that applies a five-element model to multi-scale decision-making for AI agents and developers.
Online Video Editor AI
An AI-powered video editing assistant that transforms plain language descriptions into polished, production-ready video content via cloud-based rendering.
Steam Icon Fixer
A specialized utility to restore and automate the installation of missing Steam game icons on Linux desktop environments.
Featured*
