A local-first UX research tool for Openclaw Skills that monitors interactions and provides actionable insights through automated observation and feedback.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawsight
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 clawsight 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 UXR Observer?
UXR Observer is a specialized research skill designed to sit within the Openclaw environment, functioning as an automated UX researcher. It bridges the gap between raw AI interactions and actionable user experience data by monitoring conversation patterns, task completion success, and user friction points. As part of the broader ecosystem of Openclaw Skills, it emphasizes a local-first privacy model where all captured data—including verbatim quotes and sentiment analysis—remains strictly on the user's local filesystem.
The skill is essential for developers and teams who need to understand exactly how an AI agent is performing in real-world scenarios without sacrificing data sovereignty. It uses a sophisticated mix of passive observation and active micro-surveys to build a comprehensive picture of the user journey, identifying where the agent excels and where it stumbles. By integrating UXR Observer into your workflow, you gain a transparent view into usage patterns, allowing for data-driven refinements to agent behavior and prompt engineering.
UXR Observer Use Cases
- Tracking AI agent task completion rates and success metrics across different coding or writing sessions.
- Identifying specific friction points where the AI agent repeatedly misunderstands or fails to meet user expectations.
- Collecting qualitative verbatim feedback to understand the emotional response and satisfaction levels of users.
- Generating comprehensive daily reports to audit agent performance and identify recurring technical hurdles.
- Providing transparent interaction logs for users who want to review their own usage patterns and productivity trends.
How UXR Observer Works
- On activation, the skill initializes a local directory structure to store session data and configuration files.
- During every interaction, an observer sub-agent captures metadata such as user intent, tool usage, and verbatim quotes.
- The system monitors for friction signals like repeated attempts or user corrections to tag sentiment and outcome.
- After each distinct task completion, the skill triggers a brief micro-survey to gather immediate satisfaction ratings.
- At the end of a session or day, a distiller agent aggregates all logs and survey responses into a structured Markdown report.
UXR Observer Setup
To get started with this addition to your Openclaw Skills library, follow these steps:
- Enable the skill within your agent configuration.
- On the first run, the skill will automatically create the necessary local storage:
mkdir -p ~/.uxr-observer/{sessions,reports}
touch ~/.uxr-observer/config.json
- The agent will provide a brief introductory message confirming that passive observation and micro-surveys are active.
- You can check the status at any time by asking the agent "What are you tracking?".
UXR Observer Data Schema & Taxonomy
The skill maintains a structured local database using JSONL for logs and Markdown for human-readable reports.
| File Path | Description | Data Type |
|---|---|---|
~/.uxr-observer/sessions/YYYY-MM-DD/observations.jsonl |
Continuous log of interactions, intent, and tool usage | JSONL |
~/.uxr-observer/sessions/YYYY-MM-DD/surveys.jsonl |
Verbatim user responses to post-task and daily surveys | JSONL |
~/.uxr-observer/reports/YYYY-MM-DD-daily-report.md |
Synthesized insights and thematic analysis | Markdown |
~/.uxr-observer/config.json |
User preferences, opt-out topics, and anonymous participant ID | JSON |
UXR Observer Advanced Features
- Verbatim Capture Policy: Automatically logs exact user language with interpretive headers for high-fidelity qualitative data.
- Multi-Agent Support: Spawns specialized Observer and Distiller sub-agents to handle background logging and report generation independently.
- Automated Friction Detection: Uses heuristics to identify repeated attempts or scope mismatches without manual tagging.
- Sentiment Analysis: Categorizes user emotions ranging from delighted to frustrated based on interaction context.
- On-Demand Reporting: Supports natural language commands to generate trends or email reports to specific recipients directly through Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Moltbot Arena
A comprehensive skill for building, controlling, and automating AI agents in the Moltbot Arena multiplayer programming environment.
Erotic Fiction Writer
An advanced AI creative writing tool designed to craft tasteful, high-quality adult fiction and intimate narratives.
OpenClaw Memory Fix
A sophisticated four-layer memory optimization system for AI agents featuring dynamic decay, semantic retrieval, and self-reflection capabilities.
OpenClaw Memory Fix Skill
A comprehensive memory management system for OpenClaw that enables AI agents to remember preferences, learn from errors, and maintain long-term context.
UXR Observer
An embedded UX research skill that performs ethnographic observation, satisfaction measurement, and automated cost tracking for AI agent interactions.
UXR Ethnographic Observer
An embedded ethnographic research tool that monitors interaction data and generates structured insights to optimize your OpenClaw experience.
Featured*
