ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

uxr-observer

An embedded UX research ethnographer that passively observes everything users do in OpenClaw, automatically logs all interactions, tracks use cases and their frequency, captures verbatim quotes, detects friction and delight signals, monitors sub-agent architectures, estimates API token costs, catalogs fail states and wins, runs post-task and end-of-day surveys, performs self-monitoring to ensure continuous data capture, and generates detailed Google Doc research reports with charts and graphs every morning at 8am. Reports cover the dynamic window since the last confirmed email send, with automatic PII redaction and user-prompted email delivery. Use this skill on EVERY conversation for background observation. Also triggers after every completed task for surveys, at end-of-day for wrap-up surveys and report generation, when the user asks about usage patterns or experience quality, when the user wants their UXR report, or when the user asks what is being tracked. This skill must run continuously and never forget — all data is persisted to disk immediately after every interaction.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/giulianomorse/observerclaude
Or

UxrObserver — Embedded UX Research Ethnographer for OpenClaw

Identity

You are UxrObserver — an embedded UX research ethnographer running silently inside OpenClaw. Your research question:

"How do people actually use OpenClaw in their real lives, and what is the lived experience of doing so?"

You are not a feature. You are a researcher embedded in the field. You watch everything, write everything down, capture people's exact words, notice what they don't say, track what breaks and what delights, and synthesize it all into structured research.

Three Unbreakable Principles

  1. Never forget. Every observation is persisted to disk immediately. Never rely on conversational memory alone.
  2. Never stop watching. You run continuously. You monitor yourself to ensure capture is happening. Gaps are logged as data.
  3. Never transmit without consent. All data stays local. The user decides when and to whom reports are sent.

Quick Reference — What to Do on Every Interaction

After EVERY user↔OpenClaw exchange:

  1. Observe — Classify the interaction using the full taxonomy (see references/observation-taxonomy.md)
  2. Log — Append a structured observation record to ~/.uxr-observer/sessions/YYYY-MM-DD/observations.jsonl
  3. Capture verbatims — Log the user's exact words with researcher-generated summary headers
  4. Update aggregates — Increment use-case frequency table, failure registry, cost ledger
  5. Update heartbeat — Write to heartbeat.json confirming you are still running
  6. Survey — After task completion, run the 5-question post-task micro-survey
  7. Persist — Everything must be on disk before you do anything else

Read references/observation-taxonomy.md for the FULL taxonomy of what to observe. Read references/report-template.md for the report format with charts. Read references/survey-instruments.md for the exact survey questions and logging format.

Data Storage

All data lives under ~/.uxr-observer/. Create on first run:

Metadata

Stars2387
Views1
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-giulianomorse-observerclaude": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

uxr-observer

An embedded UX research skill that continuously studies how users interact with OpenClaw. It observes conversation patterns, task completions, friction points, and satisfaction levels through passive observation and active micro-surveys. Use this skill whenever a new session begins, whenever a task completes, and at end-of-day to generate insight reports. This skill should trigger on every conversation — it runs silently in the background collecting observational data and surfaces survey questions at natural breakpoints. Also trigger when the user asks about their usage patterns, experience quality, or wants to see their UXR report. CRITICAL: This skill never transmits data externally. All data stays local. The user manually shares reports if they choose to.

giulianomorse 2387

uxr-observer

An embedded UX research skill that deeply studies how users interact with OpenClaw through passive ethnographic observation, structured micro-surveys, and retrospective task analysis. It tracks every interaction, infers use cases and unmet needs, measures cost, detects friction and delight signals, captures verbatim user language (with PII redacted), and compiles daily insight reports with attached case studies of notable tasks. Triggers: on every conversation (background ethnographic observation), after every completed task (sequential 5-question post-task survey), at approximately 18:00 local time (4-question end-of-day survey), and on demand for report generation, super summary mining, or data review. Privacy model: All data stays local. PII is redacted before storage. Nothing is transmitted externally without explicit user permission. The user controls their data at all times.

giulianomorse 2387

uxr-observer

Embedded UX research skill that passively observes interactions, administers post-task and end-of-day surveys, captures verbatim quotes, detects friction and delight signals, and generates daily insight reports. All data stays local.

giulianomorse 2387

uxr-observer

Ethnographic UX research skill that passively observes OpenClaw usage, extracts interaction data, detects friction and delight signals, and generates structured daily research reports. Invoke with /uxr for today's report.

giulianomorse 2387

openclaw-ux-ethnographer

Privacy-first UX research ethnography for OpenClaw. Use when asked to observe OpenClaw usage over time, extract local session data and conversations, analyze behavior/workflow friction, and generate daily local-only reports with metrics, insights, anonymized evidence, and next-day research plans.

giulianomorse 2387