LaunchKit · 2026
Back to Skills

Learn user preferences from conversations and personalize responses automatically.

0
1.2k downloads
by @fliellerjulian

Setup & Installation

openclaw skills install @fliellerjulian/pref0

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install pref0

Version History

v1.0.1Feb 9, 2026 - Version note by skill developer:

pref0 1.0.1 - Improved API documentation to clarify track and profile endpoints, including more detailed response fields for conversation tracking. - Added a ready-to-use prompt field to the profile API response for easier system prompt integration. - Now, the profile endpoint (`GET /v1/profiles/:userId`) returns the `prompt` directly alongside learned preferences and patterns. - Created notes.txt file (contents not specified in this changelog).

What This Skill Does

pref0 learns user preferences from conversation history and injects them into future sessions automatically. Corrections like "use pnpm, not npm" are extracted, scored by confidence, and served back via a ready-to-use system prompt string. Preferences compound across sessions as the same signals repeat.

Instead of manually maintaining a preferences file or re-stating preferences each session, pref0 extracts and scores them automatically from natural conversation corrections.

When to use it

  • Stop repeating tooling preferences to an AI agent every session
  • Capture corrections mid-conversation and apply them going forward
  • Inject personalized context into agent system prompts at inference time
  • Reset a user's preference profile on request or account deletion
  • Build multi-user AI apps where each user gets personalized defaults

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Help me scaffold a new web project

AGENT
  1. 1Fetch preferences via GET /v1/profiles/{userId}?minConfidence=0.5
  2. 2Append the returned prompt field to the system prompt
  3. 3Generate scaffold using the learned preferences (TypeScript, pnpm, Tailwind)
  4. 4After session ends, call POST /v1/track with the full message history
  5. 5pref0 extracts any new corrections or preferences and updates confidence scores
OUTPUT

Scaffolded project matches user's known preferences without any explicit instruction; new corrections from the session are stored for next time

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

PREF0_API_KEY environment variablepref0 account (sign up at pref0.com/signup)