本文へスキップ
TakoAPI
スキル一覧に戻る

pref0

fliellerjulian 作

Web & Frontend Development
1.2kダウンロード数はclawskills.shが公開している値です
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Learn user preferences from conversations and personalize responses automatically.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

User asks: Help me scaffold a new web project

エージェント
  1. 1

    Fetch preferences via GET /v1/profiles/{userId}?minConfidence=0.5

  2. 2

    Append the returned prompt field to the system prompt

  3. 3

    Generate scaffold using the learned preferences (TypeScript, pnpm, Tailwind)

  4. 4

    After session ends, call POST /v1/track with the full message history

  5. 5

    pref0 extracts any new corrections or preferences and updates confidence scores

出力

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

要件

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

インストール

clawhub install fliellerjulian/pref0

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク