OpenClaw

pref0

Learn user preferences from conversations and personalize responses automatically. Preferences compound over time — corrections like "use TypeScript, not JavaScript" are captured and injected into future sessions.

fliellerjulian0 来源安装数☆ 0 仓库 Starsv1.0.0

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install fliellerjulian/pref0

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

pref0 — Preference Learning for AI Agents

You have access to the pref0 API. It learns user preferences from conversations and serves them back at inference time. The more conversations you track, the better it gets.

When to use this skill

After a conversation ends → Track it

After finishing a conversation (or at natural breakpoints), send the messages to pref0 so it can extract preferences. This is especially valuable when the user corrects you (e.g., "use pnpm, not npm") or states explicit preferences (e.g., "always use metric units").

Before responding to a user → Fetch their preferences

Before generating a response, fetch the user's learned preferences and follow them. This prevents the user from having to repeat themselves across sessions.

API Reference

Base URL: https://api.pref0.com Auth: Authorization: Bearer $PREF0_API_KEY

Track a conversation (POST /v1/track)

Send a conversation so pref0 can learn from it. It extracts corrections, explicit preferences, and behavioral patterns automatically.

curl -X POST https://api.pref0.com/v1/track \
  -H "Authorization: Bearer $PREF0_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "userId": "<user-id>",
    "messages": [
      { "role": "user", "content": "Help me set up a new project" },
      { "role": "assistant", "content": "Here is a project using npm and JavaScript..." },
      { "role": "user", "content": "Use pnpm, not npm. And TypeScript." },
      { "role": "assistant", "content": "Updated to pnpm and TypeScript..." }
    ]
  }'

Response:

{
  "messagesAnalyzed": 4,
  "preferences": { "created": 2, "reinforced": 0, "decreased": 0, "removed": 0 },
  "patterns": { "created": 1, "reinforced": 0 }
}

The response tells you how many messages were processed (messagesAnalyzed) and exactly what changed: created (new preference learned), reinforced (existing preference seen again, confidence increased), decreased (user retr...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/fliellerjulian/pref0
Version: 1.0.0
Commit: 0fb5c046213e771a3a38167a9db7a3351f60e7ef
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# pref0 — Preference Learning for AI Agents

You have access to the pref0 API. It learns user preferences from conversations and serves them back at inference time. The more conversations you track, the better it gets.

## When to use this skill

### After a conversation ends → Track it

After finishing a conversation (or at natural breakpoints), send the messages to pref0 so it can extract preferences. This is especially valuable when the user **corrects** you (e.g., "use pnpm, not npm") or states explicit preferences (e.g., "always use metric units").

### Before responding to a user → Fetch their preferences

Before generating a response, fetch the user's learned preferences and follow them. This prevents the user from having to repeat themselves across sessions.

## API Reference

**Base URL:** `https://api.pref0.com`
**Auth:** `Authorization: Bearer $PREF0_API_KEY`

### Track a conversation (POST /v1/track)

Send a conversation so pref0 can learn from it. It extracts corrections, explicit preferences, and behavioral patterns automatically.

```bash
curl -X POST https://api.pref0.com/v1/track \
  -H "Authorization: Bearer $PREF0_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "userId": "<user-id>",
    "messages": [
      { "role": "user", "content": "Help me set up a new project" },
      { "role": "assistant", "content": "Here is a project using npm and JavaScript..." },
      { "role": "user", "content": "Use pnpm, not npm. And TypeScript." },
      { "role": "assistant", "content": "Updated to pnpm and TypeScript..." }
    ]
  }'
```

**Response:**
```json
{
  "messagesAnalyzed": 4,
  "preferences": { "created": 2, "reinforced": 0, "decreased": 0, "removed": 0 },
  "patterns": { "created": 1, "reinforced": 0 }
}
```

The response tells you how many messages were processed (`messagesAnalyzed`) and exactly what changed: `created` (new preference learned), `reinforced` (existing preference seen again, confidence increased), `decreased` (user retr...

搜索