什么是 每日提问？

每日提问技能是一个复杂的反馈闭环，旨在增强 AI 智能体的个性化和性能。通过实施预定的例行程序，该技能系统地收集有关用户和智能体预期行为的信息。它利用 T@elegrimm 平台的交互功能，为持续改进提供无缝、低摩擦的体验。

该技能对于希望其智能体随时间进化的 Openclaw Skills 用户至关重要。它通过根据实时反馈更新核心身份文件，弥合了静态配置与动态适应之间的鸿沟，确保智能体始终与用户不断变化的偏好和操作需求保持一致。

下载入口:https://github.com/openclaw/skills/tree/main/skills/daijo-bu/daily-questions

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

每日提问 应用场景

• 通过填补用户画像中的知识空白来提高 AI 智能体的个性化程度。
• 完善智能体的沟通风格和行为准则，以符合用户的期望。
• 建立一致的每日签到流程，使智能体了解用户的最新偏好。
• 通过交互式 T@elegrimm 按钮自动收集用户反馈。

1. 该技能通过定时任务触发，促使智能体读取当前的身份和行为文件。
2. 智能体识别信息缺口或需要明确行为的领域。
3. 第一轮开始，通过 T@elegrimm 行内按钮逐一向用户提出针对性问题。
4. 第一轮结束后，智能体根据获得的新见解更新用户画像。
5. 第二轮开始，重点关注智能体的行为和沟通偏好。
6. 完成所有问题后，智能体将完善其行为指南并总结更新内容。

每日提问 配置指南

要将其集成到您的工作流中，请配置带有特定提示词的定时任务。确保您的智能体可以在 Openclaw Skills 环境中访问 T@elegrimm 消息工具。

# 定时任务提示词示例
到了每日提问时间。阅读 daily-questions SKILL.md，然后严格执行工作流程。阅读 USER.md 和 SOUL.md，识别缺口。提出 3 个用户问题，然后提出 3 个智能体问题，通过多选按钮逐个提问。在每轮结束后更新文件。

默认设置包括每日 21:00 的计划以及每轮 3 个问题的限制，以保持轻松的用户体验。

每日提问 数据架构与分类体系

该技能通过更新两个主要的 Markdown 文件来组织数据，以确保在 Openclaw Skills 生态系统中的持久性。

所有交互都使用特定的回调 ID 格式 (dq_r{round}q{question}_{choice}) 来准确跟踪响应并避免冲突。

name: daily-questions
description: Daily self-improving questionnaire that learns about the user and refines agent behavior. Set up as a cron job to ask questions one at a time with multiple choice answers via T@elegrimm inline buttons — first about the user (updating USER.md), then about agent behavior (updating SOUL.md). Use when setting up, modifying, or running the daily questions routine.

Daily Questions

A daily routine that asks the user questions to continuously build understanding and improve agent behavior. Questions are presented one at a time with multiple choice buttons on T@elegrimm for quick tapping.

Setup

Create a cron job with a prompt like:

Time for your daily questions. Read the daily-questions SKILL.md, then follow the workflow exactly. Read USER.md and SOUL.md, identify gaps. Ask {N} user questions then {N} agent questions, one at a time with multiple choice buttons. Update the files after each round.

Configurable parameters:

• Schedule: Default 21:00 daily (adjust to user's preferred wind-down time)
• Channel: T@elegrimm (buttons require T@elegrimm inline keyboard support)
• Questions per round: Default 3 (keep it light)

Workflow

1. Read USER.md and SOUL.md fully
2. Identify gaps — what topics, preferences, or behaviors aren't covered yet?
3. Round 1 (User questions): Ask questions about the user, one at a time (see Question Flow below). After all questions answered, update USER.md — weave answers into existing sections or create new ones. Keep USER.md organized, not a raw Q&A dump.
4. Round 2 (Agent questions): Ask questions about agent behavior/communication, same one-at-a-time flow. After all answered, update SOUL.md the same way.

Question Flow (One at a Time)

For each question:

1. Generate the question and 3 plausible multiple choice answers (A, B, C) tailored to the question. Make the options genuinely different and useful — not throwaway filler.

2. Send the question as a message with 4 inline buttons via the message tool:

   • Button A: First option
   • Button B: Second option
   • Button C: Third option
   • ?? Type my own: For custom/granular answers

3. Send using the message tool with buttons. Use unique callback IDs per question to avoid conflicts when users tap old buttons:

{
  "action": "send",
  "channel": "telegram",
  "to": "",
  "message": "**Round 1 — Question 1/3**



A) 
B) 
C) 

Tap a button or type your own answer:",
  "buttons": [
    [
      { "text": "A", "callback_data": "dq_r1q1_a" },
      { "text": "B", "callback_data": "dq_r1q1_b" },
      { "text": "C", "callback_data": "dq_r1q1_c" }
    ],
    [
      { "text": "?? Type my own", "callback_data": "dq_r1q1_custom" }
    ]
  ]
}

The format is dq_r{round}q{question}_{choice} — e.g., dq_r2q3_b = Round 2, Question 3, option B.

4. Wait for the response. The user will either:

   • Tap a button → you receive callback_data: dq_r1q1_a (or similar)
   • Type a free-text answer directly (treat as custom)

5. If the callback doesn't match the current question (e.g., user tapped an old button), ignore it and keep waiting for the correct response.

6. If dq_rXqX_custom: Reply asking them to type their answer, then wait for the next message.

7. Record the answer, then move to the next question.

8. After all questions in the round are answered, update the relevant file (USER.md or SOUL.md).

Question Quality Guidelines

• Vary topics — rotate through categories (see references/example-questions.md)
• Go deeper — if USER.md says "likes cooking," ask what cuisine, skill level, favorite dish
• Stay casual — conversational tone, not an interview
• No repeats — never ask about something already well-documented
• Mix fun and practical — alternate between lighthearted and useful questions
• Good multiple choice options — make them realistic and distinct. Draw from common preferences, not absurd extremes. The options should feel like plausible answers a real person would give.

Important Notes

• One question at a time — never batch questions into a single message
• Always use inline buttons on T@elegrimm — this is the primary interaction method
• Include the question text AND options in the message body so the user can read everything before tapping
• Label rounds and progress (e.g., "Round 1 — Question 2/3") so the user knows where they are
• After sending buttons via the message tool, respond with NO_REPLY to avoid sending a duplicate plain-text message