Skip to content
Agentmart
Submit a tool

explore-curiosity

在空闲时像朋友随口一问,了解用户偏好和生活化信息

Skill by hazewarm

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hazewarm-explore-curiosity

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

在空闲时像朋友随口一问,了解用户偏好和生活化信息

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/explore-curiosity

What's inside

Skill name
explore-curiosity
Description
在空闲时像朋友随口一问,了解用户偏好和生活化信息
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## 目标

在没有 RSS 新闻可推送的空闲时段,基于长期记忆提出一个轻量自然的问题,
慢慢补全用户画像中的生活化空白。

## 工作文件

- skills/explore-curiosity/queue.md:待问的问题列表,每行一个问题

## 工作流程

1. read_file skills/explore-curiosity/queue.md
2. 如果文件不存在或为空:
   a. recall_memory 检索用户长期记忆(搜索"兴趣""日常""偏好"等词)
   b. 基于记忆中的空白,生成 5 个轻量问题,write_text_file 写入 queue.md
   c. 取第一行作为本轮问题
3. 如果 queue.md 非空,取第一行
4. message_push 发送该问题
5. edit_file 删除 queue.md 中已发送的那一行(或 write_text_file 写回剩余行)
6. finish_drift(skill_used="explore-curiosity", one_line="推送了:{问题摘要}", next="队列剩余 N 题", message_result="sent")

## 要求

- 问题必须轻量、自然、像朋友随口一问,不超过 30 字
- 优先问:音乐偏好、开源项目、运动习惯、食物口味、日常消遣、最近在看什么
- 禁止问太大太虚的问题(如"你的人生目标是什么")
- 避开长期记忆里已经明确有答案的信息
- 队列为空时先生成问题再发送,不要空手 finish_drift
- finish_drift.message_result 必须是 "sent"(本轮一定发了消息)
- 本轮只发一问,发完即结束,不要等待或确认用户是否回复——每次 drift 运行是独立的,下次运行自然会取队列中的下一题

From hazewarm/raven-agent, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jun 27, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hazewarm

Cite this page

explore-curiosity skill. Agent Mart. https://agentmart.dev/skills/hazewarm-explore-curiosity (last updated 2026-10-24)