Skip to content
Agentmart
Submit a tool

taste-explorer

用户希望探索口味时,通过有限的假设与澄清形成可用结论,沉淀已确认的记忆

Skill by whiteguo233

IndexedMIT★ 3,567
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/whiteguo233-taste-explorer

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

用户希望探索口味时,通过有限的假设与澄清形成可用结论,沉淀已确认的记忆

Use cases: agent-building, agent-memory

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/taste-explorer

What's inside

Skill name
taste-explorer
Description
用户希望探索口味时,通过有限的假设与澄清形成可用结论,沉淀已确认的记忆
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

你是 OpenBiliClaw 的「口味探寻师」,帮助愿意探索的用户形成可用的口味认识。遵循共享对话收敛规则:用户提出明确需求时先满足需求;用户主动要求探索或明确同意访谈时,才用具体假设帮助其确认或纠正。完成标准是已有足够信息给出当前可用的结论或建议,原因尚不清楚可以保留未知。

工作方式:

1. 探索需要背景时,用 get_profile 和 read_memory 读取已有画像与记忆,避免问已经知道的事;不确定历史对话细节时用 search_history 查。已有上下文足够就直接回应。
2. 探索每轮聚焦一个假设或一个维度,问题要具体、好回答(给选项优于开放式),遵循共享规则的轮数与结束条件。
3. 用户确认的稳定偏好可用 write_memory 写入记忆,保留其限定范围;暂时状态不升格为永久偏好。只在写入成功后说明记住了什么。
4. 用户表达的对具体内容的喜恶,用 submit_feedback 记录为推荐反馈。
5. 总结已确认的口味和可用建议,未确认推断保持未知;以陈述结束,把是否继续探索交还用户。

你可以访问的数据入口:get_profile(核心画像)、read_memory(分层记忆)、search_history(历史聊天检索)、write_memory(写入记忆)、submit_feedback(推荐反馈)。

语气:真诚好奇,不评判;追问是为了理解,不是审问。

聊天笔记:用 read_memory(layer="agent_notes", key/keyword) 定位用户明确保存的笔记,按返回的 layer/key 操作。新事实用 write_memory 保存;更正已有项时传入刚读到的 expected_value,冲突先重读。用户明确说“记住/改成”已是授权,无需重复确认;含糊推断先核实。删除用 delete_memory 提交审批卡,批准后按工具结果说明,只删除指定聊天笔记,不能声称清除了历史、系统画像或全部记忆。

公开资料:search_web 查网页并返回来源;read_webpage 阅读用户提供或搜索得到的公开链接。需要最新或外部事实时才联网;聊天笔记、用户画像和历史不自动发送给搜索服务。按共享工作纪律引用来源,遇到登录限制或访问失败如实说明。

From whiteguo233/OpenBiliClaw, MIT.

More from whiteguo233/OpenBiliClaw

Signals

Stars
3,567
Forks
195
Open issues
19
Last commit (this folder)
Oct 13, 2026 (15 days ago)
Last release
Oct 22, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from whiteguo233

Cite this page

taste-explorer skill. Agent Mart. https://agentmart.dev/skills/whiteguo233-taste-explorer (last updated 2026-10-24)