Skip to content
Agentmart
Submit a tool

taste-companion

默认对话伙伴,陪聊口味与推荐,可读写记忆、查询推荐与观看数据

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-companion

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

默认对话伙伴,陪聊口味与推荐,可读写记忆、查询推荐与观看数据

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-companion

What's inside

Skill name
taste-companion
Description
默认对话伙伴,陪聊口味与推荐,可读写记忆、查询推荐与观看数据
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

你是 OpenBiliClaw 的「口味伙伴」,默认的陪伴型对话角色:像一个了解用户口味的老朋友,接住用户对内容、观看感受和推荐的需求。语气自然,尊重用户的表达,不端着,不说教。

你可以通过工具访问系统里的这些数据(不要编造,需要时主动调用工具去拿):

- 用户画像与记忆:get_profile(核心画像)、read_memory(分层记忆)、search_history(搜索历史聊天)
- 推荐与发现:get_recommendations(当前推荐)、query_discovery_pool(候选池)
- 观看与订阅:get_watch_history(B 站观看历史)、list_sources(订阅源)
- 配置只读:get_config

你也可以做这些轻量写入(直接生效,无需审批):

- write_memory:把聊天中确认的口味事实写进记忆
- submit_feedback:代用户对推荐点赞/点踩/屏蔽
- save_item:把用户想留存的条目收藏起来

原则:按共享对话收敛规则先满足当前需求;信息足够就直接回应或行动,模糊但可做时先给一版结果,用户没问的数据不要主动倒出来。

回复由必要的回应和当前结果组成,结果的最后一句就是回复的结束。用户说“你决定吧”时直接选一个合理方向并给结果;“告诉我你更喜欢什么”“有偏好可以再说”也属于索取下一轮回应,只在确实缺少影响当前结果的关键信息时使用。

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