Agent skill

Taste Explorer

by whiteguo233 in whiteguo233/OpenBiliClaw

“苏格拉底式追问,通过假设与澄清深挖用户口味,沉淀进记忆”

— description from SKILL.md by whiteguo233
MITAuto-check passed

Install Taste Explorer

skills CLI
$ npx skills add whiteguo233/OpenBiliClaw --skill taste-explorer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install whiteguo233/OpenBiliClaw taste-explorer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/whiteguo233/OpenBiliClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/openbiliclaw/agent/skills_builtin/taste-explorer .claude/skills/taste-explorer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
taste-explorer
GitHub stars
3.4k
Token cost
~276 tokens
SKILL.md length
40 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 5 steps: 先用 get_profile 和 read_memory… → 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)。 → 用户的确认/纠正要及时用 write_memory… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Taste Explorer is a skill in whiteguo233/OpenBiliClaw (3.4k stars). Its SKILL.md is about 276 tokens. Licence: MIT.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 先用 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。
  2. 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)。
  3. 用户的确认/纠正要及时用 write_memory 写入记忆,并让用户知道"我记住了什么"。
  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. 一次不要问太多;用户疲惫或跑题时收敛,总结本轮收获。

What it can do on your machine

Read from SKILL.md and the folder at commit 2d8fe41. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Taste Explorer loads about 276 tokens when it runs. Until then it costs about 11 tokens; SKILL.md has 40 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~11
When it runs · the whole SKILL.md, loaded when a task matches
~276

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from whiteguo233/OpenBiliClaw at commit 2d8fe41, republished under its MIT licence (© whiteguo233). 40 words, ~276 tokens.

Download SKILL.mdSave it as .claude/skills/taste-explorer/SKILL.md (or your agent's skills folder).
name
taste-explorer
description
苏格拉底式追问,通过假设与澄清深挖用户口味,沉淀进记忆
title
口味探寻师
tools
search_web, read_webpage, get_profile, read_memory, write_memory, delete_memory, search_history, submit_feedback

你是 OpenBiliClaw 的「口味探寻师」,一位温和而执着的访谈者。你的目标不是陪聊,而是通过苏格拉底式的追问真正搞清楚用户喜欢什么、为什么喜欢:提出具体假设,请用户确认或纠正;对模糊的回答追问具体例子;把确认过的结论沉淀为长期记忆。

工作方式:

  1. 先用 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。
  2. 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)。
  3. 用户的确认/纠正要及时用 write_memory 写入记忆,并让用户知道"我记住了什么"。
  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. 一次不要问太多;用户疲惫或跑题时收敛,总结本轮收获。

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。

© whiteguo233, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/openbiliclaw/agent/skills_builtin/taste-explorer of whiteguo233/OpenBiliClaw.

Open the folder on GitHubat commit 2d8fe41

Compare with similar skills

Taste Explorer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Taste Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Taste Explorer this skillwhiteguo233/OpenBiliClaw3.4k—~276Automated safety check: PassMIT
Explorersupabase/supabase111k—~845Automated safety check: PassApache-2.0
Tasteaffaan-m/ECC276k1 repos~3.8kAutomated safety check: PassMIT
Tasteasgeirtj/system_prompts_leaks69k—~506Automated safety check: PassCC0-1.0
Agent Scout Explorerruvnet/ruflo74k2 repos~1.6kAutomated safety check: PassMIT
Caveman Repository ExplorerJuliusBrussee/caveman111k1 repos~492Automated safety check: PassApache-2.0

Similar skills

  • Explorer

    supabase/supabase

    Official

    Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.

    111k GitHub stars~845 tokensUpdated today
    DatabasesAuto-check passed
  • Taste

    affaan-m/ECC

    Creative-direction layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop family — a named-genre aesthetic vocabulary, mood + color + light system, beat-synced…

    276k GitHub starsUsed in 1 repo~3.8k tokens
    Media & CreativeAuto-check passed
  • Taste

    asgeirtj/system_prompts_leaks

    Mandatory preflight for web frontend visual design. An agent skill from asgeirtj/system_prompts_leaks.

    69k GitHub stars~506 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Agent skill for scout-explorer - invoke with $agent-scout-explorer

    74k GitHub starsUsed in 2 repos~1.6k tokens
    Auto-check passed
  • Caveman Repository Explorer

    JuliusBrussee/caveman

    A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context.

    111k GitHub starsUsed in 1 repo~492 tokens
    Agent WorkflowsAuto-check passed
  • Taste Distillation

    affaan-m/ECC

    Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a…

    276k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

More from whiteguo233/OpenBiliClaw

All 9 skills in this repo
  • Release

    whiteguo233/OpenBiliClaw

    A skill your agent uses when releasing a version, bumping project versions, or pushing release tags.

    3.4k GitHub stars~680 tokensUpdated today
    Auto-check passed
  • Add Platform Source

    whiteguo233/OpenBiliClaw

    Add, repair, or validate an OpenBiliClaw platform source across fetching, account signals, discovery, and user surfaces.

    3.4k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Openbiliclaw Adapter

    whiteguo233/OpenBiliClaw

    Use OpenBiliClaw's versioned Agent Bridge CLI to read multi-source recommendations, profile state, dialogue, probes, saved lists, and submit explicit feedback.

    3.4k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Writing Specs

    whiteguo233/OpenBiliClaw

    A skill your agent uses when authoring a spec or implementation plan, or planning multi-task work.

    3.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Verify

    whiteguo233/OpenBiliClaw

    Drive a real serve-api process against isolated project roots to verify backend/web changes end-to-end

    3.4k GitHub stars~539 tokensUpdated today
    Auto-check passed
  • System Steward

    whiteguo233/OpenBiliClaw

    管理订阅源与系统配置,所有改动逐项向用户说明并等待批准

    3.4k GitHub stars~238 tokensUpdated today
    Auto-check passed

Questions about Taste Explorer

How do I install Taste Explorer in Claude Code?

Run `npx skills add whiteguo233/OpenBiliClaw --skill taste-explorer -a claude-code`. Or copy the skill folder (src/openbiliclaw/agent/skills_builtin/taste-explorer in whiteguo233/OpenBiliClaw) into .claude/skills/taste-explorer in your project. Claude Code loads it when a task matches its description.

How do I install Taste Explorer in Codex?

Run `npx skills add whiteguo233/OpenBiliClaw --skill taste-explorer -a codex`. Or copy the skill folder (src/openbiliclaw/agent/skills_builtin/taste-explorer in whiteguo233/OpenBiliClaw) into .agents/skills/taste-explorer in your project. Codex loads it when a task matches its description.

Can I use Taste Explorer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add whiteguo233/OpenBiliClaw --skill taste-explorer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/taste-explorer, .gemini/skills/taste-explorer, .github/skills/taste-explorer and .opencode/skills/taste-explorer in your project.

What does Taste Explorer need to run?

SKILL.md names no scripts, command-line tools or credentials: Taste Explorer is instructions for the agent only.

Does Taste Explorer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Taste Explorer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Taste Explorer use?

Taste Explorer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Taste Explorer use?

About 276 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Taste Explorer?

Skills that share tags, products or a category with Taste Explorer: Explorer (supabase/supabase, 111k stars), Taste (affaan-m/ECC, 276k stars), Taste (asgeirtj/system_prompts_leaks, 69k stars) and Agent Scout Explorer (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Taste Explorer?

whiteguo233 (a GitHub user) maintains it in whiteguo233/OpenBiliClaw, which has 3,406 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.

Source: whiteguo233/OpenBiliClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.