Agent skill

Directed Expert Chatroom

by dontbesilent2025 in dontbesilent2025/dbskill

Hosts a chatroom where several expert personas discuss a topic and a judge summarizes their disagreements, with experts recommended by the agent or named by you.

Custom licenceAuto-check passedBusiness, Finance & HR

SKILL.md written in Chinese; this summary is our English description.

Install Directed Expert Chatroom

skills CLI
$ npx skills add dontbesilent2025/dbskill --skill dbs-chatroom -a claude-code

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

GitHub CLI
$ gh skill install dontbesilent2025/dbskill dbs-chatroom --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/dontbesilent2025/dbskill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dbs-chatroom .claude/skills/dbs-chatroom && 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
dbs-chatroom
GitHub stars
11k
Token cost
~896 tokens
SKILL.md length
159 words
Files
2
Skills in repo
37
Repo updated
First seen
Licence
Custom licence

At a glance

Hosts a chatroom where several expert personas discuss a topic and a judge summarizes their disagreements, with experts recommended by the agent or named by you.

  • Works in 5 steps: 命题清楚:能说出核心命题、适用边界和判断方法。 → 经受时间检验:经历过长期使用、批评、反驳和修正,价值不依赖一时的流行。 → 可独立验证:理论的价值能通过原著、研究、案例或长期实践检验,不依赖提出者持续讲述自… → …
  • Getting several expert viewpoints on a business or life decision
  • SKILL.md covers 聊天室的边界, 工作流程 and 注意事项
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent acts as moderator of a multi-role discussion. If you name the experts (the example uses Charlie Munger, Daniel Kahneman and Ray Dalio), it goes straight to the debate. Otherwise it analyzes the topic, recommends 3-5 experts with a one-line reason each, and waits for you to confirm or adjust the list before continuing.

Recommendations are chosen by theory rather than fame. Each candidate needs a clear core proposition, a record of surviving long-term testing, independent verifiability and a variable no one else covers, and content influencers or people known mainly for personal success stories are excluded. After confirmation each expert runs as its own parallel sub-agent and a judge summarizes the round. The room stays open for follow-up questions with the same experts until you ask to end it or type /dbs. The skill text is in Chinese.

When your agent uses it

  • Getting several expert viewpoints on a business or life decision
  • Stress-testing a plan against differing frameworks
  • Continuing an existing multi-expert discussion with a new question

Example prompts

  • “Open a chatroom on whether I should quit my job to start a company, and recommend the experts.”
  • “Start a chatroom with Charlie Munger and Daniel Kahneman on whether to raise our prices.”
  • “Keep the chatroom going, but focus the next round on cash flow risk.”

Requirements

  • An agent that can launch parallel sub-agents

Workflow steps

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

  1. 命题清楚:能说出核心命题、适用边界和判断方法。
  2. 经受时间检验:经历过长期使用、批评、反驳和修正,价值不依赖一时的流行。
  3. 可独立验证:理论的价值能通过原著、研究、案例或长期实践检验,不依赖提出者持续讲述自己有多成功。
  4. 能够处理当前变量:理论能让用户区分具体选择,并覆盖当前讨论中其他理论没有覆盖的变量。
  5. 材料足够:有可靠的一手文本与足够的解释材料,能够忠实还原方法,不把零散名言拼成一个虚构观点。

What it can do on your machine

Read from SKILL.md and the folder at commit 8d3ed39. 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

Directed Expert Chatroom loads about 896 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~896

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 159 words (~896 tokens).

name
dbs-chatroom

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/dbs-chatroom of dontbesilent2025/dbskill.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 8d3ed39

Compare with similar skills

Directed Expert Chatroom 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.

Directed Expert Chatroom compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Directed Expert Chatroom this skilldontbesilent2025/dbskill11k—~896Automated safety check: PassCustom licence
Tradingagents AnalysisKylinMountain/TradingAgents-AShare857—~1.8kAutomated safety check: PassCustom licence
AI Team Orchestrationboshi-xixixi/TraeSkill276—~1.4kAutomated safety check: PassMIT
Workflow OrchestrationAnastasiyaW/codex-claude-code-config154—~3.8kAutomated safety check: PassMIT
AI Team Orchestrationgithub/awesome-copilot40k—~992Automated safety check: PassMIT
Design Orchestrationaiskillstore/marketplace4336 repos~952Automated safety check: PassNone

Similar skills

  • Tradingagents Analysis

    KylinMountain/TradingAgents-AShare

    A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪(北向资金/主力资金)、宏观经济分析及博弈论推演, 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。

    857 GitHub stars~1.8k tokensUpdated 23 days ago
    Business, Finance & HRAuto-check passed
  • AI Team Orchestration

    boshi-xixixi/TraeSkill

    Bootstrap and run a multi-agent AI development team. An agent skill from boshi-xixixi/TraeSkill.

    276 GitHub stars~1.4k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Workflow Orchestration

    AnastasiyaW/codex-claude-code-config

    Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

    154 GitHub stars~3.8k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • AI Team Orchestration

    github/awesome-copilot

    Official

    Bootstrap and run a lightweight multi-agent development team.

    40k GitHub stars~992 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Design Orchestration

    aiskillstore/marketplace

    Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order.

    433 GitHub starsUsed in 6 repos~952 tokens
    Agent WorkflowsAuto-check passed
  • Multi Agent Brainstorming

    aiskillstore/marketplace

    Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.

    433 GitHub starsUsed in 6 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

More from dontbesilent2025/dbskill

All 37 skills in this repo
  • DBS Business Toolkit Entry

    dontbesilent2025/dbskill

    Chinese-language entry skill for the dontbesilent business toolkit: onboards new users, orchestrates tasks across sub-skills, runs numbered prompts and lists hidden ones.

    11k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • DBS Skill Maker

    dontbesilent2025/dbskill

    Turns a problem you keep running into into a single installable, tested skill, and prepares a GitHub repository only when you ask to share it.

    11k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Short Video Extractor

    dontbesilent2025/dbskill

    Extracts post data and speech transcripts from Douyin, Xiaohongshu and WeChat Channels share links and saves the transcripts as Markdown by author and title.

    11k GitHub stars~949 tokensUpdated yesterday
    Auto-check passed
  • Dbs Human Dispatch

    dontbesilent2025/dbskill

    当用户希望将任务交给员工或协作者并跟进结果时,结合本地人员资料选择负责人,写清要求、协商工期、提供帮助并验收汇报;有飞书 CLI 时派单、读取回填和回复,缺少工具或权限时交付可转发文字。支持事件队列与可配置 Agent 接入,不承担招聘、绩效排名或惩罚。

    11k GitHub stars~790 tokensUpdated yesterday
    Auto-check passed
  • Cross-Agent Skill Installer

    dontbesilent2025/dbskill

    Links a skill or a whole skill collection into every installed agent's directory, choosing a shared or per-client entry point automatically.

    11k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Dbs Video Navigation

    dontbesilent2025/dbskill

    根据本地视频或带时间戳字幕划分章节、话题或步骤,生成可导入剪辑软件的导航条 MP4、动态分段进度和时间表。用户要求视频章节导航、顶部进度条或当前位置提示时使用;不负责平台链接数据提取、标题封面开头文案、风险声明贴片或剪辑原片。

    11k GitHub stars~727 tokensUpdated yesterday
    Auto-check passed

Questions about Directed Expert Chatroom

What does Directed Expert Chatroom do?

Hosts a chatroom where several expert personas discuss a topic and a judge summarizes their disagreements, with experts recommended by the agent or named by you. The agent acts as moderator of a multi-role discussion. If you name the experts (the example uses Charlie Munger, Daniel Kahneman and Ray Dalio), it goes straight to the debate.

When should I use Directed Expert Chatroom?

Directed Expert Chatroom fits situations like: getting several expert viewpoints on a business or life decision; stress-testing a plan against differing frameworks; continuing an existing multi-expert discussion with a new question.

How do I install Directed Expert Chatroom in Claude Code?

Run `npx skills add dontbesilent2025/dbskill --skill dbs-chatroom -a claude-code`. Or copy the skill folder (skills/dbs-chatroom in dontbesilent2025/dbskill) into .claude/skills/dbs-chatroom in your project. Claude Code loads it when a task matches its description.

How do I install Directed Expert Chatroom in Codex?

Run `npx skills add dontbesilent2025/dbskill --skill dbs-chatroom -a codex`. Or copy the skill folder (skills/dbs-chatroom in dontbesilent2025/dbskill) into .agents/skills/dbs-chatroom in your project. Codex loads it when a task matches its description.

Can I use Directed Expert Chatroom 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 dontbesilent2025/dbskill --skill dbs-chatroom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dbs-chatroom, .gemini/skills/dbs-chatroom, .github/skills/dbs-chatroom and .opencode/skills/dbs-chatroom in your project.

What does Directed Expert Chatroom need to run?

SKILL.md names no scripts, command-line tools or credentials: Directed Expert Chatroom is instructions for the agent only. Our summary lists: An agent that can launch parallel sub-agents.

Does Directed Expert Chatroom 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 Directed Expert Chatroom 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 Directed Expert Chatroom use?

Directed Expert Chatroom has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Directed Expert Chatroom use?

About 896 tokens (SKILL.md is roughly 3.6k 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 Directed Expert Chatroom?

Skills that share tags, products or a category with Directed Expert Chatroom: Tradingagents Analysis (KylinMountain/TradingAgents-AShare, 857 stars), AI Team Orchestration (boshi-xixixi/TraeSkill, 276 stars), Workflow Orchestration (AnastasiyaW/codex-claude-code-config, 154 stars) and AI Team Orchestration (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Directed Expert Chatroom?

dontbesilent2025 (a GitHub user) maintains it in dontbesilent2025/dbskill, which has 10,589 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 10, 2026.

Source: dontbesilent2025/dbskill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.