meeting
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business, life). The user can mix teams, add custom personas on the fly, and size the meeting up or down. Full debate written to a markdown file in the current directory, only the Boss's final synthesis is shown in the console.
npx skills add davepoon/buildwithclaude --skill meeting --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business, life). The user can mix teams, add custom personas on the fly, and size the meeting up or down. Full debate written to a markdown file in the current directory, only the Boss's final synthesis is shown in the console.
How it works
The skill sets up a lineup of 3 to 10 AI personas drawn from specified teams (dev, design, product, business, life) with archetypes Boss, Pusher, Rookie, Watcher, Cynic. The user can specify a topic and optional teams or custom agents. It creates a transcript file in the current working directory named in the form meeting-<short-slug>.md and writes an initial header with the topic, date, lineup, and language.
It runs a multi-round process:
- Round 1: opening statements from all personas, written to the transcript file.
- Round 2: rebuttals, referencing a shared context summarizing Round 1, written to the transcript file.
- Round 3: closing statements, referencing Round 2 context, written to the transcript file.
- Boss synthesis: a single Boss generates a final synthesis that answers the user's question, shown in the console and not echoing individual round content.
The console output is kept minimal: it shows setup lines, per-round status lines, the final Boss synthesis, and the transcript file path.
When to use it
Use when you want a structured debate among multiple AI personas with defined roles to synthesize a topic and generate a comprehensive markdown transcript for later review.
What it can touch
The skill uses agents and write operations to create and modify the transcript file in the current directory. It will spawn persona outputs and append them to the transcript via Bash append calls, maintaining the transcript as the canonical record.
Caveats
License: MIT. Requires the claude-code tool and the declared Agent, Write, Bash capabilities. Behavior relies on the availability of configured persona archetypes and teams; custom personas are supported via natural-language description and on-the-fly creation, with internal prompts stored for reuse. The Boss synthesis stands alone in the console and does not reference individual persona names.
# Meeting Bots You are the **chair** of a meeting. A lineup of 3 to 10 personas with distinct psychologies will debate the user's topic. The lineup defaults to 5 personas from one team, but the user can mix teams, add custom personas described in natural language, and size the meeting up or down. The full debate is written to a markdown file in the current working directory. The console stays clea
What does the meeting skill do?
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business, life). The user can mix teams, add custom personas on the fly, and size the meeting up or down. Full debate written to a markdown file in the current directory, only the Boss's final synthesis is shown in the console.
How do I install it?
Run `npx skills add davepoon/buildwithclaude --skill meeting --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From davepoon/buildwithclaude, a repository with 3,251 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.