Individual skill
ai-meeting
Run structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices. Use when the user wants an AI meeting, AI roundtable, multi-agent discussion, debate, proposal review, plan review, decision review, or wants Codex, Claude Code, and other CLI agents to analyze a proposal across multiple expert roles, challenge assumptions, preserve per-agent sessions, and produce a final decision report with provenance. 也适用于中文场景：方案评审、多 Agent 讨论、技术路线评审、商业决策评审。
plugins/ai-meeting/SKILL.md
Source commit 5bd4f168edf7c18a8303cbfde20708ff62aabc4d
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 998
- Repository last updated
- Aug 12, 2026
- License
- Apache-2.0
Observed agent integration: claude-code
- claude-code Repository topic
- claude-code-commands Repository topic
- claude-code-hooks Repository topic
- claude-code-mcp Repository topic
- claude-code-plugin Repository topic
- claude-code-subagents Repository topic
- awesome-claude-code Repository topic
- awesome-list Repository topic
- awesome-resources Repository topic
- awesome-plugins Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.claude-plugin/plugin.jsonasset · 250 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesSKILL.mdcore · 14,919 bytesagents/openai.yamlasset · 225 bytesreferences/output-template.mddoc · 2,081 bytesreferences/prompt-templates.mddoc · 5,396 bytesreferences/provider-adapters.mddoc · 13,987 bytesreferences/state-schema.mddoc · 5,105 bytesscripts/ai-meeting.mjsruns · 50,625 bytesscripts/providers/claude.mjsruns · 3,067 bytesscripts/providers/codex.mjsruns · 3,329 bytesscripts/providers/cursor.mjsruns · 5,370 bytesscripts/providers/gemini.mjsruns · 5,658 bytesscripts/providers/hermes.mjsruns · 4,150 bytesscripts/providers/opencode.mjsruns · 7,229 bytesscripts/providers/qoder.mjsruns · 5,256 bytesscripts/providers/registry.mjsruns · 541 bytesscripts/providers/shared.mjsruns · 5,350 bytes
Read excerpt
# AI Meeting
## 核心定位
把一个方案交给多个 AI Agent 进行结构化会议评审：每个 Agent 从项目核心目标和用户价值出发独立判断，经过多轮质询与修正，最后输出可执行的 Markdown 决策报告。
第一版优先支持 Codex 和 Claude Code。Qoder、OpenCode、Cursor、Gemini 和 Hermes 已作为可选 provider adapter 注册。项目不按品牌预设封禁其他 CLI Agent 工具；任何 CLI Agent 只要 provider adapter 能通过 `doctor` 如实报告认证、prompt 传输、会话处理和权限边界，就可以参与会议。
## 必须遵守
1. 不要把 AI Meeting 做成闲聊。每次会议都必须服务于一个明确决策。
2. 所有 Agent 必须从项目核心目标、真实用户价值、成本、风险和替代方案出发分析。
3. 不要默认认同其他 Agent。观点可以改变，但必须说明是哪个证据、约束或推理改变了判断。
4. 优先使用每个 Agent 自己的持久会话：Codex 使用 thread id，Claude Code 使用 session id。