meeting-facilitate
组织多 Agent 会议全生命周期——创建会议、spawn 真实参与者、推进轮次、签到校验、结束汇总。当需要多方协作做决策、评审方案、辩论分歧、复盘项目、头脑风暴或方案评估时使用本技能。
Skill by amar3012005
Chalk Labs
Need help deploying meeting-facilitate?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/amar3012005-meeting-facilitate
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.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo 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/meeting-facilitate
What's inside
- Skill name
meeting-facilitate- Description
- 组织多 Agent 会议全生命周期——创建会议、spawn 真实参与者、推进轮次、签到校验、结束汇总。当需要多方协作做决策、评审方案、辩论分歧、复盘项目、头脑风暴或方案评估时使用本技能。
- License
- Apache-2.0
- Instructions
- 352 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- decision.md · templates/
- retrospective.md · templates/
- review.md · templates/
- standup.md · templates/
SKILL.md (first lines)
# Meeting Facilitate — 会议主持技能
本技能指导你(Leader 或具备主持职责的 Agent)端到端组织一场多 Agent 会议:选模板 → 创建会议 → spawn 真实参与者 → 签到 → 推进轮次 → 验证全员发言 → 结束并汇总。
## 前置要求
- 已完成 `os-register`,拥有自己的 `agent_id`(用于以主持人身份发言)
- 已明确:会议目的、需要的角色、目标产出
- 已知会议涉及的关键文件路径(用于 materials/context_files)
## 核心原则(看完这三条再往下读)
1. **OS 不会自动 spawn 参与者** — `meeting_create` 只创建会议记录和 dispatch_plan,**真正让参与者到场必须靠你亲自调用 Agent tool**。光创建不 spawn = 没人到场 = 会议失败。
2. **绝不代打他人发言** — 你以主持人身份发言时,`agent_id` 和 `caller_agent_id` 必须都填**你自己的 ID**。用别人的 `agent_id` 发言会被 OS 标记为 `impersonation=true` 并写入审计日志。
3. **conclude 前必须确认全员发言** — `meeting_conclude` 默认开启 `validate_attendance`,未发言者会让 conclude 返回 400。**不要用 `force=True` 绕过**——除非有不可抗力的技术理由。
---
## 主持流程(7 步)
### Step 1: 选择会议模板
根据会议目的对照下表选模板。详细模板说明见 `templates/<name>.md`(progressive disclosure)。
| 目的 | 推荐模板 | 轮数 | 为何 |
|------|---------|------|------|
| 发散创意、产生新想法 | `brainstorm` | 4 | 独立发散 → 交叉启发 → 评估 → 汇总 |
| 多方案中做选择 | `decision` | 3 | 陈述 → 质询 → 收敛 |
| 评审代码 / PR / 交付物 | `review` | 3 | 陈述 → 独立评审 → 回应裁定 |
| 项目复盘、提取教训 | `retrospective` | 3 | 4Ls → 改进方向 → 承诺计划 |
| 每日进度同步 | `standup` | 1 | 三问:完成 / 计划 / 阻塞 |
| 决策有重大分歧或风险 | `debate` | 4 | 正方陈述 → 反方质疑 → 正方回应 → 裁决 |
| 开放议程、自由议题 | `lean_coffee` | 3 | 议题收集 → 投票 → 时间盒讨论 |
| 架构 / 方案多视角评审 | `council` | 3 | 专家视角 → 交叉质询 → 裁决 |
不确定?用 `template="free"`,OS 会根据 `topic` 关键词自动推荐。
### Step 2: 创建会议(拿到 dispatch_plan)
**必须使用结构化 `participants`**(dict 列表),否则 dispatch_plan 里的 `launch_call` 会是空的,无法 ready-to-paste。
```
meeting_create(
topic="评审 v0.9 Prompt Registry 架构方案",
template="council", # Step 1 选的模板
team_id="repo-insight-arch", # 可省略,自动用活跃团队
team_name="repo-insight-arch", # 用于 launch_call.params.team_name
participants=[
{
"name": "arch-lead",
"agent_template": "software-architect",
"role": "评估架构整体可行性与分层合理性",
"context_files": ["docs/v0.9-prompt-registry.md"],
"expected_output": "三段式:可行性 / 风险 / 建议",
},
{
"name": "backend-arch",
"agent_template": "backend-architect",
"role": "评估存储层与 API 设计",
"context_files": ["docs/v0.9-prompt-registry.md", "src/aiteam/storage/repository.py"],
"expected_output": "存储方案 + 接口契约 + 迁移路径",
},
],
rounds=[ # 可选,省略则用模板默认 rounds
{"topic": "立场陈述", "rule": "每人 3 段:评估视角 / 风险点 / 评分 1-5"},
],
materials=["docs/v0.9-prompt-registry.md"], # 全员必读
)
```
返回结构(关键字段):
```
{
"data": {"id": "mtg-abc123", ...},
"dispatch_plan": [
{
"participant": "arch-lead",
"launch_call": {
"tool": "Agent",
"params": {
"subagent_type": "software-architect",
"name": "arch-lead",
"team_name": "repo-insight-arch",
"description": "评估架构整体可行性与分层合理性",
"prompt": "<OS 已生成的完整 prompt,包含 meeting_id / 角色 / 必读材料 / 发言规则 / meeting_send_message 调用示例 / 完成后 SendMessage 指令>",
},
},
"ready_to_paste": True,
},
...
],
"expected_participants": ["arch-lead", "backend-arch"],
"attendance_check_command": "meeting_attendance_check(meeting_id='mtg-abc123')",
}
```
记录 `meeting_id`,后续每一步都要用到。
### Step 3: Spawn 每位参与者(最关键的一步)
> ⚠️ **这是整个流程的关键。跳过这一步 = 会议没有任何人到场 = 后续所有步骤都会失败。**
遍历 `dispatch_plan`,对每个 `ready_to_paste=True` 的项目调用 Agent tool,**直接把 `launch_call.params` 整体作为 Agent tool 的参数**:
```
for item in dispatch_plan:
if not item["ready_to_paste"]:
# 旧字符串格式:补结构化参数后重新 meeting_create
continue
Agent(**item["launch_call"]["params"])
```
**约束:**
- **不要修改 `prompt` 字段的内容** — OS 已经把 meeting_id、角色、必读材料、发言规则、`meeting_send_message` 调用示例、完成后 `SendMessage("已发言")` 指令全部预设好了。手动改动反而会破坏闭环。
- **不要省略任何参与者** — 漏掉一个,Step 7 conclude 时就会被 attendance 校验拦下。
- 多个 spawn 可以**并行发出**(同一个消息里多个 Agent 调用),加快到场速度。
### Step 4: 签到 — 等待全员发言From amar3012005/BLAIQ-CORE, Apache-2.0.
More from amar3012005/BLAIQ-CORE
- 0.469score
meeting-participate
amar3012005
Participate in AI Team OS meetings with structured discussion rounds
SkillCFreshness: CClaude Code +9 - 0.469score
os-register
amar3012005
Auto-register as a team member when joining an AI Team OS project
SkillCFreshness: CClaude Code +9 - 0.466score
autopilot
amar3012005
让 OS 在用户离开期间自主推进任务。支持三个子命令:start(启动)、stop(停止)、status(状态查询)。
SkillCFreshness: CClaude Code +9 - 0.463score
continuous-mode
amar3012005
启动持续工作模式——Leader自动循环领取和执行任务
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 11, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/amar3012005/BLAIQ-CORE
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from amar3012005
- 0.469score
meeting-participate
amar3012005
Participate in AI Team OS meetings with structured discussion rounds
SkillCFreshness: CClaude Code +9 - 0.469score
os-register
amar3012005
Auto-register as a team member when joining an AI Team OS project
SkillCFreshness: CClaude Code +9 - 0.466score
autopilot
amar3012005
让 OS 在用户离开期间自主推进任务。支持三个子命令:start(启动)、stop(停止)、status(状态查询)。
SkillCFreshness: CClaude Code +9 - 0.463score
continuous-mode
amar3012005
启动持续工作模式——Leader自动循环领取和执行任务
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get meeting-facilitate running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
meeting-facilitate skill. Agent Mart. https://agentmart.dev/skills/amar3012005-meeting-facilitate (last updated 2026-10-24)