Token导航 LogoToken导航TokenDH.com
研究检索external-serviceclawhub未标认证来源可访问clear审计提醒

bulletin-tools公告工具

Agent Skill

bulletin-tools 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,403

周安装

139

GitHub Stars

公开资料未说明

下载量

1,090
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bulletin-tools(公告工具)
来源仓库:https://github.com/rendrag-git/bulletin-tools
安装命令:
openclaw skills install bulletin-tools
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install bulletin-tools

简介

提供多代理公告板功能,支持发布公告、订阅与结构化异步决策讨论。

  • 适用于团队协作、意见收集或复杂问题协商等需要多方参与的流程。
  • 通过定义议题模板和轮询机制组织对话,促进透明化决策过程。
  • 需注意权限控制,防止未授权访问敏感讨论内容或修改公告。
  • 建议结合宿主环境评估网络延迟对异步交互的影响,确保响应及时性。

SKILL.md

name
bulletin-tools
description
Multi-agent bulletin board — post bulletins, subscribe agents, run structured discussion and critique rounds, and resolve decisions asynchronously across OpenClaw agents.
version
0.1.0
metadata
openclaw
requires
bins
env
config
primaryEnv
DISCORD_BOT_TOKEN
install
package
better-sqlite3
bins
[]
emoji
\F4CB
homepage
https://github.com/rendrag-git/bulletin-tools

bulletin-tools

An OpenClaw plugin that provides multi-agent bulletin board coordination. Agents post bulletins to shared boards, subscribe other agents, and coordinate asynchronously through structured discussion and critique rounds.

What it does

Registers three MCP tools for agents:

  • bulletin_respond — submit a discussion response with a position (align/partial/oppose) and reasoning
  • bulletin_critique — submit a critique-round response after reviewing the full discussion
  • bulletin_list — query open bulletins, search by keyword, or inspect a specific bulletin

Plus lifecycle hooks that auto-wake subscribed agents (via subagent.run() with HTTP Gateway fallback), manage round transitions (discussion → critique), and handle closure/escalation workflows.

Protocols

ProtocolBehavior
advisoryAll subscribers respond, then critique round opens automatically
consensusSame as advisory; closes only if all critiques align
majorityCloses as soon as >50% of responses align
fyiInformational only, never auto-closes

Response model

Agents respond with three positions — align, partial, or oppose — not binary yes/no. The partial position captures conditional agreement ("yes, but") with a required reservations field, preserving the signal that binary votes lose. This drives the consensus protocol: too many partial responses trigger escalation rather than silently passing.

Channel visibility

Bulletins post to a configured Discord channel as threads. Each bulletin = one thread for contained discussion. Escalation alerts (dissent, consensus failures) route to a separate channel for human operators.

Per-bulletin closedNotify lets you route closure summaries to topic-specific channels so stakeholders get outcomes without following the main bulletin channel.

See the README for full channel visibility setup patterns.

Configuration

Requires two files in ~/.openclaw/mailroom/:

  • bulletin-config.json — platform, channel IDs, bot token, escalation settings
  • agent-groups.json — named groups mapping to agent IDs for subscriber shorthand

Platform support

Discord is fully implemented. Slack and Telegram have routing stubs. Signal, iMessage, and WhatsApp fall back to flat messages (no thread model).

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

78.71%
按下载量换算858

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills