/install global-wire
GlobalWire
Use this skill when the user wants major world news to read like a professional wire desk instead of a loose AI summary.
Track major world events like a wire desk: professional briefings, credibility labels, and rolling timelines.
GlobalWire is an editorial skill, not a crawler framework.
Default assumption:
- the current model or active workflow may already have found the core answer
- GlobalWire's main job is to normalize, tighten, and publish that answer
- only add extra search when the answer is clearly incomplete or weakly sourced
When the user asks in Chinese, default to fully Chinese section labels and Chinese confidence labels. Do not leave English field names in a Chinese-only response unless the user explicitly asks for bilingual formatting.
Quick start
Example natural-language prompts:
今天发生了什么重大新闻?按 GlobalWire 格式输出。Use $global-wire to summarize today's biggest global events in Chinese.Use $global-wire to build a full timeline of the 2026 US-Iran conflict.Use $global-wire to verify how credible this report is.
Example explicit invocations:
$global-wire/global_wire
On surfaces that sanitize slash-command names, the display name remains GlobalWire while the command may appear as /global_wire.
Product promise
GlobalWire should feel like a newsroom editor handling a rough draft:
- cleaner structure
- lower noise
- clearer fact versus analysis separation
- stronger timeline discipline
- explicit confidence labels
- stronger focus on globally consequential developments
- concise, reusable markdown output
Core modes
Pick one primary mode:
-
brief- Use for daily or on-demand major-news summaries.
- Return
3-5independent cards by default, but prefer fewer stronger cards over padding. - Expand to at most
8on unusually heavy days. - If there is no clear global-level top event, say so and add
Still worth watching. - Require clear global spillover for inclusion in the main card list.
-
timeline- Use for a continuing event.
- Default to the event's full arc from its start to today.
- Write event development, not media history.
-
verify- Use when the user asks whether a claim or summary is reliable.
- Grade reliability; do not pretend to be an absolute fact-checking authority.
-
alert- Use for fast, developing, high-impact events.
- Keep the first pass short and explicit about uncertainty.
Result-first workflow
- Start from the best answer already available in context.
- If the answer is obviously thin, add light evidence patching.
- Reorganize into the correct GlobalWire mode.
- Apply timeline, formatting, source-priority, and confidence rules.
- Save to markdown when requested or when the workflow is archival.
Search stance
Do not default to heavy browser automation or multi-platform orchestration.
Preferred order:
- current model's native search result or answer
- user-provided answer or draft
- targeted web search or source checking only when needed
- browser automation only as a last-resort patch path
Read {baseDir}/references/source-priority.md before adding or revising sources.
Hard editorial rules
- Keep sports, entertainment, local social incidents, and small funding rounds out of the default major-news brief.
- Separate
FactsfromAnalysisevery time. - Do not write media coverage history as if it were event history.
- Do not upgrade weakly sourced timelines into high-confidence narratives.
- Domestic sources can supplement, but should not dominate major conflict or geopolitics timelines.
- Social posts and prediction markets are weak signals, not factual anchors.
- Do not pad with assistant chatter, moral framing, or generic commentary.
- Do not pad the daily brief with entertainment, sports, or low-spillover items just to hit a card count target.
- Keep confidence labels clean; if nuance is needed, explain it in a note, not by bloating the label.
- In Chinese output, localize the briefing header, section labels, confidence labels, and watchlist labels.
References to load
Always use:
{baseDir}/references/output-modes.md{baseDir}/references/timeline-rules.md{baseDir}/references/credibility-rules.md{baseDir}/references/source-priority.md{baseDir}/references/formatting-rules.md
Use as needed:
{baseDir}/references/exemplars.md{baseDir}/references/file-layout.md
Output contract
Always show:
- a style line
- a length line
Default style is always wire unless the user explicitly asks otherwise.
Supported voice modes:
wirebriefanalyst
Translate visible labels to match the user's language while preserving structure and meaning.
Preferred visible labels:
- English:
Current style,Current length - Chinese:
当前风格,当前长度
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install global-wire - 安装完成后,直接呼叫该 Skill 的名称或使用
/global-wire触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
GlobalWire 是什么?
Turn answers about major world events into wire-style briefings, rolling event timelines, verification notes, and alert bullets with stable formatting, sourc... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 127 次。
如何安装 GlobalWire?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install global-wire」即可一键安装,无需额外配置。
GlobalWire 是免费的吗?
是的,GlobalWire 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
GlobalWire 支持哪些平台?
GlobalWire 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 GlobalWire?
由 Yansoun(@yly46967-source)开发并维护,当前版本 v0.1.0。