← 返回 Skills 市场
Us Macro News Monitor
作者
Nguyễn Đức Thành
· GitHub ↗
· v1.0.2
789
总下载
3
收藏
4
当前安装
3
版本数
在 OpenClaw 中安装
/install us-macro-news-monitor
功能描述
Tracks US macro signals from Bloomberg, WSJ, and Reuters and maps potential spillover to Vietnam sectors; used when users ask about US macro news and likely...
安全使用建议
This skill appears coherent for its stated purpose, but verify two things before installing: (1) Confirm whether the platform will supply the 'Brave API' / web-fetch capability and whether any credentials or API keys will be required — the SKILL.md mentions Brave API but the registry metadata doesn't list any env vars. Ask where those keys would be stored and ensure least-privilege access. (2) Understand how the skill will handle paywalled sources: the skill says to respect paywalls and use fallback public sources, which is good — ensure it won't attempt to bypass paywalls or access account-only content. Also note this skill produces monitoring signals, not financial advice; if you plan to provide it with an ACTIVE_WATCHLIST, confirm the agent's outputs are only signals and that you (not the skill) retain control of any trading decisions. If you need higher assurance, request a version that explicitly documents the required platform capabilities/credentials and how web fetches are authenticated and logged.
功能分析
Type: OpenClaw Skill
Name: us-macro-news-monitor
Version: 1.0.2
The skill bundle is benign. Its purpose is clearly defined as monitoring US macro news and mapping impacts to Vietnamese equities, using legitimate public data sources. The `SKILL.md` provides detailed, well-structured instructions for the AI agent, including guardrails against providing financial advice and emphasizing data quality. There are no indications of prompt injection attempts to deviate from the stated purpose, exfiltrate data, execute arbitrary commands, or perform any other malicious actions. The tooling relies on platform-provided web fetch and API access, consistent with its function.
能力评估
Purpose & Capability
The name/description (US macro → Vietnam spillovers) matches the SKILL.md workflow: collecting headlines, classifying themes, scoring confidence, and mapping to Vietnam sectors. The only mismatch is the SKILL.md's requirement for 'Brave API access' and 'OpenClaw web fetch' which are listed as tooling assumptions but are not declared as required credentials or environment variables in the registry metadata.
Instruction Scope
All runtime instructions stay within the monitoring/mapping scope: fetch headlines, classify, tag tone, map transmission channels, and run quality gates. The skill explicitly instructs respecting paywalls (use accessible metadata or fallbacks) and to avoid making buy/sell recommendations, which reduces risky scope creep. It does depend on web-fetching capabilities but does not instruct reading local files, system secrets, or exfiltrating data to external endpoints beyond the listed news sources.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest-risk delivery mechanism. Nothing is downloaded or written to disk by the skill itself.
Credentials
The SKILL.md says it requires 'OpenClaw web fetch + Brave API access', but the skill declares no required environment variables or credentials. That is an inconsistency to clarify: Brave API usage often implies a service endpoint or key (platform-provided or user-provided). No other unrelated secrets are requested, and the skill doesn't ask for AWS/GitHub/etc. credentials.
Persistence & Privilege
The skill is user-invocable, not 'always: true', and doesn't request persistent system changes or modify other skills. The normal autonomous invocation flag remains false-worthy only if combined with other red flags (which are not present).
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install us-macro-news-monitor - 安装完成后，直接呼叫该 Skill 的名称或使用
/us-macro-news-monitor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
版本历史
v1.0.2
- Added "Watchlist mode" section: supports user-provided ticker watchlists and outputs a Watchlist Impact Map with monitoring triggers and confidence tags.
- Clarified that no absolute buy/sell instructions are produced; the skill offers signals and watch items.
- No other major changes; core process and data quality requirements remain the same.
v1.0.1
- Expanded skill description for clarity and added explicit usage scenarios.
- Introduced a "compatibility" line to clarify workflow requirements.
- Refined the execution workflow with clear, ordered steps.
- Added a "Theme taxonomy" section for consistent macro theme classification.
- Included a new "Trigger examples" section with sample user prompts.
- Improved documentation structure for maintainability and usability.
v1.0.0
US Macro News Monitor skill – initial release:
- Enables automatic monitoring of US macroeconomic news from leading sources (Bloomberg, WSJ, Reuters) and relevant public data (Fed, BLS, BEA, FRED) with fallback handling.
- Classifies news by macro themes and tone, with a focus on potential transmission to Vietnamese equities and sectors.
- Implements a data quality gate for freshness, coverage, de-duplication, evidence tagging, and fallback logging.
- Applies a clear, shared confidence rubric for each output based on source count, freshness, and cross-confirmation.
- Outputs structured summaries: top headlines, theme/tone overview, Vietnam spillover map, actionable watchlist, and explicit confidence indicators.
元数据
常见问题
Us Macro News Monitor 是什么？
Tracks US macro signals from Bloomberg, WSJ, and Reuters and maps potential spillover to Vietnam sectors; used when users ask about US macro news and likely... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 789 次。
如何安装 Us Macro News Monitor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install us-macro-news-monitor」即可一键安装，无需额外配置。
Us Macro News Monitor 是免费的吗？
是的，Us Macro News Monitor 完全免费（开源免费），可自由下载、安装和使用。
Us Macro News Monitor 支持哪些平台？
Us Macro News Monitor 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 Us Macro News Monitor？
由 Nguyễn Đức Thành（@ndtchan）开发并维护，当前版本 v1.0.2。
推荐 Skills