← Back to Skills Marketplace
chinfi-codex

Iran War Tracker

by chinfi-codex · GitHub ↗ · v1.1.2 · MIT-0
cross-platform ⚠ suspicious
306
Downloads
0
Stars
0
Active Installs
9
Versions
Install in OpenClaw
/install iran-war-tracker
Description
高频获取2026年3月开始的伊朗战争的最新动态,分析局势进展和风险资产交易线索。生成结构化的伊朗局势分析报告,关注战争动态、霍尔木兹海峡通航状况、油气供应风险及市场反应。 This skill generates structured Iran situation reports focused on war d...
README (SKILL.md)

行动基准哲学

  • 分析框架是展开一切行动的基准
  • 基于分析框架,要做到的是绝对的冷静,客观,不会做任何的主观预设,绝对不将自己置于信息茧房的可能性中。
  • 将世界事件的走向认为是在多重变量变化叠加下所产生的概率论分支。所以要识别当前事件的核心变量,思考其对应权重。然后和高可信度信源信息叠加分析,推演事件的走向,和其对现实世界施加的影响性 。

信息数据归集

**信息处理准则:

  • 真实性,一手信息优于二手信息
  • 根据信源等级确定可信度
    • 最高:官网、国家级官媒,官方平台,官方领导人社交平台发言
    • 次要:社交大V,传言的重要人物讲话
  • 【重要】以下列出的步骤要全部执行:新闻搜索,电报(财联社+金十数据),风险资产数据
  • 【重要】对新闻、电报数据,筛选时效性,默认为过去18小时

使用新闻搜索

第一步,搜索词构建

根据加载的分析框架,分析变量和权重,推导出最重要的3-5个研究方向,每个方向构建搜索关键词组。举例如下: * 战争局势更新 / war situation updates * 霍尔木兹海峡关闭、通航、油轮及袭船事件 / Hormuz Strait closure, transit, tanker, ship attacks * 石油供应、出口、制裁及产量变化 / oil supply, exports, sanctions, production * 天然气供应、LNG、基础设施及出口变化 / natural gas supply, LNG, infrastructure, exports * 领导人、外交官及军方表态 / leader, diplomat, military statements

第二步,使用搜索工具搜索搜索全部关键词组
  • 优先使用当前环境下可用的Tool:WebSearch/Kimi_search,WebFetch
    • Jina**(可选预处理层,可与 WebFetch/curl 组合使用,由于其特性可节省 tokens 消耗,请积极在任务合适时组合使用):第三方网络服务,可将网页转为 Markdown,大幅节省 token 但可能有信息损耗。调用方式为 r.jina.ai/example.com(URL 前加前缀,不保留原网址 http 前缀),限 20 RPM。
  • 可选搜索API,按顺序选择一项可用的即可,根据当前环境下配置使用:
    • Tavily Search API
      • 高质量新闻搜索 API
      • 需要 环境变量 API KEY
    • DuckDuckGo Lite
      • 免费网页搜索(无需 API key)
      • 当上述方法失败时自动作为降级方案
      • 通过 DuckDuckGo Lite HTML 界面搜索
第三步,将所有结果汇总

电报(财联社+金十数据)

用独立脚本 cls_telegraph.py 抓取来自财联社,金十数据的实时电报,并筛选伊朗相关的内容。(脚本已经默认做了筛选)

风险资产数据

使用以下url 获取数据 - BTC: [https://stooq.com/q/l/?s=btcusd&i=d] - 黄金: [https://stooq.com/q/l/?s=xauusd&i=d] - 原油(WTI): [https://stooq.com/q/l/?s=cl.f&i=d] - 天然气: [https://stooq.com/q/l/?s=ng.f&i=d] - 纳指期货: [https://stooq.com/q/l/?s=nq.f&i=d]

分析输出

输出要求

  • 【重要】在报告中输出新闻内容,以时间-新闻[来源]的格式呈现
  • 如果使用subagent进行报告分析输出,则回复结果一定要将subagent最后给出的完整报告内容输出。 主agent仅做简短的精要评述即可!
  • 报告中不同的模块内容,使用适当的分割线,恰当不要喧宾夺主,同时要考虑手机屏幕宽度
  • 报告总字数控制在3000字以内。

分析要求

遵守以下规则(非风格建议,而是硬性要求):

  • 报告默认必须使用中文产出。每个部分都应内容充实,而非一句话总结。
  • 不能仅停留在事件总结。每个部分都需要证据加解读。
  • 必须区分: * 确认的事实 * 市场定价信号 * 推断或情景判断
  • 能源与经济影响的传导路径:
    • 必须分开分析石油和天然气,不能合并成笼统的"能源"段落。
    • 必须严格按照加载的分析框架所指引的传导路径对要素进行分析
  • 补充其他从分析框架中得出的重要路径和变量信号

完整报告模板

📊 战争烈度评估 / War Intensity Assessment

🔥 美以伊动态播报 | YYYY-MM-DD HH:00 🔥


### 📊 【战争烈度评估】/ War Intensity Assessment
X级(🔺上升/🔻下降/➡️持平)/ Level X (Rising/Falling/Stable)
- 当前态势简述 / Current situation summary
- 关键变化点 / Key changes
⚔️ 局势进展 / Situation Updates


### ⚔️ 【局势进展】/ Situation Progress

▸ 🇺🇸 美国汇总 / US Summary
- 🎯 军事行动 / Military Actions:
- 📌 其他动态 / Other Updates:

▸ 🇮🇱 以色列汇总 / Israel Summary
- 🎯 军事行动 / Military Actions:
- 📌 其他动态 / Other Updates:

▸ 🇮🇷 伊朗汇总 / Iran Summary
- ⚡ 反击行动 / Retaliation Actions:
- 📌 其他动态 / Other Updates:

▸ 领导人表态 / Leader Statements:
包括参战方,其他国家,国际重要组织的各方领导人表态汇总

▸ 📈 边际变化评估 / Marginal Change Assessment
├─ 🔴 战争扩大信号 / Escalation Signals:
│  • 空袭烈度/频次是否加大 / Airstrike intensity/frequency:
│  • 地面进攻迹象 / Ground operation signs:
│  • 新参战方动态 / New participants:
├─ 🟢 战争缓和信号 / De-escalation Signals:
│  • 谈判信号 / Negotiation signals:
│  • 停火提议 / Ceasefire proposals:
│  • 外交斡旋 / Diplomatic mediation:
└─ 🚢 霍尔木兹海峡封锁 / Hormuz Strait Blockade:
   • 通航状态 / Transit status:
   • 袭船事件 / Ship attacks:
   • 船只动态 / Vessel movements:
💹 风险资产波动 / Risk Asset Fluctuations

覆盖 BTC、黄金、WTI 原油、天然气和纳指期货。说明价格变动是证实还是反驳地缘叙事。

🛢️ 能源与经济分析

根据分析框架指导进行路径分析 列举石油,天然气,宏观经济等要素

📑 情景推演 / Scenario Analysis
  • 基准情景 / Base Case
  • 升级情景 / Escalation Case
  • 缓和情景 / De-escalation Case

细节下限 / Detail Floor

为避免较弱模型生成浅层输出,强制执行最低细节标准:

  • 局势进展 中美国、以色列、伊朗各方至少 2 个要点
  • 油气分析 中原油和天然气各至少 4 个要点
  • 风险资产波动 至少 3 个要点
  • 情景推演 至少 3 个情景

如证据稀疏,说明证据稀疏,但仍需使用谨慎推断完成完整结构,而非缩短报告。

Usage Guidance
This skill is functionally coherent for generating Iran conflict reports, but be cautious: it will try to use any model/search API keys or custom endpoints present in your environment (OPENAI_API_KEY, OPENCLAW_MODEL_ENDPOINT, OPENCLAW_SEARCH_URL, TAVILY_API_KEY, etc.). That means the full assembled prompt + collected context could be sent to those endpoints. Also the skill prefers loading a remote Gist at runtime (the analysis framework), so its behavior/content can change if that Gist is updated. Before installing or running: (1) review the code yourself or run it in a network-restricted sandbox; (2) avoid setting API keys or custom model endpoints you don't trust; (3) if you need model functionality, prefer trusted provider credentials and review the ai_client target URL; (4) consider whether you are comfortable with the skill fetching external telegraph/news endpoints at runtime. If you want a lower-risk setup, run the scripts locally with network access restricted and keep the framework file local so nothing remote can change behavior unexpectedly.
Capability Analysis
Type: OpenClaw Skill Name: iran-war-tracker Version: 1.1.2 The skill is a specialized geopolitical and market analysis tool designed to track a hypothetical 2026 conflict scenario. It collects data from legitimate financial and news sources (Stooq, CoinGecko, CLS, Jin10) and utilizes search APIs (Tavily, DuckDuckGo). While it employs a remote-loading pattern for its analysis framework via a GitHub Gist (scripts/framework_loader.py), which is a potential vector for remote prompt injection, the current implementation and local fallbacks are strictly aligned with the stated purpose. There is no evidence of data exfiltration, credential theft, or unauthorized command execution.
Capability Assessment
Purpose & Capability
The code (news search, CLS/Jin10 telegraph fetchers, stooq/Coingecko asset fetchers, prompt builder, and AI client) aligns with the stated goal of high-frequency Iran conflict reporting and market signal extraction. Using a model endpoint to synthesize reports is expected. However, the skill is packaged with code that will use optional external services (Tavily, local model-search endpoints, OpenAI/compatible endpoints) if environment variables are present — functionality that is plausible for the purpose but not declared in the metadata.
Instruction Scope
SKILL.md requires loading a remote analysis framework (Gist) with fallback to a local markdown, performing news searches, pulling CLS/Jin10 telegraph feeds, and collecting several risk-asset feeds. The runtime scripts implement these steps and follow the hard rules specified in SKILL.md. No instructions in SKILL.md ask the agent to read unrelated system files or exfiltrate data; the behavior stays within the reporting/aggregation scope.
Install Mechanism
There is no install spec — this is an instruction-and-script package; nothing is downloaded during install. That lowers supply-chain risk. The repository does fetch remote runtime data (Gist, Jin10, CLS, Tavily, stooq, Coingecko, DuckDuckGo) at runtime, which is expected for a live-tracking tool.
Credentials
The skill metadata declares no required environment variables, but the code reads multiple optional env vars that materially change runtime behavior and network targets: OPENCLAW_MODEL_ENDPOINT, OPENAI_API_KEY, OPENAI_BASE_URL, OPENCLAW_SESSION, LLM_API_KEY, LLM_API_BASE, OPENCLAW_SEARCH_URL, OPENCLAW_API_KEY, and TAVILY_API_KEY. If any of these are set, the skill will forward the assembled prompt and context to those endpoints (including arbitrary model endpoints configured via OPENCLAW_MODEL_ENDPOINT or OPENCLAW_SEARCH_URL). That creates a credible path for sensitive context (news, telegraph snippets, market data, and the full report prompt) to be transmitted to third parties without being declared as required credentials — a proportionality and transparency gap the user should consider.
Persistence & Privilege
The skill is not always-enabled and does not request permanent system-level privileges in its manifest. It does not modify other skills' configs. Autonomous invocation (model calling itself) is allowed by default but not combined with an 'always:true' flag or other elevated persistence requests.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install iran-war-tracker
  3. After installation, invoke the skill by name or use /iran-war-tracker
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
- 增加金十数据,优化财联社/金十实时电报数据抓取和伊朗相关信息筛选。 - 电报和新闻数据默认仅处理过去18小时的内容,提升时效性。 - 增加新闻内容输出规范,所有新闻须以“时间-来源”格式呈现。 - 报告字数推荐控制在3000字以内,精简冗余,提升阅读体验。 - 优化细节下限要求:局势、油气、风险资产、情景推演等部分细化约束标准。 - 新增时间工具脚本(time_utils.py)及多项脚本优化,加强数据处理及模块结构。
v1.1.1
- Now includes detailed news content in reports, presented in "time - news [source]" format. - Adds requirements for clear visual separation between report modules, with attention to mobile-friendly formatting. - Improves clarity on output structure and analysis requirements in the documentation. - Version bump to 1.1.1.
v1.1.0
Version 1.1.0 (iran-war-tracker) - Added `/irantracker` and `伊朗动态` as official trigger keywords in skill metadata. - Clarified stepwise news search requirements: explicitly require constructing, searching, and aggregating all major Iran war-related keyword groups. - Made it mandatory to execute all major information-gathering steps: news, CLS telegram, and risk asset data. - Updated instructions for analysis output: main agent must provide a concise summary while the subagent must output the full structured report. - Improved structure and formatting of reporting, tightened requirements for detail, and enhanced enforcement of detail minimums.
v1.0.5
**1.0.5 简要变更** - 重构脚本架构,新增独立数据、分析和处理模块(如:ai_client.py、config.py、market_data.py、report_writer.py 等)。 - 支持按本地与远程分析框架自动切换,优化框架加载逻辑,框架本地文件名调整。 - 明确分离和强化油气、财经数据、行情采集与归档能力。 - 丰富和细化分析流程、信息来源、搜索关键词及报告结构说明,提升模型指导与输出一致性。 - 删除旧版本地分析报告文件,避免混淆。 - 文档(SKill.md)全面更新:突出分析流程、数据处理原则和细节下限标准,强调框架优先与冷静分析哲学。
v1.0.4
Make Chinese output the default report language; only switch to English on explicit user request.
v1.0.3
Prefer remote framework gist with 10s timeout and local fallback; sync prompt and script behavior.
v1.0.2
**Changelog for iran-war-tracker v1.0.2** - Added skill.json file for metadata/configuration. - Enhanced documentation with a new quickstart and usage section at the top of SKILL.md. - Added clear trigger word table and example usage to improve onboarding. - No functional logic changes; this release is documentation and metadata improvements only.
v1.0.1
- Added bilingual (Chinese/English) documentation and report structure for broader accessibility. - Expanded and clarified trigger keywords in both Chinese and English. - Improved section organization: merged and streamlined explanations for workflow, analysis rules, structure, and data sources. - Enhanced clarity of mandatory analysis standards and minimum detail floor. - Updated quick start and environment variable instructions for easier setup. - Refined descriptions to guide users on report content, required depth, and trigger usage.
v1.0.0
Initial release of Iran War Tracker - Provides structured reports on Iran conflict developments, Hormuz Strait status, energy supply risks, and risk asset movements (BTC, gold, WTI crude, natural gas, Nasdaq futures). - Integrates Tavily news search, CLS Telegraph fast news crawling, and market snapshot APIs (Stooq, CoinGecko). - Enforces detailed, sectioned Chinese reporting with mandatory scenario analysis, interpretation, and a minimum content floor for all sections. - Strictly separates oil and gas analysis, explains transmission paths from conflict to market impact, and distinguishes fact, market signal, and inference. - Supports prioritized multi-source news search (model search, Tavily, DuckDuckGo fallback). - Requires local framework file loading for analytic consistency and transparency.
Metadata
Slug iran-war-tracker
Version 1.1.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 9
Frequently Asked Questions

What is Iran War Tracker?

高频获取2026年3月开始的伊朗战争的最新动态,分析局势进展和风险资产交易线索。生成结构化的伊朗局势分析报告,关注战争动态、霍尔木兹海峡通航状况、油气供应风险及市场反应。 This skill generates structured Iran situation reports focused on war d... It is an AI Agent Skill for Claude Code / OpenClaw, with 306 downloads so far.

How do I install Iran War Tracker?

Run "/install iran-war-tracker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Iran War Tracker free?

Yes, Iran War Tracker is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Iran War Tracker support?

Iran War Tracker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Iran War Tracker?

It is built and maintained by chinfi-codex (@chinfi-codex); the current version is v1.1.2.

💬 Comments