← 返回 Skills 市场
zif10765-maker

crypto-research

作者 zif10765-maker · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
610
总下载
1
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install crypto-research
功能描述
加密货币投研分析框架,用于每日行情展望报告和市场实时监控。当需要:(1) 生成每日行情报告,(2) 分析BTC/ETH走势,(3) 监控市场资讯和币价异动,(4) 制定交易预案时使用此skill。
使用说明 (SKILL.md)

加密货币投研分析

专业的投研分析框架,用于生成行情展望报告和交易预案。

核心工作流程

1. 每日报告流程(UTC+8 9:00)

  1. 收集情报 → 2. 宏观分析 → 3. 供需分析 → 4. 技术面 → 5. 情绪面 → 6. 预案 → 7. 结论

2. 数据获取

使用以下API获取实时数据:

数据类型 数据源 获取方式
币价 Binance curl "https://api.binance.com/api/v3/ticker/24hr?symbol=BTCUSDT"
资金费率 Binance curl "https://fapi.binance.com/fapi/v1/premiumIndex?symbol=BTCUSDT"
宏观资讯 jin10 web_fetch
机构资金 ARKM API API key: e77c4a5d-f752-4a49-a49e-503970893e37
补充数据 QVeris skill工具

3. 报告结构

情报 → 宏观 → 供需 → 技术面 → 情绪 → 全场景预案 → 结论

报告要求

情报收集

  • 过去24h重要事件
  • TG群关键资讯(@MEcapital_bot)
  • 宏观数据发布

宏观分析

  • 政策/数据
  • 地缘政治
  • 市场风险偏好
  • 品种价格表:价格 | 24h | 7d | 30d

供需层面

  • 资金费率
  • 链上指标(MVRV、STH-RP)
  • ETF流向
  • 机构动态

技术面

  • 4小时线 + 30分钟线
  • 缠论为主(笔、线段、中枢)
  • 支撑/压力位

情绪面

  • 恐慌指数
  • 资金费率
  • 多空比

全场景预案

  • 剧本A(向上突破):触发、目标、止损
  • 剧本B(向下变盘):触发、目标、止损
  • 剧本C(震荡延续):区间、策略

结论

  • 核心判断(回答:市场在关注什么?)
  • 操作建议
  • 风险提示

报告思路

不是堆砌数据,而是回答问题:什么在影响涨跌?市场在关注什么?

不是罗列指标,而是给出判断:基于这些数据,结论是什么?

不是机械执行,而是主动思考:需要监控什么?什么时候需要提醒用户?

关键原则

  1. 基于实时数据 - 每个报告必须使用当下真实数据
  2. 分析框架不是内容模板 - 学习分析方法,不是复制旧内容
  3. 回答核心问题 - 始终回答:市场在交易什么?
  4. 主动提醒 - 发现重要信息时主动提醒用户

触发条件

  • 用户要求生成行情报告
  • 用户要求分析BTC/ETH走势
  • 实时监控发现重大变化
  • 需要制定交易预案
安全使用建议
This skill largely does what it claims (calls Binance and formats crypto research), but it includes an undeclared hard-coded API key and references undeclared external tools (jin10, QVeris) and a Telegram bot. Before installing or using it: (1) Do not assume the embedded ARKM key is safe—treat it as a leaked/third-party credential and remove it or replace with your own key provided via a secure env var; (2) Ask the publisher for source/homepage and explanation for the embedded key and for details on the referenced tools; (3) If you need monitoring/alerts, confirm exactly what endpoints and external services will be contacted and whether any user data will be transmitted; (4) Run the scripts in a sandboxed environment first and inspect network calls (they currently only curl Binance endpoints, which is expected); (5) Prefer replacing hard-coded secrets with declared required env vars and documented configuration; (6) If you cannot verify the author or purpose of the embedded key and external references, avoid giving the skill autonomous monitoring privileges or installing it in production systems.
功能分析
Type: OpenClaw Skill Name: crypto-research Version: 1.0.0 The skill is classified as suspicious due to two main security vulnerabilities. Firstly, the `SKILL.md` file explicitly exposes an API key (`e77c4a5d-f752-4a49-a49e-503970893e37`) for the ARKM API, which is an information disclosure risk. Secondly, the `scripts/get_7d_price.sh` script is vulnerable to shell injection as it directly interpolates the `$SYMBOL` variable into a `curl` command without apparent sanitization, posing a potential remote code execution risk if the input is user-controlled. While there is no evidence of intentional malicious behavior, these are significant security flaws.
能力评估
Purpose & Capability
The skill's name/description (crypto research, daily reports, BTC/ETH monitoring) aligns with the included scripts that query Binance. However the SKILL.md lists an ARKM API key (e77c4a5d-f752-4a49-a49e-503970893e37) inline and references external data sources/tools (jin10 via web_fetch and 'QVeris skill工具') that are not declared in metadata or requires.env. Embedding an API key in the instructions and referring to other skills/tools without declaring dependencies is disproportionate and unexpected for a straightforward research skill.
Instruction Scope
Instructions are explicit about fetching Binance endpoints (fine) and about producing reports. But they also (a) include a hard-coded ARKM API key in the data-source table, (b) use unspecified 'web_fetch' for jin10 and an external 'QVeris' tool, and (c) reference a Telegram source (@MEcapital_bot). The SKILL.md gives the agent latitude to '主动提醒' when important info is found (implying monitoring/alerting) but offers no constraints or declaration of what data may be accessed/transmitted. The included scripts themselves only call Binance endpoints and are consistent with purpose.
Install Mechanism
No install spec — instruction-only with two small bash scripts. No downloads, package installs, or archive extraction. This is low-risk from an install mechanism perspective.
Credentials
The skill declares no required environment variables or credentials, yet contains a clear hard-coded API key inside SKILL.md. That key is a secret-sized string (looks like an API token) and is not justified in metadata or scope. The presence of an embedded credential is disproportionate (it should either require the user to provide credentials or omit them). Additionally, references to other external services/tools are undeclared (no env vars described for jin10, QVeris, or Telegram access).
Persistence & Privilege
always:false and no install spec means the skill doesn't request permanent/system-level presence. It does not modify other skills or global agent config in the provided files. Autonomous invocation is allowed (platform default) but not combined with other high privileges here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install crypto-research
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /crypto-research 触发
  4. 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
v1.0.0
Initial release of crypto-research skill. - Provides a professional research analysis framework for daily crypto market reports and real-time monitoring. - Supports workflows for intel gathering, macro analysis, supply-demand, technical and sentiment analysis, and scenario planning. - Integrates real-time data from Binance, jin10, ARKM API, and QVeris. - Designed for BTC/ETH trend analysis, market intel monitoring, and trade planning. - Prioritizes answering core market questions and proactive user alerts based on real events.
元数据
Slug crypto-research
版本 1.0.0
许可证
累计安装 6
当前安装数 5
历史版本数 1
常见问题

crypto-research 是什么?

加密货币投研分析框架,用于每日行情展望报告和市场实时监控。当需要:(1) 生成每日行情报告,(2) 分析BTC/ETH走势,(3) 监控市场资讯和币价异动,(4) 制定交易预案时使用此skill。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 610 次。

如何安装 crypto-research?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install crypto-research」即可一键安装,无需额外配置。

crypto-research 是免费的吗?

是的,crypto-research 完全免费(开源免费),可自由下载、安装和使用。

crypto-research 支持哪些平台?

crypto-research 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 crypto-research?

由 zif10765-maker(@zif10765-maker)开发并维护,当前版本 v1.0.0。

💬 留言讨论