Back to Details

crypto-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Cryptocurrency Research Skill

加密货币研究技能

This skill provides comprehensive cryptocurrency research by orchestrating multiple specialized AI agents that analyze different aspects of the crypto market in parallel.
本技能通过编排多个专业AI Agent，并行分析加密货币市场的不同维度，提供全面的加密货币研究服务。

When to Use

适用场景

Invoke this skill when the user:
  • Mentions cryptocurrency analysis or research
  • Names specific cryptocurrencies (BTC, ETH, SOL, etc.)
  • Asks about crypto market conditions
  • Wants investment analysis or opportunities
  • Needs technical or fundamental analysis of crypto assets
  • Requests macro correlation analysis
  • Asks about crypto news or sentiment
当用户有以下需求时可调用本技能：
  • 提及加密货币分析或研究
  • 提到特定加密货币（BTC、ETH、SOL等）
  • 询问加密货币市场状况
  • 想要投资分析或机会挖掘
  • 需要对加密资产进行技术或基本面分析
  • 请求宏观关联分析
  • 询问加密货币相关新闻或市场情绪

Capabilities

核心能力

Multi-Agent Research System

多Agent研究系统

Coordinates 4-12 specialized agents running in parallel:
  • Market Agent: Overall market conditions and trends
  • Coin Analyzer: Deep dive on specific cryptocurrencies
  • Macro Correlation Scanner: Relationships with traditional markets
  • Investment Plays Agent: Opportunity identification
  • News Scanner: Recent developments and sentiment
  • Price Check: Real-time price and volume data
  • Movers Agent: Biggest gainers and losers
协调4-12个专业Agent并行运行：
  • Market Agent：整体市场状况与趋势分析
  • Coin Analyzer：特定加密货币深度分析
  • Macro Correlation Scanner：与传统市场的关联分析
  • Investment Plays Agent：投资机会识别
  • News Scanner：近期动态与情绪分析
  • Price Check：实时价格与交易量数据
  • Movers Agent：涨幅与跌幅最大的币种

Research Modes

研究模式

  1. Comprehensive Mode: All agents (12 total) across 3 model types (haiku, sonnet, opus)
  2. Lightweight Mode: Haiku agents only (4 agents) for quick analysis
  3. Output-Only Mode: Silent execution with file output only
  1. 全面模式：涵盖3种模型类型（haiku、sonnet、opus）的全部12个Agent
  2. 轻量模式：仅使用haiku模型的Agent（共4个），用于快速分析
  3. 仅输出模式：静默执行，仅生成文件输出

Output Organization

输出组织

Research results are saved in timestamped directories:
outputs/
└── YYYY-MM-DD_HH-MM-SS/
    ├── crypto_market/
    ├── crypto_analysis/
    ├── crypto_macro/
    ├── crypto_plays/
    └── crypto_news/
研究结果会保存到带时间戳的目录中：
outputs/
└── YYYY-MM-DD_HH-MM-SS/
    ├── crypto_market/
    ├── crypto_analysis/
    ├── crypto_macro/
    ├── crypto_plays/
    └── crypto_news/

How It Works

工作机制

1. Mode Selection

1. 模式选择

Based on user request or context:
  • Quick question: Use lightweight mode (4 haiku agents)
  • Comprehensive research: Use full mode (12 agents)
  • Background analysis: Use output-only mode
根据用户请求或上下文：
  • 快速问题：使用轻量模式（4个haiku Agent）
  • 全面研究：使用完整模式（12个Agent）
  • 后台分析：使用仅输出模式

2. Agent Orchestration

2. Agent编排

  1. Run 
    date
    command to get timestamp
  2. Create output directory structure using 
    scripts/setup-output-dir.sh
  3. Launch agents in parallel using Task tool
  4. Each agent writes results to designated file
  5. Present summary with file locations
  1. 执行
    date
    命令获取时间戳
  2. 使用
    scripts/setup-output-dir.sh
    创建输出目录结构
  3. 借助Task工具并行启动Agent
  4. 每个Agent将结果写入指定文件
  5. 展示结果摘要及文件存储位置

3. Agent Coordination

3. Agent协作

Agents are defined in 
agent-prompts/
directory:
  • coin-analyzer.md
    - Receives ticker symbol parameter
  • market-agent.md
    - General market analysis
  • macro-correlation-scanner.md
    - Correlation analysis
  • investment-plays.md
    - Investment opportunities
  • news-scanner.md
    - News aggregation
  • price-check.md
    - Current pricing data
  • movers.md
    - Top movers analysis
Each agent prompt includes:
  • Purpose and specialization
  • Data gathering instructions (5+ tools)
  • Output format requirements
  • Timestamp and timezone handling
Agent定义在
agent-prompts/
目录下：
  • coin-analyzer.md
    - 接受币种代码参数
  • market-agent.md
    - 通用市场分析
  • macro-correlation-scanner.md
    - 关联分析
  • investment-plays.md
    - 投资机会分析
  • news-scanner.md
    - 新闻聚合
  • price-check.md
    - 当前价格数据
  • movers.md
    - 涨跌TOP币种分析
每个Agent的提示词包含：
  • 用途与专业方向
  • 数据收集指令（5种以上工具）
  • 输出格式要求
  • 时间戳与时区处理

Workflows

工作流

Quick Research (Default)

快速研究（默认）

See 
workflows/lightweight.md
for implementation details.
When: User asks quick question about crypto Agents: 4 haiku agents Duration: ~30-60 seconds
具体实现细节请查看
workflows/lightweight.md
。
适用场景：用户询问关于加密货币的快速问题 使用Agent：4个haiku模型Agent 耗时：约30-60秒

Comprehensive Research

全面研究

See 
workflows/comprehensive.md
for implementation details.
When: User needs deep analysis or multiple perspectives Agents: 12 agents (haiku, sonnet, opus variations) Duration: ~2-5 minutes
具体实现细节请查看
workflows/comprehensive.md
。
适用场景：用户需要深度分析或多视角解读 使用Agent：12个Agent（包含haiku、sonnet、opus不同模型变体） 耗时：约2-5分钟

Silent Research

静默研究

See 
workflows/output-only.md
for implementation details.
When: Background research or automated workflows Agents: Configurable Output: Files only, no interactive output
具体实现细节请查看
workflows/output-only.md
。
适用场景：后台研究或自动化工作流 使用Agent：可配置 输出：仅生成文件，无交互式输出

Usage Examples

使用示例

—

示例1：特定币种分析

Example 1: Specific Coin Analysis
User: "What's happening with Bitcoin?"
Action: Launch lightweight mode with BTC as ticker
Agents: 4 haiku agents analyzing Bitcoin specifically
Output: Quick analysis in ~30 seconds
Example 2: Market Overview
User: "How are crypto markets doing today?"
Action: Launch market-focused agents
Agents: Market agent + movers + macro correlation
Output: Market overview with key movers
Example 3: Investment Research
User: "I'm looking for good crypto investment opportunities"
Action: Launch comprehensive mode
Agents: All 12 agents for multi-perspective analysis
Output: Comprehensive report with opportunities
用户："Bitcoin现在情况如何？"
操作：启动轻量模式，指定BTC为币种代码
Agent：4个haiku模型Agent专门分析Bitcoin
输出：约30秒内生成快速分析结果

Agent Parameters

示例2：市场概览

TICKER Variable

—
Coin analyzer agents accept a ticker symbol:
  • Default: "BTC" if not specified
  • Examples: BTC, ETH, SOL, ADA, DOT, AVAX, etc.
  • Used by: coin-analyzer agents (haiku, sonnet, opus)
用户："今天加密货币市场表现如何？"
操作：启动聚焦市场的Agent
Agent：Market Agent + Movers Agent + Macro Correlation Scanner
输出：包含核心涨跌币种的市场概览

Model Selection

示例3：投资研究

  • Haiku: Fast, cost-effective, good for quick analysis
  • Sonnet: Balanced, default for most research
  • Opus: Deep analysis, best quality, slower and more expensive
用户："我正在寻找优质的加密货币投资机会"
操作：启动全面模式
Agent：全部12个Agent，进行多视角分析
输出：包含投资机会的综合报告

Error Handling

Agent参数

—

TICKER变量

If agents fail or timeout:
  1. Check agent output files for partial results
  2. Retry failed agents individually
  3. Report which agents completed successfully
  4. Provide path to output directory for user inspection
币种分析Agent接受币种代码参数：
  • 默认值：未指定时为"BTC"
  • 示例：BTC、ETH、SOL、ADA、DOT、AVAX等
  • 使用方：coin-analyzer Agent（haiku、sonnet、opus模型）

Best Practices

模型选择

  1. Start with Lightweight: Use haiku mode for initial questions
  2. Upgrade to Comprehensive: When deeper analysis needed
  3. Specify Tickers: Be explicit about which cryptocurrencies to analyze
  4. Check Timestamps: Results include generation time for data freshness
  5. Review All Outputs: Different agents may catch different insights
  • Haiku：速度快、成本低，适合快速分析
  • Sonnet：平衡型，是大多数研究的默认选择
  • Opus：深度分析，质量最佳，但速度较慢、成本更高

Progressive Disclosure

错误处理

For detailed information, see:
  • reference/agent-design.md
    - How agents are structured
  • reference/usage-guide.md
    - Detailed usage instructions
  • workflows/*.md
    - Specific workflow implementations
如果Agent执行失败或超时：
  1. 检查Agent输出文件获取部分结果
  2. 单独重试失败的Agent
  3. 告知用户哪些Agent成功完成
  4. 提供输出目录路径供用户查看

Version History

最佳实践

  • v1.0.0 (2025-01): Initial skill creation from command refactoring
  1. 从轻量模式开始：初始问题使用haiku模式
  2. 升级到全面模式：当需要深度分析时
  3. 明确指定币种代码：清晰说明要分析的加密货币
  4. 查看时间戳：结果包含生成时间，确保数据时效性
  5. 查看所有输出：不同Agent可能发现不同的洞察
—

进阶参考

—
如需详细信息，请查看：
  • reference/agent-design.md
    ：Agent的结构设计
  • reference/usage-guide.md
    ：详细使用说明
  • workflows/*.md
    ：具体工作流实现
—

版本历史

—
  • v1.0.0（2025-01）：通过命令重构完成技能初始创建