Auto-invoked
analyze
Run a comprehensive multi-agent crypto analysis with phased execution. Usage: /analyze BTC or /analyze ETH SOL
@hugoguerrapInstall Skill/quick
Quick single-agent market check. Usage: /quick BTC or /quick ETH
Claude Code
$ npx -y skills add hugoguerrap/crypto-claude-desk --skill quick --agent claude-code
Codex
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a codex -y
Cursor
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a cursor -y
Gemini CLI
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a gemini-cli -y
GitHub Copilot
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a github-copilot -y
OpenCode
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a opencode -y
Windsurf
$ npx skills add hugoguerrap/crypto-claude-desk --skill quick -a windsurf -y
SKILL.md
quick.SKILL.mdname: quick description: Quick single-agent market check. Usage: /quick BTC or /quick ETH user-invocable: true
Quick Market Check
Get a fast snapshot of $ARGUMENTS using a single agent. No team needed.
Workflow
1. Delegate using the Task tool with `subagent_type: general-purpose` and `model: haiku`:
"You are the market-monitor agent. Quick market snapshot for $ARGUMENTS. Use these MCP tools (call them in parallel):
- get_exchange_prices(symbol='{SYMBOL}/USDT') for live price, 24h change, volume
- get_fear_greed_index() for market sentiment
- get_funding_rate(symbol='{SYMBOL}') for futures funding rate
Also run a WebSearch for '{SYMBOL} crypto news today' to catch any breaking events. Be concise — this is a quick check, not a full analysis. Do NOT use the Edit tool."
2. Present the result directly to the user. Keep it brief.
When to suggest deeper analysis
If the agent detects any of these, suggest running `/analyze $ARGUMENTS`:
- Price change >5% in 24h
- Extreme Fear or Extreme Greed
- Funding rate anomaly (>0.05% or <-0.05%)
- Volume spike >2x average
Stats
109
Stars
29
Forks
Maintained
Maintenance
Python
Language
MIT
License
Last commit
Created
Ships withcrypto-trading-desk
I used to spend weeks building multi-agent systems with LangGraph, CrewAI, and AutoGen. Hundreds of lines of Python orchestration code, custom state machines, fragile message passing between agents.
1078 skills7 agents
Stars on GitHub
Momentum
- stars in total
- 107
Other skills on crypto-trading-desk.
@hugoguerrapInstall SkillAuto-invoked
close-trade
Close an open trade and run post-mortem analysis. Usage: /close-trade trade_001 or /close-trade trade_001 at 98500
@hugoguerrapInstall SkillAuto-invoked
create
Extend the system by creating new MCP servers, agents, or skills. Usage: /create a DeFi protocol tracker or /create an agent for…
@hugoguerrapInstall SkillAuto-invoked
monitor
Autonomous monitoring loop. Checks open trades against SL/TP levels, closes trades that hit targets, evaluates expired…
@hugoguerrapInstall SkillAuto-invoked
portfolio
View current portfolio status, open trades, and performance stats. Usage: /portfolio
@hugoguerrapInstall SkillAuto-invoked
setup
First-time setup for Crypto Trading Desk. Detects your environment, installs dependencies, and verifies everything works. Run…
@hugoguerrapInstall SkillMore skills from other plugins.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
@browser-useInstall Skillagent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…
@vercel-labs-2Install Skill
Questions about quick.
- Which coding agents can use quick?
- quick installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.