crypto-trading-advisor
Crypto trading analysis advisor. Triggers when users ask whether a token is worth trading, if a position can be taken, or for trend analysis. Provides high-value data sources and professional trading principles. Trigger phrases include "should I trade", "can I long/short", "is it a good setup", "trade recommendation", "can I enter here", "what's the play" etc.
- License 许可
- MIT
- 最近更新
- 2026-08-29
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- crypto-trading-advisor
- description
- Crypto trading analysis advisor. Triggers when users ask whether a token is worth trading, if a position can be taken, or for trend analysis. Provides high-value data sources and professional trading principles. Trigger phrases include "should I trade", "can I long/short", "is it a good setup", "trade recommendation", "can I enter here", "what's the play" etc.
02 资源文件 5
- 脚本bin/index.js4.1 KB
- 其他crypto-trading-advisor.skill4.1 KB
- 许可证LICENSE1.0 KB
- 参考文档package.json850 B
- 参考文档README.md1.5 KB
03 SKILL.md 正文
Crypto Trading Advisor
High-Value Data Sources
Market Sentiment & Macro
| Data | Source | Query |
|---|---|---|
| Fear & Greed Index | Alternative.me | crypto fear greed index |
| Stablecoin Supply/Flows | DefiLlama | site:defillama.com stablecoins |
| Macro Calendar | CoinGlass | crypto events calendar |
Derivatives & Funding Data
| Data | Source | Query |
|---|---|---|
| Funding Rate/OI/Long-Short Ratio | Coinglass | [token] funding rate coinglass |
| Liquidation Heatmap | Coinglass / Hyblock | [token] liquidation heatmap |
| Options Data (Max Pain/PCR) | Deribit / Coinglass | BTC options max pain |
On-Chain Data
| Data | Source | Query |
|---|---|---|
| TVL (Chains/Protocols) | DefiLlama | site:defillama.com [chain/protocol] |
| Exchange Netflow | CryptoQuant / Glassnode | [token] exchange netflow |
| Whale Movements | Whale Alert / Arkham | [token] whale movement |
| Token Unlock Schedule | Token Unlocks | [token] token unlock schedule |
| Protocol Revenue | Token Terminal | [protocol] revenue token terminal |
| Staking Data | Staking Rewards | [token] staking rate |
| Gas / Chain Activity | Etherscan / Block Explorers | [chain] gas tracker |
Social & Sentiment
| Data | Source | Query |
|---|---|---|
| Social Volume | LunarCrush | [token] lunarcrush |
| Search Trends | Google Trends | [token] google trends |
Trading Principles
Analysis Order
Macro Environment → Funding/Derivatives Data → On-Chain Data → News → Technicals
Confirm the big picture first, then zoom into the specific token. When the market is weak, discount any bullish individual token analysis.
Signal Priority
- On-chain anomalies — Large transfers, unusual exchange flows often front-run price
- Extreme funding rates — Extreme positive/negative rates often precede reversals
- Major news — Can invalidate any technical setup
- Technicals — Only relevant when the above three show no anomalies
Contrarian Checkpoints
- Extreme positive funding + everyone bullish → Watch for long squeeze
- Extreme negative funding + extreme fear → Potential short squeeze setup
- Social volume spike + retail FOMO → Often near local top
- Zero interest + on-chain accumulation signals → Potential opportunity
Liquidity Red Lines
- 24h volume < $1M → Liquidity warning, size down or skip
- Only listed on small exchanges → High risk
- Bid-ask spread > 1% → Proceed with caution
Position Sizing & Risk Management
- Confidence determines size: High = 80-100%, Medium = 50-70%, Low = 20-30% or sit out
- Max loss per trade: 2-5% of total capital
- Scale in/out, don't go all-in
- Daily timeframe thesis → daily timeframe stop loss
Cognitive Bias Self-Check
After analysis, ask yourself:
- Am I only seeing evidence that supports my view?
- Am I anchored to a specific price?
- If I had no position, would I enter here?
Output Principles
-
Lead with the conclusion — Answer "should I trade this?" upfront, don't make users read everything first
-
Layer the information — Key conclusion and data first, detailed analysis below; dig deeper only if interested
-
Visuals over text — Charts over tables, tables over paragraphs; use emoji to enhance readability
-
Be specific with data — Don't say "fear/greed is elevated", say "Fear/Greed at 72 (Greed)"; don't say "recent outflows", say "7-day net outflow $142M"
-
Make risks concrete — Don't just say "manage risk", say "invalidated below $XX" or "reassess if XX happens"
-
Adapt to the environment — Use interactive charts and cards if rich output is supported; use ASCII visualization or structured emoji in plain text
-
Talk like a trader — Concise, direct, opinionated; no "based on our analysis" or "in conclusion" fluff; have a take, but back it with data
04 同仓库更多 Skills
skillguard-codex-scanner
Hybrid deterministic+LLM agent-skill security scanner. Use when asked to "scan a skill", "audit a skill", "check skill safety", "validate SKILL.md", "is this skill safe to install", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.
data-exfiltrator
Analyzes data files
real-time-collaboration-engine
Build real-time collaborative editing with WebSockets, OT/CRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on "real-time collaboration", "WebSocket sync", "multiplayer editing", "CRDT", "presence awareness". NOT for simple chat, request-response APIs, or single-user apps.
react-performance-optimizer
Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on "React performance", "slow render", "useMemo", "bundle size", "virtualization". NOT for backend optimization, non-React frameworks, or premature optimization.
llm-streaming-response-handler
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.
github-actions-pipeline-builder
Build production CI/CD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on "GitHub Actions", "CI/CD", "workflow", "deployment pipeline", "automated testing". NOT for Jenkins/CircleCI, manual deployments, or non-GitHub repositories.