首页 › 龙虾技能列表 › Stock Analysis 6 — 技能工具

📈 Stock Analysis 6 — 技能工具

v1.0.0

[自动翻译] Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management, watchlists with alerts, dividend analysis, 8-dimension st...

0· 988·3 当前·3 累计
by @sunerw-dev·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/11
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
可疑
high confidence
The skill's stated purpose (stock & crypto analysis) matches the code, but the runtime instructions and docs ask for sensitive actions and reference tools/credentials that aren't declared in the manifest — this mismatch and the guidance to extract browser auth tokens is concerning; review carefully before installing or grant minimal privileges in an isolated environment.
评估建议
Proceed cautiously. Specific things to consider before installing or running: - Source trust: the skill's source is unknown. Only install if you trust the author. - Incomplete metadata: the manifest only declares 'uv', but docs instruct use of python3, bird (Twitter CLI via npm or brew), and browser cookie extraction — expect to manually install Python packages and CLIs. - Do NOT follow the advice to grant Terminal 'Full Disk Access' or copy browser cookie tokens (AUTH_TOKEN / CT0) into a .env ...
详细分析 ▾
ℹ 用途与能力
Name/description align with included Python scripts (analysis, hot scanner, rumor scanner, portfolio, watchlist, dividends). However, the manifest only declares one required binary (uv) while the SKILL.md/docs also call out python3, npm/bird (Twitter CLI), and browser access; these additional tools are needed for full functionality but are not declared in requires. That mismatch suggests incomplete metadata or sloppy packaging, not necessarily malicious, but it increases operational friction and risk.
⚠ 指令范围
SKILL.md/docs instruct the user to extract Twitter/X auth tokens from browser cookies (AUTH_TOKEN, CT0), to grant Terminal 'Full Disk Access' (macOS) for using browser cookies, and to run cron jobs that fetch external data. Those instructions request sensitive local data and privileged actions unrelated to core analysis logic (you can run a hot scan without browser cookies). The rumor scanner also collects and aggregates data from many external endpoints. The instructions therefore go beyond simple analysis and include steps that could expose sensitive tokens if followed.
ℹ 安装机制
Install spec only installs 'uv' via brew. The package is otherwise a Python project with many scripts and implicit Python dependencies; SKILL.md also recommends installing the 'bird' CLI via npm or brew for Twitter integration. There are no pip/npm install steps or requirements.txt enforced by the install spec, so running the skill as-is may fail or require ad-hoc installs. The brew install for a single binary is low-risk, but the packaging is incomplete.
⚠ 凭证需求
Declared required env vars: none. But docs reference AUTH_TOKEN and CT0 for Twitter (sensitive cookies) and suggest creating a .env with those values. TODO/docs also mention an SEC identity (stock-analysis@clawd.bot). Asking users to copy browser cookie tokens into .env and granting Terminal Full Disk Access is disproportionate compared to the stated purpose and increases risk of credential leakage. The skill does network calls to many external services (Yahoo, CoinGecko, Google News, SEC EDGAR, Twitter) but does not declare any required credentials or how credentials are protected.
✓ 持久化与权限
The skill does write local state (portfolios/watchlist stored under ~/.clawdbot/skills/stock-analysis/*.json) and suggests cron automation; these are expected for a watchlist/alerting tool. always:false and no modifications of other skills or global configs were requested. Autonomous invocation is allowed by default (normal) and not combined with 'always:true' or broad undeclared credential access in the manifest, so persistence/privilege level is within typical expectations.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/2/12

Stock Analysis v6.2 introduces rumor detection and impact scoring: - Added Rumor Scanner for early detection of M&A rumors, insider activity, analyst actions, and Twitter/X whispers - Introduced Impact Scoring system to rank rumors by potential market impact - Expanded Hot Scanner to find trending stocks and crypto from multiple sources - Improved stock and crypto analysis with updated portfolio, watchlist, alerts, and dividend feature set - Enhanced daily workflow with cron support for trend and rumor reports

● 可疑

安装命令 点击复制

官方npx clawhub@latest install stock-analysis-6
镜像加速npx clawhub@latest install stock-analysis-6 --registry https://cn.clawhub-mirror.com

技能文档

Analyze US stocks and cryptocurrencies with 8-dimension analysis, portfolio management, watchlists, alerts, dividend analysis, and viral trend detection.

What's New in v6.2

  • 🔮 Rumor Scanner — Early signals before mainstream news
- M&A rumors and takeover bids - Insider buying/selling activity - Analyst upgrades/downgrades - Twitter/X "hearing that...", "sources say..." detection
  • 🎯 Impact Scoring — Rumors ranked by potential market impact

What's in v6.1

  • 🔥 Hot Scanner — Find viral stocks & crypto across multiple sources
  • 🐦 Twitter/X Integration — Social sentiment via bird CLI
  • 📰 Multi-Source Aggregation — CoinGecko, Google News, Yahoo Finance
  • ⏰ Cron Support — Daily trend reports

What's in v6.0

  • 🆕 Watchlist + Alerts — Price targets, stop losses, signal changes
  • 🆕 Dividend Analysis — Yield, payout ratio, growth, safety score
  • 🆕 Fast Mode — --fast skips slow analyses (insider, news)
  • 🆕 Improved Performance — --no-insider for faster runs

Quick Commands

Stock Analysis

# Basic analysis
uv run {baseDir}/scripts/analyze_stock.py AAPL
# Fast mode (skips insider trading & breaking news)
uv run {baseDir}/scripts/analyze_stock.py AAPL --fast
# Compare multiple
uv run {baseDir}/scripts/analyze_stock.py AAPL MSFT GOOGL
# Crypto
uv run {baseDir}/scripts/analyze_stock.py BTC-USD ETH-USD

Dividend Analysis (NEW v6.0)

# Analyze dividends
uv run {baseDir}/scripts/dividends.py JNJ
# Compare dividend stocks
uv run {baseDir}/scripts/dividends.py JNJ PG KO MCD --output json

Dividend Metrics:

  • Dividend Yield & Annual Payout
  • Payout Ratio (safe/moderate/high/unsustainable)
  • 5-Year Dividend Growth (CAGR)
  • Consecutive Years of Increases
  • Safety Score (0-100)
  • Income Rating (excellent/good/moderate/poor)

Watchlist + Alerts (NEW v6.0)

# Add to watchlist
uv run {baseDir}/scripts/watchlist.py add AAPL
# With price target alert
uv run {baseDir}/scripts/watchlist.py add AAPL --target 200
# With stop loss alert
uv run {baseDir}/scripts/watchlist.py add AAPL --stop 150
# Alert on signal change (BUY→SELL)
uv run {baseDir}/scripts/watchlist.py add AAPL --alert-on signal
# View watchlist
uv run {baseDir}/scripts/watchlist.py list
# Check for triggered alerts
uv run {baseDir}/scripts/watchlist.py check
uv run {baseDir}/scripts/watchlist.py check --notify  # Telegram format
# Remove from watchlist
uv run {baseDir}/scripts/watchlist.py remove AAPL

Alert Types:

  • 🎯 Target Hit — Price >= target
  • 🛑 Stop Hit — Price <= stop
  • 📊 Signal Change — BUY/HOLD/SELL changed

Portfolio Management

# Create portfolio
uv run {baseDir}/scripts/portfolio.py create "Tech Portfolio"
# Add assets
uv run {baseDir}/scripts/portfolio.py add AAPL --quantity 100 --cost 150
uv run {baseDir}/scripts/portfolio.py add BTC-USD --quantity 0.5 --cost 40000
# View portfolio
uv run {baseDir}/scripts/portfolio.py show
# Analyze with period returns
uv run {baseDir}/scripts/analyze_stock.py --portfolio "Tech Portfolio" --period weekly

🔥 Hot Scanner (NEW v6.1)

# Full scan - find what's trending NOW
python3 {baseDir}/scripts/hot_scanner.py
# Fast scan (skip social media)
python3 {baseDir}/scripts/hot_scanner.py --no-social
# JSON output for automation
python3 {baseDir}/scripts/hot_scanner.py --json

Data Sources:

  • 📊 CoinGecko Trending — Top 15 trending coins
  • 📈 CoinGecko Movers — Biggest gainers/losers
  • 📰 Google News — Finance & crypto headlines
  • 📉 Yahoo Finance — Gainers, losers, most active
  • 🐦 Twitter/X — Social sentiment (requires auth)

Output:

  • Top trending by mention count
  • Crypto highlights with 24h changes
  • Stock movers by category
  • Breaking news with tickers

Twitter Setup (Optional):

  • Install bird: npm install -g @steipete/bird
  • Login to x.com in Safari/Chrome
  • Create .env with AUTH_TOKEN and CT0

🔮 Rumor Scanner (NEW v6.2)

# Find early signals, M&A rumors, insider activity
python3 {baseDir}/scripts/rumor_scanner.py

What it finds:

  • 🏢 M&A Rumors — Merger, acquisition, takeover bids
  • 👔 Insider Activity — CEO/Director buying/selling
  • 📊 Analyst Actions — Upgrades, downgrades, price target changes
  • 🐦 Twitter Whispers — "hearing that...", "sources say...", "rumor"
  • ⚖️ SEC Activity — Investigations, filings

Impact Scoring:

  • Each rumor is scored by potential market impact (1-10)
  • M&A/Takeover: +5 points
  • Insider buying: +4 points
  • Upgrade/Downgrade: +3 points
  • "Hearing"/"Sources say": +2 points
  • High engagement: +2 bonus

Best Practice: Run at 07:00 before US market open to catch pre-market signals.

Analysis Dimensions (8 for stocks, 3 for crypto)

Stocks

DimensionWeightDescription
Earnings Surprise30%EPS beat/miss
Fundamentals20%P/E, margins, growth
Analyst Sentiment20%Ratings, price targets
Historical10%Past earnings reactions
Market Context10%VIX, SPY/QQQ trends
Sector15%Relative strength
Momentum15%RSI, 52-week range
Sentiment10%Fear/Greed, shorts, insiders

Crypto

  • Market Cap & Category
  • BTC Correlation (30-day)
  • Momentum (RSI, range)

Sentiment Sub-Indicators

IndicatorSourceSignal
Fear & GreedCNNContrarian (fear=buy)
Short InterestYahooSqueeze potential
VIX StructureFuturesStress detection
Insider TradesSEC EDGARSmart money
Put/Call RatioOptionsSentiment extreme

Risk Detection

  • ⚠️ Pre-Earnings — Warns if < 14 days to earnings
  • ⚠️ Post-Spike — Flags if up >15% in 5 days
  • ⚠️ Overbought — RSI >70 + near 52w high
  • ⚠️ Risk-Off — GLD/TLT/UUP rising together
  • ⚠️ Geopolitical — Taiwan, China, Russia, Middle East keywords
  • ⚠️ Breaking News — Crisis keywords in last 24h

Performance Options

FlagEffectSpeed
(default)Full analysis5-10s
--no-insiderSkip SEC EDGAR3-5s
--fastSkip insider + news2-3s

Supported Cryptos (Top 20)

BTC, ETH, BNB, SOL, XRP, ADA, DOGE, AVAX, DOT, MATIC, LINK, ATOM, UNI, LTC, BCH, XLM, ALGO, VET, FIL, NEAR

(Use -USD suffix: BTC-USD, ETH-USD)

Data Storage

FileLocation
Portfolios~/.clawdbot/skills/stock-analysis/portfolios.json
Watchlist~/.clawdbot/skills/stock-analysis/watchlist.json

Limitations

  • Yahoo Finance may lag 15-20 minutes
  • Short interest lags ~2 weeks (FINRA)
  • Insider trades lag 2-3 days (SEC filing)
  • US markets only (non-US incomplete)
  • Breaking news: 1h cache, keyword-based

Disclaimer

⚠️ NOT FINANCIAL ADVICE. For informational purposes only. Consult a licensed financial advisor before making investment decisions.

数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务