rkiding/awesome-finance-skills
10 skills6.1k installs27.5k starsGitHub
Install
npx skills add https://github.com/rkiding/awesome-finance-skillsSkills in this repo
1Alphaear Newsalphaear-news is an agent skill from rkiding/awesome-finance-skills that fetch hot finance news, unified trends, and prediction financial market data. use when the user needs real-time financial news, trend reports from multiple finance sources (weibo, zhihu, wallstreetcn,. # AlphaEar News Skill ## Overview Fetch real-time hot news, generate unified trend reports, and retrieve Polymarket prediction data. ## Capabilities ### 1. Fetch Hot News & Trends Use `scripts/news_tools.py` via `NewsNowTools`. - **Fetch News**: `fetch_hot_news(source_id, count)` - See [sources.md](references/sources.md) for valid `so Developers invoke alphaear-news during grow/analytics work for finance & trading tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments.1.4kinstalls2Alphaear StockThe alphaear-stock skill search A-Share HK US finance stock tickers and retrieve finance stock price history Use when user asks about finance stock codes recent price changes or specific company finance stock info AlphaEar Stock Skill Overview Search A-Share HK US stock tickers and retrieve historical price data OHLCV Stock Search Data Use scripts stock_tools py via StockTools Search search_ticker query Fuzzy search by code or name e g Moutai 600519 Returns List of code name Get Price get_stock_price ticker start_date end_date Returns DataFrame with OHLCV data Dates format YYYY-MM-DD Get Fundamentals get_stock_fundamentals ticker Returns dict with sector industry market cap PE ratio and summary Supports A-Share HK US stocks Dependencies pandas requests akshare yfinance scripts database_manager py stock tables Notes Proxy For US stock data via yfinance you may need to set environment variables if your network cannot reach Yahoo Finance directly bash export HTTP_PROXY http proxy_ip port export HTTPS_PROXY http proxy_ip port A-Share HK Data is primarily fetched via akshare EastMoney which usually works best with a direct1.2kinstalls3Alphaear Sentimentalphaear-sentiment is a finance-focused sentiment analysis skill from rkiding/awesome-finance-skills that exposes analyze_sentiment through scripts/sentiment_tools.py. Developers choose FinBERT for fast local scoring or LLM mode when they want flexible interpretation of earnings transcripts, headlines, and trader commentary. The skill returns sentiment labels plus confidence scores suitable for quant research notebooks, alerting rules, or feature stores. Reach for alphaear-sentiment when market text must be classified positive, negative, or neutral without hand-rolling NLP pipelines or generic sentiment models tuned for social media rather than finance.589installs4Alphaear Predictoralphaear-predictor is a finance skill in rkiding/awesome-finance-skills that combines quantitative forecasting with news-aware adjustments for market time series. The workflow starts with scripts/kronos_predictor.py calling KronosPredictorUtility to produce a base technical forecast, then applies a Forecast Adjustment Prompt so agents revise predictions using current news sentiment. Developers reach for alphaear-predictor when prototyping trading dashboards, risk tools, or research notebooks that need structured price or product forecasts instead of hand-tuned spreadsheets. The skill documents a two-step pipeline—generate base forecast, then agentically adjust—so agents know which script and reference prompts to load. It fits teams integrating Kronos predictions into Python backends or agent workflows where macro headlines should shift model output. Reference prompts live alongside kronos_predictor.py in the awesome-finance-skills repo. Agents load Forecast Adjustment Prompt text after the quantitative pass so headline risk can nudge direction without replacing the underlying Kronos signal entirely.529installs5Alphaear Signal Trackeralphaear-signal-tracker is an Awesome-finance-skills agent workflow for tracking how finance investment signals evolve as new market information arrives. The agent follows prompts in references/PROMPTS.md: FinResearcher gathers facts and prices, FinAnalyst creates an initial InvestmentSignal, and Signal Tracking assesses whether evidence strengthened, weakened, falsified, or left the thesis unchanged. Data collection delegates to alphaear-search and alphaear-stock skills; JSON cleanup can use scripts/fin_agent.py helper _sanitize_signal_output. The pattern is extracted from FinAgent track_signal method rather than a standalone library class, with agno agent framework and sqlite3 persistence noted as dependencies. Developers running systematic strategies use it to keep living theses auditable during live operation instead of one-off analysis snapshots when monitoring drift, misses, and trigger changes across trading sessions and portfolio review cycles that demand continuous signal state updates from alphaear companion skills.502installs6Alphaear Searchalphaear-search is a Python agent skill from RKiding's 8-skill Awesome-finance-skills collection that gives coding agents unified finance search across the public web and a local document store. Agents invoke SearchTools in scripts/search_tools.py through search(query, engine, max_results), choosing among four engines—jina, ddg, baidu, or local—or call aggregate_search(query) to merge multi-engine hits into one JSON or List[Dict] payload. Local RAG through scripts/hybrid_search.py searches a daily_news database built by sibling skills for cached financial headlines. references/PROMPTS.md supplies a Search Cache Relevance prompt so agents reuse prior results instead of repeating network calls. Install via npx skills add RKiding/Awesome-finance-skills@alphaear-search into Claude Code, Codex, or OpenCode skill paths. Quant researchers and fintech developers use alphaear-search when screening tickers, exploring themes, or assembling thesis evidence without hand-wiring Jina, DuckDuckGo, and Baidu separately.494installs7Alphaear Reporteralphaear-reporter is a finance reporting skill from rkiding/awesome-finance-skills that produces structured AlphaEar summaries of market events, portfolio signals, and narrative context. Developers and quantitative analysts invoke it when they need a readable digest of what moved markets and how current positions relate to recent headlines without manually stitching feeds and broker data. The skill assembles event timelines, signal highlights, and contextual narrative into a single report artifact suitable for morning briefings or post-trade review. Reach for alphaear-reporter when portfolio monitoring, event-driven trading, or research workflows need a consistent report format from scattered market inputs.475installs8Alphaear Logic Visualizeralphaear-logic-visualizer is a finance agent skill from rkiding/awesome-finance-skills that turns AlphaEar earnings or trading logic into visual decision trees analysts can review with stakeholders. Instead of jumping straight into live orders, the skill helps lay out branches for signals, filters, edge cases, and payoff paths so teams can spot gaps, contradictory rules, or missing conditions early. Developers and quants reach for it when building or extending systematic strategies where opaque rule chains create execution risk, or when they need a shareable artifact to align researchers, risk, and portfolio managers on what triggers a trade. The workflow centers on mapping decision flow before deployment, making implicit heuristics explicit and testable against corner cases in earnings-driven or event-driven models.445installs9Alphaear Deepear Litealphaear-deepear-lite is a Python-backed agent skill in the RKiding Awesome-finance-skills collection that calls DeepEarLiteTools.fetch_latest_signals() to pull high-frequency market signals from https://deepear.vercel.app/latest.json. The bundled deepear_lite.py script formats each signal with title, summary, sentiment_score, confidence, intensity, reasoning text, and source links into a markdown report agents can cite in investment memos. Dependencies are requests and loguru only, with no local database setup. Developers reach for alphaear-deepear-lite when an AI workflow needs immediate DeepEar Lite dashboard context for sector scans, earnings-factor research, or thesis drafting without wiring a custom scraper. Verify connectivity with python scripts/deepear_lite.py after installing via npx skills add RKiding/Awesome-finance-skills@alphaear-deepear-lite.291installs10Skill CreatorSkill-creator guides construction of new Claude Code skills for finance workflows: defining triggers, writing SKILL.md instructions, bundling scripts and references, aligning with awesome-finance-skills conventions, and packaging agent-callable capabilities so AlphaEar and related trading tools remain consistent and maintainable.247installs