@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/domains/education/open-syllabus-api/SKILL.md

@@ -0,0 +1,171 @@
+---
+name: open-syllabus-api
+description: "Analyze most-taught books and texts via Open Syllabus analytics"
+metadata:
+  openclaw:
+    emoji: "📖"
+    category: "domains"
+    subcategory: "education"
+    keywords: ["Open Syllabus", "syllabi analytics", "teaching data", "textbook rankings", "curriculum analysis", "higher education"]
+    source: "https://opensyllabus.org/"
+---
+
+# Open Syllabus API
+
+## Overview
+
+Open Syllabus analyzes 20M+ college course syllabi from 7,000+ institutions in 140+ countries, tracking which books, articles, and media are most frequently assigned in higher education. The Explorer provides teaching frequency rankings and co-assignment patterns. Useful for curriculum research, textbook selection, and understanding disciplinary norms. Free for basic search; institutional subscription for full API access.
+
+## Explorer Interface
+
+### Web Search
+
+```bash
+# The primary interface is the web explorer:
+# https://explorer.opensyllabus.org/
+
+# Search by title, author, or field
+# Filter by country, institution, discipline, year range
+```
+
+### API Access
+
+```bash
+# API requires institutional subscription
+# Base URL: https://api.opensyllabus.org/v1/
+
+# Search titles
+curl -H "Authorization: Bearer $OS_TOKEN" \
+  "https://api.opensyllabus.org/v1/titles?query=republic+plato&limit=20"
+
+# Get title details
+curl -H "Authorization: Bearer $OS_TOKEN" \
+  "https://api.opensyllabus.org/v1/titles/12345"
+
+# Co-assignment analysis
+curl -H "Authorization: Bearer $OS_TOKEN" \
+  "https://api.opensyllabus.org/v1/titles/12345/co-assigned?limit=20"
+
+# Rankings by field
+curl -H "Authorization: Bearer $OS_TOKEN" \
+  "https://api.opensyllabus.org/v1/rankings?field=Economics&limit=50"
+```
+
+### Query Parameters
+
+| Parameter | Description | Example |
+|-----------|-------------|---------|
+| `query` | Search text | `query=machine+learning` |
+| `field` | Academic discipline | `field=Computer Science` |
+| `country` | Country filter | `country=US` |
+| `institution` | Institution filter | `institution=Harvard` |
+| `year_from` | Start year | `year_from=2020` |
+| `year_to` | End year | `year_to=2026` |
+| `limit` | Results per page | `limit=50` |
+
+## Key Metrics
+
+| Metric | Description |
+|--------|-------------|
+| **Teaching Score** | 0-100 normalized frequency of syllabi appearances |
+| **Count** | Raw number of syllabi featuring the title |
+| **Rank** | Position in overall or field-specific ranking |
+| **Co-assignment** | Titles frequently taught alongside this one |
+
+## Python Usage
+
+```python
+import requests
+
+BASE_URL = "https://api.opensyllabus.org/v1"
+
+
+def search_titles(query: str, field: str = None,
+                  country: str = None,
+                  limit: int = 20, token: str = "") -> list:
+    """Search Open Syllabus for assigned titles."""
+    headers = {"Authorization": f"Bearer {token}"} if token else {}
+    params = {"query": query, "limit": limit}
+    if field:
+        params["field"] = field
+    if country:
+        params["country"] = country
+
+    resp = requests.get(
+        f"{BASE_URL}/titles",
+        headers=headers,
+        params=params,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("results", []):
+        results.append({
+            "title": item.get("title"),
+            "authors": item.get("authors"),
+            "teaching_score": item.get("teaching_score"),
+            "count": item.get("appearance_count"),
+            "rank": item.get("rank"),
+            "top_fields": item.get("top_fields", []),
+        })
+    return results
+
+
+def get_co_assigned(title_id: int, limit: int = 20,
+                    token: str = "") -> list:
+    """Get titles frequently co-assigned with a given title."""
+    headers = {"Authorization": f"Bearer {token}"} if token else {}
+    resp = requests.get(
+        f"{BASE_URL}/titles/{title_id}/co-assigned",
+        headers=headers,
+        params={"limit": limit},
+    )
+    resp.raise_for_status()
+    return resp.json().get("results", [])
+
+
+def get_field_rankings(field: str, limit: int = 50,
+                       token: str = "") -> list:
+    """Get most-taught titles in a field."""
+    headers = {"Authorization": f"Bearer {token}"} if token else {}
+    resp = requests.get(
+        f"{BASE_URL}/rankings",
+        headers=headers,
+        params={"field": field, "limit": limit},
+    )
+    resp.raise_for_status()
+    return resp.json().get("results", [])
+
+
+# Example: find most-taught economics texts
+# results = search_titles("microeconomics", field="Economics")
+# for r in results:
+#     print(f"#{r['rank']} {r['title']} — {r['authors']}")
+#     print(f"  Teaching Score: {r['teaching_score']} "
+#           f"({r['count']} syllabi)")
+```
+
+## Top Assigned Works (Examples)
+
+| Rank | Title | Author | Field |
+|------|-------|--------|-------|
+| 1 | *The Elements of Style* | Strunk & White | Writing |
+| 2 | *The Republic* | Plato | Philosophy |
+| 3 | *A Manual for Writers* | Turabian | Writing |
+| ~10 | *Thinking, Fast and Slow* | Kahneman | Psychology |
+| ~50 | *Introduction to Algorithms* | CLRS | CS |
+
+## Use Cases
+
+1. **Curriculum design**: Find canonical texts in a discipline
+2. **Textbook market research**: Identify widely adopted materials
+3. **Teaching trends**: Track changes in assigned readings over time
+4. **Interdisciplinary mapping**: Discover texts bridging fields
+5. **Academic publishing**: Understand teaching impact vs. citation impact
+
+## References
+
+- [Open Syllabus](https://opensyllabus.org/)
+- [Open Syllabus Explorer](https://explorer.opensyllabus.org/)
+- Sinykin, D. & McLaughlin, T. (2021). "Mapping the Disciplinary Canon with Open Syllabus." *Cultural Analytics*.

package/skills/domains/finance/akshare-finance-data/SKILL.md

@@ -0,0 +1,207 @@
+---
+name: akshare-finance-data
+description: "Access Chinese and global financial data using the AkShare Python library"
+metadata:
+  openclaw:
+    emoji: "💹"
+    category: "domains"
+    subcategory: "finance"
+    keywords: ["akshare", "financial data", "chinese stocks", "market data", "economic indicators", "quantitative finance"]
+    source: "https://clawhub.ai/akshare/akshare-finance"
+---
+
+# AkShare Financial Data Guide
+
+## Overview
+
+AkShare is an open-source Python library providing free access to Chinese and global financial market data. It aggregates data from 50+ sources including Sina Finance, East Money, Tushare, Yahoo Finance, and central bank websites. No API key required for most functions. Essential for financial research, quantitative analysis, and economic studies involving Chinese market data.
+
+## Installation
+
+```bash
+pip install akshare --upgrade
+
+# Verify
+python -c "import akshare as ak; print(ak.__version__)"
+```
+
+## Core Data Categories
+
+### Stock Market Data (A-Shares)
+
+```python
+import akshare as ak
+import pandas as pd
+
+# Real-time quotes for all A-shares
+df = ak.stock_zh_a_spot_em()
+print(df.head())
+# Columns: 代码, 名称, 最新价, 涨跌幅, 成交量, 成交额, ...
+
+# Historical daily data for a specific stock
+df = ak.stock_zh_a_hist(symbol="000001", period="daily",
+                         start_date="20200101", end_date="20261231")
+print(df.columns)
+# 日期, 开盘, 收盘, 最高, 最低, 成交量, 成交额, 振幅, 涨跌幅, 换手率
+
+# Minute-level data
+df = ak.stock_zh_a_hist_min_em(symbol="000001", period="5",
+                                 start_date="2026-01-01 09:30:00",
+                                 end_date="2026-03-10 15:00:00")
+```
+
+### Fund Data
+
+```python
+# ETF list
+df = ak.fund_etf_spot_em()
+
+# Open-end fund NAV history
+df = ak.fund_open_fund_info_em(symbol="000001", indicator="单位净值走势")
+
+# Fund manager information
+df = ak.fund_manager_em(symbol="000001")
+```
+
+### Bond Market
+
+```python
+# China government bond yields
+df = ak.bond_china_yield(start_date="20200101", end_date="20261231")
+
+# Corporate bond issuance
+df = ak.bond_cb_jsl()  # Convertible bonds from jisilu.cn
+```
+
+### Macroeconomic Indicators
+
+```python
+# GDP quarterly data
+df = ak.macro_china_gdp()
+
+# CPI monthly data
+df = ak.macro_china_cpi()
+
+# PMI (Purchasing Managers' Index)
+df = ak.macro_china_pmi()
+
+# Money supply (M0, M1, M2)
+df = ak.macro_china_money_supply()
+
+# US economic data
+df = ak.macro_usa_gdp()  # US GDP
+df = ak.macro_usa_cpi()  # US CPI
+df = ak.macro_usa_unemployment_rate()  # US unemployment
+```
+
+### Foreign Exchange
+
+```python
+# CNY exchange rates
+df = ak.currency_boc_sina(symbol="美元", start_date="20200101", end_date="20261231")
+
+# All major currency pairs
+df = ak.fx_spot_quote()
+```
+
+### Futures and Commodities
+
+```python
+# Chinese commodity futures
+df = ak.futures_zh_daily_sina(symbol="RB0")  # Rebar futures
+
+# Gold and silver prices
+df = ak.futures_foreign_commodity_realtime(symbol="黄金")
+```
+
+## Research Workflow Example
+
+### Financial Panel Data Construction
+
+```python
+import akshare as ak
+import pandas as pd
+
+def build_stock_panel(symbols: list, start: str, end: str) -> pd.DataFrame:
+    """Build a panel dataset of stock returns and fundamentals."""
+    panels = []
+
+    for symbol in symbols:
+        # Price data
+        price = ak.stock_zh_a_hist(symbol=symbol, period="daily",
+                                    start_date=start, end_date=end)
+        price = price.rename(columns={"日期": "date", "收盘": "close",
+                                       "涨跌幅": "return", "成交额": "volume"})
+        price["symbol"] = symbol
+        price["date"] = pd.to_datetime(price["date"])
+
+        # Financial statements (annual)
+        try:
+            fin = ak.stock_financial_analysis_indicator(symbol=symbol)
+            fin = fin[["日期", "净资产收益率(%)", "资产负债率(%)"]].rename(
+                columns={"日期": "report_date", "净资产收益率(%)": "roe",
+                         "资产负债率(%)": "leverage"})
+        except Exception:
+            fin = pd.DataFrame()
+
+        panels.append(price[["date", "symbol", "close", "return", "volume"]])
+
+    panel = pd.concat(panels, ignore_index=True)
+    panel = panel.set_index(["symbol", "date"]).sort_index()
+    return panel
+
+# Usage
+symbols = ["000001", "600519", "000858", "601318", "000333"]
+panel = build_stock_panel(symbols, "20200101", "20261231")
+print(f"Panel: {panel.shape[0]} observations, {panel.index.get_level_values(0).nunique()} firms")
+```
+
+### Event Study
+
+```python
+def event_study(symbol: str, event_date: str, window: int = 10):
+    """Simple event study around a given date."""
+    # Get data with buffer
+    start = pd.to_datetime(event_date) - pd.Timedelta(days=window*3)
+    end = pd.to_datetime(event_date) + pd.Timedelta(days=window*3)
+
+    df = ak.stock_zh_a_hist(symbol=symbol, period="daily",
+                             start_date=start.strftime("%Y%m%d"),
+                             end_date=end.strftime("%Y%m%d"))
+    df["date"] = pd.to_datetime(df["日期"])
+    df["return"] = df["涨跌幅"].astype(float)
+    df = df.set_index("date").sort_index()
+
+    # Market return (CSI 300)
+    market = ak.stock_zh_index_daily(symbol="sh000300")
+    market["date"] = pd.to_datetime(market["date"])
+    market = market.set_index("date")
+    market["mkt_return"] = market["close"].pct_change() * 100
+
+    # Merge and compute abnormal returns
+    merged = df[["return"]].join(market[["mkt_return"]], how="inner")
+    merged["abnormal_return"] = merged["return"] - merged["mkt_return"]
+
+    # Event window
+    event_idx = merged.index.get_indexer([pd.to_datetime(event_date)], method="nearest")[0]
+    event_window = merged.iloc[event_idx-window:event_idx+window+1]
+    event_window["CAR"] = event_window["abnormal_return"].cumsum()
+
+    return event_window[["return", "mkt_return", "abnormal_return", "CAR"]]
+```
+
+## Common Gotchas
+
+| Issue | Solution |
+|-------|---------|
+| Data source temporarily unavailable | AkShare aggregates from web sources; retry or use `try/except` |
+| Inconsistent column names across functions | Always check `df.columns` before processing |
+| Date format varies (string vs datetime) | Standardize: `pd.to_datetime(df["日期"])` |
+| Some functions require specific symbol format | A-shares: 6-digit code; indices: `sh000001`; HK: `00700` |
+| Rate limiting from upstream sources | Add `time.sleep(1)` between batch requests |
+
+## References
+
+- [AkShare Documentation](https://akshare.akfamily.xyz/)
+- [AkShare GitHub](https://github.com/akfamily/akshare)
+- [AkShare API Reference](https://akshare.akfamily.xyz/data/stock/stock.html)

package/skills/domains/finance/finsight-research-guide/SKILL.md

@@ -0,0 +1,113 @@
+---
+name: finsight-research-guide
+description: "Deep financial research with the FinSight multi-agent system"
+metadata:
+  openclaw:
+    emoji: "💰"
+    category: "domains"
+    subcategory: "finance"
+    keywords: ["FinSight", "financial analysis", "deep research", "market analysis", "financial reports", "multi-agent"]
+    source: "https://github.com/RUC-NLPIR/FinSight"
+---
+
+# FinSight Research Guide
+
+## Overview
+
+FinSight is a deep research agent designed specifically for financial analysis. Developed by RUC-NLPIR, it combines multi-source data retrieval, financial reasoning, and report generation to produce publication-ready financial research. It handles market analysis, company fundamentals, sector comparisons, and macroeconomic assessment through specialized agents.
+
+## Installation
+
+```bash
+git clone https://github.com/RUC-NLPIR/FinSight.git
+cd FinSight && pip install -e .
+```
+
+## Core Capabilities
+
+### Research Query to Report
+
+```python
+from finsight import FinSightAgent
+
+agent = FinSightAgent(llm_provider="anthropic")
+
+# Generate comprehensive financial analysis
+report = agent.research(
+    "Analyze the competitive landscape of the global EV battery "
+    "market. Compare CATL, LG Energy, and Panasonic on market "
+    "share, technology, margins, and growth outlook."
+)
+
+print(report.summary)
+report.save("ev_battery_analysis.pdf")
+```
+
+### Agent Architecture
+
+| Agent | Role |
+|-------|------|
+| **Retrieval Agent** | Fetches data from SEC filings, financial APIs, news |
+| **Data Agent** | Processes financial statements, ratios, time series |
+| **Analysis Agent** | Performs fundamental, technical, and comparative analysis |
+| **Reasoning Agent** | Synthesizes findings, identifies trends and risks |
+| **Report Agent** | Generates structured research reports with citations |
+
+### Financial Data Sources
+
+```python
+# FinSight integrates with multiple data sources
+config = {
+    "sec_edgar": True,        # SEC filings (free)
+    "fred": True,             # Federal Reserve economic data
+    "yahoo_finance": True,    # Market data (free)
+    "news_api": True,         # Financial news
+    "world_bank": True,       # Macro indicators
+}
+```
+
+### Analysis Types
+
+```python
+# Company fundamental analysis
+report = agent.research(
+    "Provide a fundamental analysis of NVIDIA including "
+    "revenue trends, margin analysis, valuation multiples, "
+    "and competitive moat assessment."
+)
+
+# Sector analysis
+report = agent.research(
+    "Compare the top 5 cloud computing companies by revenue "
+    "growth, operating margins, and R&D investment intensity."
+)
+
+# Macro analysis
+report = agent.research(
+    "Analyze the impact of rising interest rates on US "
+    "commercial real estate valuations since 2022."
+)
+```
+
+## Report Structure
+
+Generated reports typically include:
+
+1. **Executive Summary** — Key findings in 3-5 bullets
+2. **Market Overview** — Industry size, growth, trends
+3. **Company Analysis** — Financials, competitive position
+4. **Risk Assessment** — Key risks and mitigation
+5. **Outlook** — Forward-looking analysis with scenarios
+6. **Sources** — Cited data sources and references
+
+## Use Cases
+
+1. **Investment research**: Company and sector deep dives
+2. **Due diligence**: Comprehensive target company analysis
+3. **Academic research**: Financial economics research support
+4. **Market intelligence**: Competitive landscape mapping
+
+## References
+
+- [FinSight GitHub](https://github.com/RUC-NLPIR/FinSight)
+- [RUC-NLPIR Lab](http://playbigdata.ruc.edu.cn/)

package/skills/domains/finance/options-analytics-agent-guide/SKILL.md

@@ -0,0 +1,117 @@
+---
+name: options-analytics-agent-guide
+description: "AI agent for options pricing, Greeks, and strategy analysis"
+metadata:
+  openclaw:
+    emoji: "📉"
+    category: "domains"
+    subcategory: "finance"
+    keywords: ["options analytics", "derivatives", "Greeks", "Black-Scholes", "strategy analysis", "financial agent"]
+    source: "https://github.com/options-analytics/options-agent"
+---
+
+# Options Analytics Agent Guide
+
+## Overview
+
+An AI agent for options pricing, risk analysis, and strategy evaluation. It combines Black-Scholes and binomial models, Greeks calculations, implied volatility surfaces, and portfolio risk analytics into a conversational interface. Researchers and quantitative analysts can query options data, price exotic derivatives, and evaluate trading strategies through natural language.
+
+## Core Capabilities
+
+```python
+from options_agent import OptionsAgent
+
+agent = OptionsAgent(llm_provider="anthropic")
+
+# Price an option
+result = agent.price(
+    option_type="call",
+    strike=100,
+    spot=105,
+    expiry_days=30,
+    risk_free_rate=0.05,
+    volatility=0.20,
+    model="black_scholes",
+)
+
+print(f"Price: ${result.price:.2f}")
+print(f"Delta: {result.delta:.4f}")
+print(f"Gamma: {result.gamma:.4f}")
+print(f"Theta: {result.theta:.4f}")
+print(f"Vega: {result.vega:.4f}")
+print(f"Rho: {result.rho:.4f}")
+```
+
+## Greeks Analysis
+
+```python
+# Full Greeks surface
+surface = agent.greeks_surface(
+    strike=100,
+    spot_range=(80, 120),
+    expiry_range=(7, 90),  # days
+    volatility=0.25,
+)
+
+surface.plot_delta_surface("delta_surface.png")
+surface.plot_gamma_surface("gamma_surface.png")
+surface.plot_theta_decay("theta_decay.png")
+```
+
+## Strategy Evaluation
+
+```python
+# Evaluate an options strategy
+strategy = agent.evaluate_strategy(
+    legs=[
+        {"type": "call", "strike": 100, "action": "buy", "qty": 1},
+        {"type": "call", "strike": 110, "action": "sell", "qty": 1},
+    ],
+    spot=105,
+    expiry_days=30,
+    volatility=0.20,
+)
+
+print(f"Strategy: {strategy.name}")  # Bull Call Spread
+print(f"Max profit: ${strategy.max_profit:.2f}")
+print(f"Max loss: ${strategy.max_loss:.2f}")
+print(f"Breakeven: ${strategy.breakeven:.2f}")
+
+strategy.plot_payoff("payoff.png")
+strategy.plot_pnl_scenarios("scenarios.png")
+```
+
+## Implied Volatility
+
+```python
+# Calculate implied volatility
+iv = agent.implied_volatility(
+    market_price=5.50,
+    option_type="call",
+    strike=100,
+    spot=105,
+    expiry_days=30,
+    risk_free_rate=0.05,
+)
+print(f"Implied volatility: {iv:.2%}")
+
+# Volatility smile/surface
+vol_surface = agent.volatility_surface(
+    ticker="SPY",
+    date="2025-03-10",
+)
+vol_surface.plot("vol_surface.png")
+```
+
+## Use Cases
+
+1. **Options pricing**: Black-Scholes and numerical methods
+2. **Risk management**: Greeks and portfolio risk metrics
+3. **Strategy analysis**: P&L profiles and breakeven analysis
+4. **Volatility analysis**: IV surfaces and skew analysis
+5. **Education**: Interactive derivatives teaching tool
+
+## References
+
+- [Options Analytics Agent](https://github.com/options-analytics/options-agent)
+- [QuantLib](https://www.quantlib.org/) — Quantitative finance library