@wentorai/research-plugins 1.1.0 → 1.2.0

package/skills/domains/education/academic-study-methods/SKILL.md

@@ -0,0 +1,228 @@
+---
+name: academic-study-methods
+description: "Evidence-based study techniques for academic learning and retention"
+metadata:
+  openclaw:
+    emoji: "📚"
+    category: "domains"
+    subcategory: "education"
+    keywords: ["study methods", "learning techniques", "spaced repetition", "active recall", "academic performance", "metacognition"]
+    source: "https://clawhub.ai/ivangdavila/studying"
+---
+
+# Evidence-Based Academic Study Methods
+
+## Overview
+
+Decades of cognitive psychology research have identified which study techniques reliably improve learning and retention, and which popular methods are largely ineffective. This guide covers the most effective evidence-based strategies — spaced repetition, active recall, interleaving, elaboration, and concrete examples — with practical implementation advice for graduate students and researchers.
+
+## Effectiveness Ranking
+
+Based on Dunlosky et al. (2013) comprehensive review of 10 learning techniques:
+
+| Technique | Effectiveness | Effort | Why It Works |
+|-----------|-------------|--------|-------------|
+| **Practice testing** (active recall) | High | Medium | Strengthens retrieval pathways |
+| **Distributed practice** (spacing) | High | Low | Exploits spacing effect in memory consolidation |
+| **Interleaved practice** | Moderate-High | Medium | Improves discrimination between concepts |
+| **Elaborative interrogation** | Moderate | Low | Generates explanatory connections |
+| **Self-explanation** | Moderate | Medium | Forces integration with prior knowledge |
+| Summarization | Low | Medium | Too passive; rarely deep enough |
+| Highlighting | Low | Low | Creates illusion of learning |
+| Rereading | Low | Low | Recognition ≠ recall |
+| Keyword mnemonic | Low-Moderate | High | Works for vocabulary, not concepts |
+
+## Core Techniques
+
+### 1. Active Recall (Practice Testing)
+
+Instead of rereading notes, test yourself:
+
+```markdown
+## Implementation Strategies
+
+Flashcards:
+  - Front: Question or concept name
+  - Back: Full explanation (not just definition)
+  - Tool: Anki (spaced repetition built-in)
+  - Rule: If you can explain it without looking, you know it
+
+Blank page method:
+  1. Close all materials
+  2. Write everything you know about a topic from memory
+  3. Open materials and identify gaps
+  4. Focus next study session on the gaps
+
+Practice problems:
+  - Work through problems WITHOUT looking at solutions first
+  - Check solutions only after attempting
+  - Struggle is productive — it strengthens memory
+
+Cornell Notes method:
+  | Cue Column (30%) | Notes Column (70%)            |
+  |-------------------|-------------------------------|
+  | Key questions      | Detailed notes from lecture    |
+  | After class:       | Cover notes, use cues to recall|
+  | Summary section at bottom (written from memory)     |
+```
+
+### 2. Spaced Repetition
+
+Distribute study over time instead of cramming:
+
+```
+Cramming (massed practice):
+  Day 1: Study 4 hours → Exam Day 2 → Forget by Day 10
+
+Spaced practice:
+  Day 1: Study 1 hour
+  Day 3: Review 30 min
+  Day 7: Review 20 min
+  Day 14: Review 15 min → Retained for months
+
+Optimal spacing intervals (expanding):
+  1st review: 1 day after initial study
+  2nd review: 3 days after 1st review
+  3rd review: 7 days after 2nd review
+  4th review: 21 days after 3rd review
+  5th review: 63 days after 4th review
+```
+
+**Anki settings for academic material**:
+
+```
+Steps: 1 10 (learning steps in minutes)
+Graduating interval: 1 day
+Easy interval: 4 days
+Starting ease: 250%
+Maximum interval: 180 days (for course material)
+                  365 days (for long-term knowledge)
+New cards/day: 20-30 (adjust to workload)
+```
+
+### 3. Interleaving
+
+Mix different topics or problem types in a single study session:
+
+```
+Blocked practice (less effective):
+  Session 1: 20 calculus problems (all integration)
+  Session 2: 20 calculus problems (all differentiation)
+
+Interleaved practice (more effective):
+  Session 1: Mix of integration, differentiation, and series problems
+  Session 2: Same mix in different order
+
+Why: Forces your brain to select the right strategy, not just apply
+     the same procedure repeatedly
+```
+
+### 4. Elaborative Interrogation
+
+Ask "why" and "how" questions while studying:
+
+```markdown
+Instead of:
+  "The hippocampus is involved in memory formation."
+
+Ask yourself:
+  - WHY is the hippocampus particularly suited for this role?
+  - HOW does it interact with the prefrontal cortex?
+  - What would happen IF the hippocampus were damaged?
+  - How does this RELATE to what I learned about long-term potentiation?
+  - Can I think of a CONCRETE EXAMPLE of this process?
+```
+
+### 5. The Feynman Technique
+
+```
+Step 1: Choose a concept
+Step 2: Explain it as if teaching a 12-year-old
+  - Use simple language
+  - No jargon
+  - Draw diagrams
+Step 3: Identify gaps (where you stumble or use vague language)
+Step 4: Go back to source material for those specific gaps
+Step 5: Simplify and refine your explanation
+Step 6: Repeat until you can explain it simply and completely
+```
+
+## Weekly Study Schedule Template
+
+```markdown
+## Semester Planning
+
+For each course:
+  Hours/week = Credit hours × 2-3 (e.g., 3-credit course = 6-9 hours)
+  Split: 40% new material, 40% practice/problems, 20% review
+
+## Weekly Template (Graduate Student)
+
+Monday:    [Course A] New material + elaboration notes
+Tuesday:   [Course B] New material + elaboration notes
+Wednesday: [Course A] Practice problems (interleaved)
+           [Course B] Spaced review (Anki)
+Thursday:  [Research] Literature reading + annotation
+Friday:    [Course B] Practice problems
+           [Course A] Spaced review (Anki)
+Saturday:  [Research] Writing + data analysis
+Sunday:    Rest / light review (Anki only, 15 min)
+```
+
+## Reading Academic Papers
+
+```markdown
+## Three-Pass Method (Keshav 2007)
+
+Pass 1 (5-10 min): Skim
+  - Title, abstract, introduction, conclusions
+  - Section headings and figure captions
+  - Decide: relevant? Read further?
+
+Pass 2 (30-60 min): Comprehend
+  - Read everything except proofs/details
+  - Annotate key claims and evidence
+  - Note unfamiliar references to follow up
+  - Summarize main contribution in your own words
+
+Pass 3 (2-4 hours): Reproduce
+  - Verify every assumption and derivation
+  - Mentally re-create the work
+  - Identify strengths and weaknesses
+  - Note ideas for follow-up research
+```
+
+## Exam Preparation
+
+```markdown
+## 2-Week Exam Strategy
+
+Week 2 before:
+  - Review all lecture notes (one pass)
+  - Create summary sheets per topic
+  - Start Anki cards for key concepts
+  - Identify weak areas from practice problems
+
+Week 1 before:
+  - Focus on weak areas identified
+  - Work through past exams under timed conditions
+  - Teach concepts to study partner
+  - Daily Anki reviews (30 min)
+
+Day before:
+  - Light review only (30-60 min)
+  - No new material
+  - Prepare logistics (location, materials)
+  - Sleep ≥ 7 hours (memory consolidation requires sleep)
+
+Exam day:
+  - Brief Anki review (10 min)
+  - Arrive early, stay calm
+```
+
+## References
+
+- Dunlosky, J., et al. (2013). "Improving students' learning with effective learning techniques." *Psychological Science in the Public Interest*, 14(1), 4-58.
+- Keshav, S. (2007). "How to Read a Paper." *ACM SIGCOMM Computer Communication Review*, 37(3), 83-84.
+- Brown, P. C., et al. (2014). *Make It Stick: The Science of Successful Learning*. Harvard UP.
+- [Anki Spaced Repetition Software](https://apps.ankiweb.net/)

package/skills/domains/education/edumcp-guide/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: edumcp-guide
+description: "MCP server for educational content and learning management"
+metadata:
+  openclaw:
+    emoji: "🎓"
+    category: "domains"
+    subcategory: "education"
+    keywords: ["education MCP", "learning management", "course content", "educational AI", "tutoring", "assessment"]
+    source: "https://github.com/edumcp/edumcp"
+---
+
+# EduMCP Guide
+
+## Overview
+
+EduMCP is an MCP server that provides educational content management and learning assistance capabilities to AI agents. It enables course content retrieval, quiz generation, learning progress tracking, and adaptive tutoring workflows. Designed for educational researchers and EdTech developers building AI-powered learning systems.
+
+## MCP Configuration
+
+```json
+{
+  "mcpServers": {
+    "edumcp": {
+      "command": "npx",
+      "args": ["@edumcp/mcp-server"],
+      "env": {
+        "CONTENT_PATH": "./course_materials"
+      }
+    }
+  }
+}
+```
+
+## Features
+
+```markdown
+### Content Management
+- Course material indexing and retrieval
+- Lecture note search (full-text + semantic)
+- Syllabus parsing and topic extraction
+- Resource recommendation by topic
+
+### Assessment Generation
+- Quiz/exam question generation from content
+- Multiple question types (MCQ, short answer, essay)
+- Difficulty calibration
+- Answer key generation with explanations
+
+### Learning Analytics
+- Student progress tracking
+- Knowledge gap identification
+- Learning path recommendations
+- Performance analytics
+
+### Tutoring Support
+- Concept explanation at multiple levels
+- Step-by-step problem solving
+- Misconception detection
+- Socratic questioning
+```
+
+## Use Cases
+
+1. **Course design**: AI-assisted curriculum development
+2. **Assessment**: Automated quiz and exam generation
+3. **Tutoring**: Adaptive explanation and guidance
+4. **Analytics**: Learning progress analysis
+5. **Research**: Educational AI system development
+
+## References
+
+- [EduMCP GitHub](https://github.com/edumcp/edumcp)
+- [MCP Specification](https://modelcontextprotocol.io/)

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)