Loading...
Loading...
Found 286 Skills
Comprehensive skill for Microsoft GraphRAG - modular graph-based RAG system for reasoning over private datasets
Analyze weight loss data, calculate metabolic rate, track calorie deficit, manage weight loss stages
Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.
Comprehensive guide to Spark Structured Streaming for production workloads. Use when building streaming pipelines, implementing real-time data processing, handling stateful operations, or optimizing streaming performance.
Visualize your highlights and their connections in an interactive 2D graph
Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.
Deep-dive into analyst estimates and revision trends for any stock using Yahoo Finance data. Use when the user wants to understand analyst estimate direction, how EPS or revenue forecasts changed over time, compare estimate distributions, or analyze growth projections across periods. Triggers: "estimate analysis for AAPL", "analyst estimate trends for NVDA", "EPS revisions for TSLA", "how have estimates changed for MSFT", "estimate revisions", "EPS trend", "revenue estimates", "consensus changes", "analyst estimates", "estimate distribution", "growth estimates for", "estimate momentum", "revision trend", "forward estimates", "next quarter estimates", "annual estimates", "estimate spread", "bull vs bear estimates", "estimate range", or any request about tracking or comparing analyst estimates/revisions. Use this skill when the user asks about estimates beyond a simple lookup — if they want context, trends, or analysis, this is the right skill.
Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.
Use when about to use jq, curl, sed, awk, or bash for JSON/XML processing, API calls, data transformation, or file processing - before writing any bash commands for data manipulation
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Detect IBD-style Distribution Days for QQQ/SPY (close down at least 0.2% on higher volume), track 25-session expiration and 5% invalidation, count d5/d15/d25 clusters, classify market risk (NORMAL/CAUTION/HIGH/SEVERE), and emit TQQQ/QQQ exposure recommendations. Use after market close, before TQQQ exposure changes, or as input to FTD/market-state frameworks. Does not execute trades.
Aggregated news, regulatory filings, and Longbridge-community discussion for a single stock — classified into catalyst / regulatory / strategic / financial / opinion / other, with a fact-only key-takeaway summary and a sentiment skew. Falls back to WebSearch only when data is sparse or stale, and labels the source. Triggers: "X 最近新闻", "X 公告", "市场对 X 财报怎么看", "X 社区讨论", "X 公司动态", "市场情绪", "最近怎么了", "X 最近新聞", "X 公告", "市場對 X 財報怎麼看", "X 社區討論", "recent news", "company filings", "market reaction", "what is everyone saying about X", "community sentiment", "8-K", "港交所披露", "earnings reaction".